Search

PURPOSE: This study uses deep neural network-generated rim-to-disc area ratio (RADAR) measurements and the disc damage likelihood scale (DDLS) to measure the rate of optic disc rim loss in a large cohort of glaucoma patients. METHODS: A deep neural network was used to calculate RADAR and DDLS for each optic disc photograph (ODP). Patient demographics, diagnosis, intraocular pressure (IOP), and mean deviation (MD) from perimetry were analyzed as risk factors for faster progression of RADAR. Receiver operating characteristic (ROC) curves were used to compare RADAR and DDLS in their utility to distinguish glaucoma from glaucoma suspect (GS) and for detecting glaucoma progression. RESULTS: A total of 13,679 ODPs with evidence of glaucomatous optic nerve damage from 4106 eyes of 2407 patients with glaucoma or GS were included. Of these eyes, 3264 (79.5%) had a diagnosis of glaucoma, and 842 (20.5%) eyes were GS. Mean ± SD baseline RADAR of GS and glaucoma were 0.67 ± 0.13 and 0.57 ± 0.18, respectively (P < 0.001). Older age, greater IOP fluctuation, baseline MD, right eye, and diagnosis of secondary open-angle glaucoma were associated with slope of RADAR. The mean baseline DDLS of GS and glaucoma were 3.78 and 4.39, respectively. Both RADAR and DDLS showed a less steep slope in advanced glaucoma. In glaucoma, the change of RADAR and DDLS correlated with the corresponding change in MD. RADAR and DDLS had a similar ability to discriminate glaucoma from GS and detect disease progression. Area under the ROC curve of RADAR and DDLS was 0.658 and 0.648. CONCLUSIONS: Automated calculation of RADAR and DDLS with a neural network can be used to evaluate the extent and long-term rate of optic disc rim loss and is further evidence of long-term nerve fiber loss in treated patients with glaucoma. TRANSLATIONAL RELEVANCE: Our study provides a large clinic-based experience for RADAR and DDLS measurements in GS and glaucoma with a neural network.

A neural network was developed to detect and characterize bowel obstruction, a common cause of acute abdominal pain. In this retrospective study, 202 CT scans of 165 patients with bowel obstruction from March to June 2022 were included and partitioned into training and test data sets. A multi-channel neural network was trained to segment the gastrointestinal tract, and to predict the diameter and the longitudinal position (longitude) along the gastrointestinal tract using a novel embedding. Its performance was compared to manual segmentations using the Dice score, and to manual measurements of the diameter and longitude using intraclass correlation coefficients (ICC). ROC curves as well as sensitivity and specificity were calculated for diameters above a clinical threshold for obstruction, and for longitudes corresponding to small bowel. In the test data set, Dice score for segmentation of the gastrointestinal tract was 78 ± 8%. ICC between measured and predicted diameters was 0.72, indicating moderate agreement. ICC between measured and predicted longitude was 0.85, indicating good agreement. AUROC was 0.90 for detection of dilated bowel, and was 0.95 and 0.90 for differentiation of the proximal and distal gastrointestinal tract respectively. Overall sensitivity and specificity for dilated small bowel were 0.83 and 0.90. Since obstruction is diagnosed based on the diameter and longitude of the bowel, this neural network and embedding may enable detection and characterization of this important disease on CT.

Purpose: To investigate the validity of the Physical Activity Questionnaire for Older Children (PAQ-C) to assess the moderate- to vigorous-intensity physical activity (MVPA) level of children and adolescents diagnosed with HIV and propose cut-points, with accelerometer measures as the reference method. Method: Children and adolescents, aged 8–14 years (mean age = 12.21 y, SD = 2.09), diagnosed with HIV by vertical transmission, participated in the study. MVPA was investigated through the PAQ-C and triaxial accelerometer (ActiGraph GT3X+). Receiver operating characteristic curve and sensitivity and specificity values were used to identify a cut-point for PAQ-C to distinguish participants meeting MVPA guidelines. Results: Fifty-six children and adolescents participated in the study. Among those, 16 met MVPA guidelines. The PAQ-C score was significantly related to accelerometry-derived MVPA (ρ =.506, P <.001). The PAQ-C score cut-point of 2.151 (sensitivity = 0.625, specificity = 0.875) was able to discriminate between those who met MVPA guidelines and those that did not (area under the curve = 0.751, 95% confidence interval, 0.616–0.886). Conclusion: The PAQ-C was useful to investigate MVPA among children and adolescents diagnosed with HIV and to identify those who meet MVPA guidelines. [ABSTRACT FROM AUTHOR]

AIM: We tested the hypothesis that visual field (VF) progression can be predicted with a deep learning model based on longitudinal pairs of optic disc photographs (ODP) acquired at earlier time points during follow-up. METHODS: 3919 eyes (2259 patients) with ≥2 ODPs at least 2 years apart, and ≥5 24-2 VF exams spanning ≥3 years of follow-up were included. Serial VF mean deviation (MD) rates of change were estimated starting at the fifth visit and subsequently by adding visits until final visit. VF progression was defined as a statistically significant negative slope at two consecutive visits and final visit. We built a twin-neural network with ResNet50-backbone. A pair of ODPs acquired up to a year before the VF progression date or the last VF in non-progressing eyes were included as input. Primary outcome measures were area under the receiver operating characteristic curve (AUC) and model accuracy. RESULTS: The average (SD) follow-up time and baseline VF MD were 8.1 (4.8) years and -3.3 (4.9) dB, respectively. VF progression was identified in 761 eyes (19%). The median (IQR) time to progression in progressing eyes was 7.3 (4.5-11.1) years. The AUC and accuracy for predicting VF progression were 0.862 (0.812-0.913) and 80.0% (73.9%-84.6%). When only fast-progressing eyes were considered (MD rate < -1.0 dB/year), AUC increased to 0.926 (0.857-0.994). CONCLUSIONS: A deep learning model can predict subsequent glaucoma progression from longitudinal ODPs with clinically relevant accuracy. This model may be implemented, after validation, for predicting glaucoma progression in the clinical setting.

BACKGROUND: Endometriosis is considered as a systemic disease with the presence of proinflammatory cytokines in the circulation, which drives hypercoagulable state of endometriosis. Currently, endometriosis is classified into four stages: I (minimal), II (mild), III (moderate) and IV (severe). The aim of this study is to investigate the correlations between inflammatory markers and coagulation factors in patients diagnosed of endometriosis with stage IV. METHODS: This retrospective case-control study included 171 endometriosis patients with stage IV and 184 controls. Continuous data were expressed by mean ± standard deviation. Mann-Whitney U and χ2 tests were used to compare the medians and frequencies among the groups. Spearman analysis was conducted to determine the correlation among the measured parameters. The diagnostic values of the parameters differentiating endometriomas were tested by receiver operating characteristic (ROC) curve. RESULTS: The time of activated partial thromboplastin time (APTT) was decreased and the concentration of fibrinogen (FIB) and neutrophil-to-lymphocyte ratio (NLR) were increased in women of endometriosis with stage IV. The APTT were negatively correlated with NLR while the concentrations of FIB were positively correlated with NLR. The ROC analysis showed that the Area under the curve (AUC) of FIB was 0.766 (95% confidence interval:0.717-0.814) with sensitivity and specificity reaching 86.5 and 60.9%, respectively. The AUC of CA125 and CA199 was 0.638 (95% confidence interval: 0.578-0.697), 0.71 (95% confidence interval: 0.656-0.763) with sensitivity and specificity reaching 40.9 and 91.8%, 80.7 and 56.5% respectively. The combination of these factors showed the highest AUC of 0.895 (0.862-0.927) with sensitivity of 88.9% and specificity of 77.7%. CONCLUSION: In the present study, we found that inflammatory factors showed significant correlation with APTT or FIB in endometriosis with stage IV. Moreover, the coagulation factors combined with CA125 and CA199 were more reliable for identifying the endometriosis with stage IV.

BACKGROUND: Cerebral vasospasm (CV) is a feared complication which occurs after 20-40% of subarachnoid haemorrhage (SAH). It is standard practice to admit patients with SAH to intensive care for an extended period of resource-intensive monitoring. We used machine learning to predict CV requiring verapamil (CVRV) in the largest and only multi-center study to date. METHODS: Patients with SAH admitted to UCLA from 2013 to 2022 and a validation cohort from VUMC from 2018 to 2023 were included. For each patient, 172 unique intensive care unit (ICU) variables were extracted through the primary endpoint, namely first verapamil administration or no verapamil. At each institution, a light gradient boosting machine (LightGBM) was trained using five-fold cross validation to predict the primary endpoint at various hospitalization timepoints. FINDINGS: A total of 1750 patients were included from UCLA, 125 receiving verapamil. LightGBM achieved an area under the ROC (AUC) of 0.88 > 1 week in advance and ruled out 8% of non-verapamil patients with zero false negatives. Our models predicted no CVRV vs CVRV within three days vs CVRV after three days with AUCs = 0.88, 0.83, and 0.88, respectively. From VUMC, 1654 patients were included, 75 receiving verapamil. VUMC predictions averaged within 0.01 AUC points of UCLA predictions. INTERPRETATION: We present an accurate and early predictor of CVRV using machine learning with multi-center validation. This represents a significant step towards optimized clinical management and resource allocation in patients with SAH. FUNDING: Robert E. Freundlich is supported by National Center for Advancing Translational Sciences federal grant UL1TR002243 and National Heart, Lung, and Blood Institute federal grant K23HL148640; these funders did not play any role in this study. The National Institutes of Health supports Vanderbilt University Medical Center which indirectly supported these research efforts. Neither this study nor any other authors personally received financial support for the research presented in this manuscript. No support from pharmaceutical companies was received.

This study compared the prognostic value of quantified thoracic artery calcium (TAC) including aortic arch on chest CT and coronary artery calcium (CAC) score on ECG-gated cardiac CT.MethodsA total of 2412 participants who underwent both chest CT and ECG-gated cardiac CT at the same period were included in the Multi-Ethnic Study of Atherosclerosis Exam 5. All participants were monitored for incident atherosclerotic cardiovascular disease (ASCVD) events. TAC is defined as calcification in the ascending aorta, aortic arch and descending aorta on chest CT. The quantification of TAC was measured using the Agatston method. Time-dependent receiver-operating characteristic (ROC) curves were used to compare the prognostic value of TAC and CAC scores.ResultsParticipants were 69±9 years of age and 47% were male. The Spearman correlation between TAC and CAC scores was 0.46 (p

Polygenic scores (PGSs) summarize the combined effect of common risk variants and are associated with breast cancer risk in patients without identifiable monogenic risk factors. One of the most well-validated PGSs in breast cancer to date is PGS313, which was developed from a Northern European biobank but has shown attenuated performance in non-European ancestries. We further investigate the generalizability of the PGS313 for American women of European (EA), African (AFR), Asian (EAA), and Latinx (HL) ancestry within one institution with a singular electronic health record (EHR) system, genotyping platform, and quality control process. We found that the PGS313 achieved overlapping areas under the receiver operator characteristic (ROC) curve (AUCs) in females of HL (AUC = 0.68, 95% confidence interval [CI] = 0.65-0.71) and EA ancestry (AUC = 0.70, 95% CI = 0.69-0.71) but lower AUCs for the AFR and EAA populations (AFR: AUC = 0.61, 95% CI = 0.56-0.65; EAA: AUC = 0.64, 95% CI = 0.60-0.680). While PGS313 is associated with hormone-receptor-positive (HR+) disease in EA Americans (odds ratio [OR] = 1.42, 95% CI = 1.16-1.64), this association is lost in African, Latinx, and Asian Americans. In summary, we found that PGS313 was significantly associated with breast cancer but with attenuated accuracy in women of AFR and EAA descent within a singular health system in Los Angeles. Our work further highlights the need for additional validation in diverse cohorts prior to the clinical implementation of PGSs.

BackgroundOxygen saturation (Spo2) screening has not led to earlier detection of critical congenital heart disease (CCHD). Adding pulse oximetry features (ie, perfusion data and radiofemoral pulse delay) may improve CCHD detection, especially coarctation of the aorta (CoA). We developed and tested a machine learning (ML) pulse oximetry algorithm to enhance CCHD detection.Methods and resultsSix sites prospectively enrolled newborns with and without CCHD and recorded simultaneous pre- and postductal pulse oximetry. We focused on models at 1 versus 2 time points and with/without pulse delay for our ML algorithms. The sensitivity, specificity, and area under the receiver operating characteristic curve were compared between the Spo2-alone and ML algorithms. A total of 523 newborns were enrolled (no CHD, 317; CHD, 74; CCHD, 132, of whom 21 had isolated CoA). When applying the Spo2-alone algorithm to all patients, 26.2% of CCHD would be missed. We narrowed the sample to patients with both 2 time point measurements and pulse-delay data (no CHD, 65; CCHD, 14) to compare ML performance. Among these patients, sensitivity for CCHD detection increased with both the addition of pulse delay and a second time point. All ML models had 100% specificity. With a 2-time-points+pulse-delay model, CCHD sensitivity increased to 92.86% (P=0.25) compared with Spo2 alone (71.43%), and CoA increased to 66.67% (P=0.5) from 0. The area under the receiver operating characteristic curve for CCHD and CoA detection significantly improved (0.96 versus 0.83 for CCHD, 0.83 versus 0.48 for CoA; both P=0.03) using the 2-time-points+pulse-delay model compared with Spo2 alone.ConclusionsML pulse oximetry that combines oxygenation, perfusion data, and pulse delay at 2 time points may improve detection of CCHD and CoA within 48 hours after birth.RegistrationURL: https://www.clinicaltrials.gov/study/NCT04056104?term=NCT04056104&rank=1; Unique identifier: NCT04056104.

Background & aimsDiscerning whether laryngeal symptoms result from gastroesophageal reflux is clinically challenging and a reliable tool to stratify patients is needed. We aimed to develop and validate a model to predict the likelihood of gastroesophageal reflux disease (GERD) among patients with chronic laryngeal symptoms.MethodsThis multicenter international study collected data from adults with chronic laryngeal symptoms who underwent objective testing (upper gastrointestinal endoscopy and/or ambulatory reflux monitoring) between March 2018 and May 2023. The training phase identified a model with optimal receiver operating characteristic curves, and β coefficients informed a weighted model. The validation phase assessed performance characteristics of the weighted model.ResultsA total of 856 adults, 304 in the training cohort and 552 in the validation cohort, were included. In the training phase, the optimal predictive model (area under the curve, 0.68; 95% CI, 0.62-0.74), was the Cough, Overweight/obesity, Globus, Hiatal Hernia, Regurgitation, and male seX (COuGH RefluX) score, with a lower threshold of 2.5 and an upper threshold of 5.0 to predict proven GERD. In the validation phase, the COuGH RefluX score had an area under the curve of 0.67 (95% CI, 0.62-0.71), with 79% sensitivity and 81% specificity for proven GERD.ConclusionsThe externally validated COuGH RefluX score is a clinically practical model to predict the likelihood of proven GERD. The score classifies most patients with chronic laryngeal symptoms as low/high likelihood of proven GERD, with only 38% remaining as indeterminate. Thus, the COuGH RefluX score can guide diagnostic strategies and reduce inappropriate proton pump inhibitor use or testing for patients referred for evaluation of chronic laryngeal symptoms.

BackgroundS100A8 is a melanoma biomarker expressed in the melanoma-associated epidermal keratinocytes, but its diagnostic utility has not been compared with other biomarkers, including PRAME.ObjectivesTo compare the utility of S100A8 and PRAME immunohistochemistry (IHC) in the differential diagnosis of melanoma and naevi in a case-control study.MethodsA previously described cohort of 209 melanomas (case samples) and naevi (control samples) dual-immunostained for S100A8 and PRAME were included. For S100A8, previously reported scores indicating the proportion of tumour-associated epidermis stained (0 = indeterminate; 1 = 0-4%; 2 = 5-25%; 3 = 26-50%; 4 = 51-75%; 5 = > 75%) were utilized. PRAME IHC was reviewed by at least two reviewers and a consensus score assigned, with score indicating the proportion of tumour stained (0 = indeterminate; 1 = 0%; 2 = 1-50%; 3 = > 50%). A positive test was defined as > 50% staining.ResultsThe area under the receiver operating characteristic curves for S100A8 (0.833) and PRAME (0.874) were not significantly different from each other (P = 0.22). The diagnostic sensitivity and specificity were 42.4% [95% confidence interval (CI) 32.6-52.8%] and 98.2% (95% CI 93.6-99.8%) for S100A8, and 79.8% (95% CI 70.5-87.2%) and 87.3% (95% CI 79.6-92.9%) for PRAME, respectively. A combined test requiring both S100A8 and PRAME IHC positivity had a sensitivity of 39.4% (95% CI 29.7-49.7%) and specificity of 99.1% (95% CI 95.0-100.0%).ConclusionsS100A8 and PRAME have utility in the diagnostic workup of melanoma, with S100A8 being more specific and PRAME being more sensitive when using this threshold. Our findings suggest that these two immunohistochemical markers may favourably complement one another to improve the detection of melanoma.

BACKGROUND: With the availability of disease-modifying therapies for Alzheimers disease (AD), it is important for clinicians to have tests to aid in AD diagnosis, especially when the presence of amyloid pathology is a criterion for receiving treatment. METHODS: High-throughput, mass spectrometry-based assays were used to measure %p-tau217 and amyloid beta (Aβ)42/40 ratio in blood samples from 583 individuals with suspected AD (53% positron emission tomography [PET] positive by Centiloid > 25). An algorithm (PrecivityAD2 test) was developed using these plasma biomarkers to identify brain amyloidosis by PET. RESULTS: The area under the receiver operating characteristic curve (AUC-ROC) for %p-tau217 (0.94) was statistically significantly higher than that for p-tau217 concentration (0.91). The AUC-ROC for the PrecivityAD2 test output, the Amyloid Probability Score 2, was 0.94, yielding 88% agreement with amyloid PET. Diagnostic performance of the APS2 was similar by ethnicity, sex, age, and apoE4 status. DISCUSSION: The PrecivityAD2 blood test showed strong clinical validity, with excellent agreement with brain amyloidosis by PET.

UNLABELLED: Hip fracture risk assessment is an important but challenging task. Quantitative CT-based patient-specific finite element (FE) analysis (FEA) incorporates bone geometry and bone density in the proximal femur. We developed a global FEA-computed fracture risk index to increase the prediction accuracy of hip fracture incidence. PURPOSE: Quantitative CT-based patient-specific finite element (FE) analysis (FEA) incorporates bone geometry and bone density in the proximal femur to compute the force (fracture load) and energy necessary to break the proximal femur in a particular loading condition. The fracture loads and energies-to-failure are individually associated with incident hip fracture, and provide different structural information about the proximal femur. METHODS: We used principal component analysis (PCA) to develop a global FEA-computed fracture risk index that incorporates the FEA-computed yield and ultimate failure loads and energies-to-failure in four loading conditions of 110 hip fracture subjects and 235 age- and sex-matched control subjects from the AGES-Reykjavik study. Using a logistic regression model, we compared the prediction performance for hip fracture based on the stratified resampling. RESULTS: We referred the first principal component (PC1) of the FE parameters as the global FEA-computed fracture risk index, which was the significant predictor of hip fracture (p-value

The proposed symptoms for Neurobehavioral Disorder Associated with Prenatal Alcohol Exposure (ND-PAE) were evaluated in children who participated in the Collaboration on Fetal Alcohol Spectrum Disorders Prevalence study. Children at-risk for ND-PAE (n = 204) were contrasted to children with no prenatal alcohol exposure, alcohol-related dysmorphia or growth deficits (n = 908). Symptoms were defined based on neuropsychological testing using two diagnostic threshold levels (1.0 and 1.5 STD). Individuals at risk for ND-PAE had higher endorsement rates of the self-regulation and adaptive impairments at the 1.0 threshold and of the neurocognitive and self-regulation impairments at the 1.5 threshold. Endorsement of the disorder significantly differed at the 1.0 threshold. Receiver operating characteristic curve analysis indicated that having an IQ below 70 was not predictive of the diagnosis but modifications of the IQ criterion improved predictive validity. Discrimination validity was poor without documentation of PAE which continues to be a necessity for a diagnosis of ND-PAE.

Fluid bolus therapy (FBT) is fundamental to the management of circulatory shock in critical care but balancing the benefits and toxicities of FBT has proven challenging in individual patients. Improved predictors of the hemodynamic response to a fluid bolus, commonly referred to as a fluid challenge, are needed to limit non-beneficial fluid administration and to enable automated clinical decision support and patient-specific precision critical care management. In this study we retrospectively analyzed data from 394 fluid boluses from 58 pigs subjected to either hemorrhagic or distributive shock. All animals had continuous blood pressure and cardiac output monitored throughout the study. Using this data, we developed a machine learning (ML) model to predict the hemodynamic response to a fluid challenge using only arterial blood pressure waveform data as the input. A Random Forest binary classifier referred to as the ML fluid responsiveness algorithm (MLFRA) was trained to detect fluid responsiveness (FR), defined as a ≥ 15% change in cardiac stroke volume after a fluid challenge. We then compared its performance to pulse pressure variation, a commonly used metric of FR. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC), confusion matrix metrics, and calibration curves plotting predicted probabilities against observed outcomes. Across multiple train/test splits and feature selection methods designed to assess performance in the setting of small sample size conditions typical of large animal experiments, the MLFRA achieved an average AUROC, recall (sensitivity), specificity, and precision of 0.82, 0.86, 0.62. and 0.76, respectively. In the same datasets, pulse pressure variation had an AUROC, recall, specificity, and precision of 0.73, 0.91, 0.49, and 0.71, respectively. The MLFRA was generally well-calibrated across its range of predicted probabilities and appeared to perform equally well across physiologic conditions. These results suggest that ML, using only inputs from arterial blood pressure monitoring, may substantially improve the accuracy of predicting FR compared to the use of pulse pressure variation. If generalizable, these methods may enable more effective, automated precision management of critically ill patients with circulatory shock.

Key points Spontaneous cerebrospinal fluid rhinorrhea (sCSFR) is often accompanied by an increase in intracranial pressure (ICP). The widening of optic nerve sheath diameter (ONSD) is an indicator of increased ICP. Using CT to measure ONSD is a simple and noninvasive auxiliary method for determining high ICP in sCSFR patients. Spontaneous cerebrospinal fluid rhinorrhea (sCSFR) is often accompanied by an increase in intracranial pressure (ICP).The widening of optic nerve sheath diameter (ONSD) is an indicator of increased ICP.Using CT to measure ONSD is a simple and noninvasive auxiliary method for determining high ICP in sCSFR patients. [ABSTRACT FROM AUTHOR]

Morphological and functional asymmetry of the lower limbs is a well-recognized factor contributing to musculoskeletal injuries among athletes across different levels. However, limited research exists on evaluating foot mobility asymmetry as a potential predictor of such injuries. This study aimed to (1) assess the frequency of foot mobility asymmetries among amateur athletes, (2) investigate the predictive value of foot mobility asymmetry (measured via navicular height drop) for injury risk, and (3) explore the relationship between foot type and injury occurrence. A cross-sectional sampling method was employed to select 45 physically active male amateur athletes (runners and team sports practitioners) from a university. Injury history was retrospectively recorded, and a modified navicular drop test was conducted to classify foot arch height. The predictive power of navicular height drop asymmetry was analyzed using ROC curves, and the relationship between foot type (neutral and defective combinations—pronated or supinated) and injury occurrence was examined using chi-square tests for independence. Multiple logistic regression was applied to calculate injury risk odds ratios across different foot type subgroups. The results revealed a significant frequency (51.1%) of participants with at least one defective foot, including 31.1% with one neutral and one defective foot and 20% with both feet defective. Navicular height drop asymmetry emerged as a valuable predictor of injuries, with a 36% asymmetry identified as the cut-off for increased injury risk (AUC = 0.832, 95% CI: 0.691–0.973, p < 0.001). A significant relationship was found between foot type and injury occurrence. Only one out of 22 participants with neutral feet (4.55%) experienced an injury, compared to 9 out of 14 (64.29%) with one neutral and one defective foot and 5 out of 9 (55.56%) with both feet defective. These differences were statistically significant (χ2 = 16.24, p < 0.001, Cramer's V = 0.60). The odds ratio for injury risk was 37.8 (p = 0.016) for those with asymmetry (one neutral and one defective foot) and 26.3 (p = 0.102) for those with both feet defective, compared to participants with both feet neutral. In clinical practice, these findings suggest that routine screenings for physically active individuals should incorporate foot mobility asymmetry assessment. However, it is essential to integrate this factor with other risk indicators. For individuals exhibiting high asymmetry, general foot defect correction programs may be beneficial, but injury prevention strategies should adopt a more comprehensive approach, focusing on overall fitness and tailored interventions for high-risk individuals. [ABSTRACT FROM AUTHOR]

Introduction Cigarette smoking greatly promotes the progression and poor prognosis of colorectal cancer (CRC) patients, with the molecular mechanism still not fully clear. Methods In this study, CRC cells were exposed to tobacco-specific nitrosamine 4‑(methylnitrosamino)‑1‑(3‑pyridyl)-1‑butanone (NNK), and the differentially expressed smoking-related genes were identified based on both NNK-induced CRC cells and a total of 763 CRC tissues from The Cancer Genome Atlas cohort. Cox regression analysis, receiver operating characteristic curve and Kaplan–Meier plot were used to establish the risk score model for CRC prognosis. Moreover, quantitative real-time–PCR, western blotting, colony formation, migration, and invasion assays were performed to verify the core differentially expressed smoking-related gene and its molecular function in NNK-induced CRC progression. Results Results indicated NNK significantly enhanced CRC cell proliferation, migration and invasion. Moreover, a four-gene signature containing AKR1B10, CALB2, PLAC1, and GNA15 was established as a CRC prognosis marker. Among these four genes, AKR1B10 was further validated as the core gene, and its expression was significantly inhibited after NNK exposure in CRC cells. Results of gene enrichment analysis and western blotting suggested AKR1B10 might reduce the malignant progression of NNK-induced CRC cells by inhibiting the Wnt signaling pathway by promoting E-Cadherin expression and inhibiting the expression of N-Cadherin, β-Catenin, Vimentin, and Snail. Conclusions In conclusion, new four smoking-related genes can be jointly used as prognostic markers for CRC. AKR1B10 served as a tumor suppressor, and can be used as a potential target to inhibit NNK-induced CRC malignant progression by regulating the Wnt signaling pathway. Implications This study demonstrates that tobacco-derived NNK dependence would promote the malignant progression of colorectal cancer by regulating the expressions of the AKR1B10/Wnt signaling pathway. A novel four-gene signature is established for the prognosis prediction of smoking CRC patients. These findings have important translational implications given the continued use of tobacco and the difficulty in smoking cessation worldwide, which can be applied to alleviate the adverse effects induced by tobacco dependence on colorectal cancer patients. [ABSTRACT FROM AUTHOR]

Purpose: Inter-eye variability is a recognized characteristic of Dry Eye Disease (DED) and has been proposed as a diagnostic indicator in clinical practice. This study aimed to assess the diagnostic potential of the absolute difference between eyes in three key diagnostic tests recommended by the Tear Film and Ocular Surface Society Dry Eye Workshop II (TFOS DEWS II) Diagnostic Methodology report: tear film osmolarity, Fluorescein Break-Up Time (FBUT), and ocular surface staining. Methods: A total of 180 participants were included in a cross-sectional study. Before a dry eye examination, participants completed an online self-administered OSDI questionnaire. The TFOS DEWS II diagnostic criteria for DED assessment were used: along with OSDI, osmolarity, FBUT and ocular surface staining were measured in all participants in both eyes following standardized methodology. Based on signs and symptoms, participants were diagnosed as having No DED or DED. After diagnosis, the parameters were computed as the right and left eyes' absolute inter-eye difference (|OD-OS|). Results: Receiver Operating Characteristics analyses for computed parameters were used based on the previous diagnosis. ROC analyses showed that Osmolarity|OD-OS| have a diagnostic capability to differentiate between No DED and DED participants with a cut-off value of 9.5 mOsm/L (AUC = 0.745 ± 0.052, p < 0.003), whereas FBUT|OD-OS| and Corneal Stainning|OD-OS| have not (AUC, both p ≥ 0.160). Conclusion: The present study found that the Osmolarity|OD-OS| parameter could be used as a diagnostic indicator for DED assessment, while the FBUT|OD-OS| and the Corneal Staining|OD-OS| parameters do not have this capability. [ABSTRACT FROM AUTHOR]

Breast cancer is the leading cause of cancer-related mortality among women worldwide. MicroRNAs (miRNAs), short non-coding RNAs, have been implicated in cancer-related processes such as tumor development, metastasis, angiogenesis, and drug resistance. Circulating miRNA-373 demonstrates higher relative exosomal serum levels in breast cancer patients compared to healthy women, making it a potential non-invasive biomarker. Separately, vascular endothelial growth factor (VEGF) is crucial for angiogenesis, and is elevated in breast cancer. In this case–control study, we aimed to investigate the diagnostic accuracy of miRNA-373 and VEGF as biomarkers for early-stage breast cancer detection. Serum samples were collected from 120 participants, comprising 30 breast cancer patients, 30 benign breast tumor patients, and 60 healthy controls, over the period of April 2022 to January 2023. MiRNA-373 expression was analyzed by reverse transcription-quantitative PCR with GAPDH normalisation, while VEGF levels in serum samples were measured by ELISA. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of both biomarkers. MiRNA-373 expression (∆Ct) differed significantly between the three groups (breast cancer: − 12.20 ± 1.11; benign tumors: − 12.79 ± 1.09; controls: − 13.64 ± 0.93). ROC analysis revealed moderate discriminative power for miRNA-373 (specificity = 76.7%; sensitivity = 70.0%; AUC = 0.839) and excellent discriminative power for VEGF (specificity = 85.0%; sensitivity = 90.0%; AUC = 0.944) in distinguishing early-stage breast cancer patients from healthy controls. In summary, this study demonstrates the promising potential of miRNA-373 as an early diagnostic biomarker for breast cancer detection, requiring further validation in larger cohorts. Our findings also reinforce the diagnostic value of circulating VEGF levels for breast cancer screening. [ABSTRACT FROM AUTHOR]

Objective: This study aims to analyze the relationship between papillary thyroid carcinoma (PTC) and various factors. Methods: The study involved two groups—PTC patients and non-PTC controls. We utilized binary logistic regression and Least Absolute Shrinkage and Selection Operator (Lasso) regression for variable selection and risk factor analysis. Correlation analysis was performed using Spearman’s rank correlation. The diagnostic value of thyroid stimulating hormone (TSH) levels for PTC was assessed using Receiver Operating Characteristic (ROC) curves. Results: PTC patients exhibited higher body mass index (BMI) (23.71 vs. 22.66, p<0.05) and TSH levels (3.38 vs. 1.59, p<0.05). Urinary iodine concentration (UIC) was an independent predictor of PTC (OR=1.005, p<0.05). The optimal TSH threshold for PTC diagnosis was 2.4 mIU/L [The Area Under the Curve (AUC)=67.3%, specificity=71.4%, sensitivity=70.1%]. TSH levels positively correlated with BMI (r=0.593, p<0.05) and UIC (r=0.737, p<0.05). Conclusions: UIC may be an independent predictor of PTC, and TSH levels have some diagnostic value for identifying PTC. [ABSTRACT FROM AUTHOR]

The minimal clinically important difference (MCID) is an important concept with big appeal in a field struggling to interpret quality of life (QOL) and other patient-reported outcomes (PRO), is also a bridge between statistics and clinical medicine. This study uses the ROC curve to formulate the MCID value of the Quality of Life Instruments for Chronic Diseases of Systemic lupus erythematosus (QLICD-SLE V2.0) scale. Using the representative item "In general, would you say your health is" of the MOS item short form health survey(SF-36) as an anchor, the questionnaire of QLICD-SLE V2.0 and the anchor item were used to investigate the patients on the first day of hospitalization, and the day before the patient was discharged. 279 patients with lupus erythematosus were participated in this longitudinal follow-up study. The ROC curve was constructed by using the classification based on the anchor item as the gold standard and the difference score of the scale as the test variable. The cut-off point corresponding to the maximum value of the Youden index in the ROC curve is taken as the minimum clinical importance difference (MCID) value of the QLICD-SLE (V2.0) scale. The Results showed that the MCID of physical domain, psychological domain, social domain, general module, specific module and QLICD-SLE (V2.0) total scale are 8.3, 2.3, 2.5, 2.7, 9.2 and 3.2, respectively. Area under the ROC curve of QLICD-SLE (V2.0) is 0.898, P (Area = 0.5) < 0.001, the sensitivity is 100%, the specificity is 66.9%. It concluded that if the total scores after treatments changes at least 3.2 points positively, the treatment intervention can be considered as clinically significant. It is more convincing to use the corresponding cut-off point as the MCID for ROC curve method can visualize the sensitivity and specificity. [ABSTRACT FROM AUTHOR]

The development of new statistical models for the meta‐analysis of diagnostic test accuracy studies is still an ongoing field of research, especially with respect to summary receiver operating characteristic (ROC) curves. In the recently published updated version of the “Cochrane Handbook for Systematic Reviews of Diagnostic Test Accuracy”, the authors point to the challenges of this kind of meta‐analysis and propose two approaches. However, both of them come with some disadvantages, such as the nonstraightforward choice of priors in Bayesian models or the requirement of a two‐step approach where parameters are estimated for the individual studies, followed by summarizing the results. As an alternative, we propose a novel model by applying methods from time‐to‐event analysis. To this task we use the discrete proportional hazard approach to treat the different diagnostic thresholds, that provide means to estimate sensitivity and specificity and are reported by the single studies, as categorical variables in a generalized linear mixed model, using both the logit‐ and the asymmetric cloglog‐link. This leads to a model specification with threshold‐specific discrete hazards, avoiding a linear dependency between thresholds, discrete hazard, and sensitivity/specificity and thus increasing model flexibility. We compare the resulting models to approaches from the literature in a simulation study. While the estimated area under the summary ROC curve is estimated comparably well in most approaches, the results depict substantial differences in the estimated sensitivities and specificities. We also show the practical applicability of the models to data from a meta‐analysis for the screening of type 2 diabetes. [ABSTRACT FROM AUTHOR]

Introduction Musculoskeletal injuries are one of the primary causes of Soldiers' inability to be medically ready, comprising over 80% of such causes. The electronic profile (e-Profile) is the way that musculoskeletal injuries are documented so that commanders will know the type of injury as well as the length of the time that the Soldier will need limited duty. A previous study of e-Profiles in an Army MTF Integrated Pain Management Center showed that the median length of an e-Profile was 30 days. It is in the best interest of the Army to have the Soldier out of the fight the minimum amount of time for recovery to ensure the unit readiness. The goal of this study was to utilize e-Profile data to see if a machine learning model can be developed to determine the appropriate time a Soldier needs to be on profile for a given diagnoses. Materials and Methods Institutional Review Board approval was obtained from the USAMRDC (protocol #M-10966). The initial dataset provided to the research team consisted of a single pipe delimited ("|") text file containing 2.9 million rows of e-Profile data. Linear regression, decision trees, and random forests (RFs) were evaluated to see which model would best predict the number of days needed for an e-Profile. Results Linear regression had an adjusted R-squared of 0.165. The positive predictive value of decision trees (0-to-30-day range of e-Profiles) was 73.6%, and the negative predictive value (30-90 days) was 60.9% with an area under the receiver operating characteristic curve (AUC) of 0.694 for the model. The positive predictive value of RFs was 85.3% (for the 0-30 range), and the negative predictive value was 58.7% (for the 30-90 range) with an AUC of 0.794. An AUC that approaches 1 indicates a more accurate prediction. Conclusions The 3 models (linear regression, decision trees, and RF) studied as part of this project did not predict the days on e-Profile with a high degree of certainty. Future research will focus on adding additional data to the e-Profile dataset in order to improve model accuracy. [ABSTRACT FROM AUTHOR]

Introduction Deployment-limiting medical conditions (DLMCs) such as debilitating injuries and conditions may interfere with the ability of military service members (SMs) to deploy. SMs in the United States (U.S.) Department of the Navy (DoN) with DLMCs who are not deployable should be placed in the medically restricted status of limited duty (LIMDU) or referred to the Physical Evaluation Board (PEB) for Service retention determination. It is critical to identify SMs correctly and promptly with DLMCs and predict their return-to-duty (RTD) to ensure the combat readiness of the U.S. Military. In this study, an algorithmic approach was developed to identify DoN SMs with previously unidentified DLMCs and predict whether SMs on LIMDU will be able to RTD. Materials and Methods Five years of historical data (2016–2022) were obtained from inpatient and outpatient datasets across direct and purchased care from the Military Health System (MHS) Data Repository (MDR). Key fields included International Classification of Diseases diagnosis and procedure codes, Current Procedure Terminology codes, prescription medications, and demographics information such as age, rank, gender, and service. The data consisted of 44,580,668 medical encounters across 1,065,224 SMs. To identify SMs with unidentified DLMCs, we developed an ensemble model combining outputs from multiple machine learning (ML) algorithms. When the ML ensemble model predicted a SM to have high risk scores, despite appearing healthy on administrative reports, their case was reviewed by expert clinicians to investigate for previously unidentified DLMCs; and such feedback served to validate the developed algorithms. In addition, leveraging 1,735,422 encounters (60,433 SMs) from LIMDU periods, we developed four separate ML models to estimate RTD probabilities for SMs after each medical encounter and predict the final LIMDU outcome. Results The ensemble model had 0.91 area under the receiver operating characteristic curve (AUROC). Out of 236 (round one) and 314 (round two) SMs reviewed by clinicians, 127 (54%) and 208 (66%) SMs were identified with a previously unidentified or undocumented DLMC, respectively. Regarding predicting RTD for SMs placed on LIMDU, the best performing ML model achieved 0.76 AUROC, 68% sensitivity, and 71% specificity. Conclusion Our research highlighted potential benefits of using predictive analytics in a medical assessment to identify SMs with DLMCs and to predict RTD outcomes once placed on LIMDU. This capability is being deployed for real-time clinical decision support to enhance health care provider's deployability assessment capability, improve accuracy of the DLMC population, and enhance combat readiness of the U.S Military. [ABSTRACT FROM AUTHOR]

This article addresses the challenge of estimating receiver operating characteristic (ROC) curves and the areas under these curves (AUC) in the context of an imperfect gold standard, a common issue in diagnostic accuracy studies. We delve into the nonparametric identification and estimation of ROC curves and AUCs when the reference standard for disease status is prone to error. Our approach hinges on the known or estimable accuracy of this imperfect reference standard and the conditional independent assumption, under which we demonstrate the identifiability of ROC curves and propose a nonparametric estimation method. In cases where the accuracy of the imperfect reference standard remains unknown, we establish that while ROC curves are unidentifiable, the sign of the difference between two AUCs is identifiable. This insight leads us to develop a hypothesis-testing method for assessing the relative superiority of AUCs. Compared to the existing methods, the proposed methods are nonparametric so that they do not rely on the parametric model assumptions. In addition, they are applicable to both the ROC/AUC analysis of continuous biomarkers and the AUC analysis of ordinal biomarkers. Our theoretical results and simulation studies validate the proposed methods, which we further illustrate through application in two real-world diagnostic studies. [ABSTRACT FROM AUTHOR]

Landslides in the state of Mizoram result in damage to life and properties annually. The study focuses on landslide susceptibility zones by frequency ratio (FR), evidential belief function (EBF) and index of entropy (IOE) models. A total of 1,486 landslide points were used to build a relationship between 16 factors and landslide occurrences. The results reveal 14.44%, 19.64% and 3.55% of the area as very high susceptible zones in FR, EBF and IOE models, respectively. The AUC results support the adoption of the EBF model in land use planning and decision-making processes to enhance natural resource management and mitigate landslide risks in Mizoram. [ABSTRACT FROM AUTHOR]

Diagnostic biomarkers play a critical role in biomedical research, particularly for the diagnosis and prediction of diseases, etc. To enhance diagnostic accuracy, extensive research about combining multiple biomarkers has been developed based on the multivariate normality, which is often not true in practice, as most biomarkers follow distributions that deviate from normality. While the likelihood ratio combination is recognized to be the optimal approach, it is complicated to calculate. To achieve a more accurate and effective combination of biomarkers, especially when these biomarkers deviate from normality, we propose using a receiver operating characteristic (ROC) curve methodology based on the optimal combination of elliptically distributed biomarkers. In this paper, we derive the ROC curve function for the elliptical likelihood ratio combination. Further, proceeding from the derived best combinations of biomarkers, we propose an efficient technique via nonparametric maximum likelihood estimate (NPMLE) to build empirical estimation. Simulation results show that the proposed elliptical combination method consistently provided better performance, demonstrating its robustness in handling various distribution types of biomarkers. We apply the proposed method to two real datasets: Autism/autism spectrum disorder (ASD) and neural tube defects (NTD). In both applications, the elliptical likelihood ratio combination improves the AUC value compared to the multivariate normal likelihood ratio combination and the best linear combination. [ABSTRACT FROM AUTHOR]

Simple Summary: Studies analyzing specific treatment-related prognostic factors can provide important information about disease biology and improve the use of biomarkers to optimize treatment decisions. The aim of our retrospective study was to determine the prognostic performance of clinicopathological factors and blood biomarkers in patients with unresectable metastatic melanoma treated with BRAF and MEK inhibitors. A total of 199 patients were included in the multivariate analysis of the risk of progression and death. We found that primary tumor localization on the limbs, Clark invasion level V, M1c stage or M1d stage at the start of therapy, and elevated baseline serum S100B level were independently and significantly associated with poor outcomes. The present study suggests that clinicopathological factors, including primary tumor characteristics and stage of metastatic disease, as well as serum markers may provide information on the probability of survival in patients with advanced melanoma treated with BRAF and MEK inhibitors. Prognostic studies can provide important information about disease biology and improve the use of biomarkers to optimize treatment decisions. Methods: A total of 199 patients with advanced melanoma treated with BRAF + MEK inhibitors were included in our single-center retrospective study. We analyzed the risk of progression and death using multivariate Cox proportional hazard models. The predictive effect of prognostic factors on progression-free survival (PFS) was evaluated in ROC analysis. Results: We found that primary tumor localization, Clark level, pT category, baseline M stage and baseline serum S100B are independent and significant prognostic factors for PFS. The discriminative power of the combination of these factors was excellent for predicting 18 month PFS (AUC 0.822 [95% CI 0.727; 0.916], p < 0.001). Primary tumor localization on the extremities, Clark level V, baseline M1c stage or M1d stage, and elevated baseline serum S100B and LDH levels were independently and significantly associated with unfavorable overall survival (OS). Conclusion: Baseline M stage and serum S100B appear to be independent prognostic factors for both PFS and OS in melanoma patients treated with BRAF + MEK inhibitors. We newly identified significant and independent prognostic effects of primary tumor localization and Clark level on survival that warrant further investigation. [ABSTRACT FROM AUTHOR]

Background: The current study relates to the utility of the levels of B-type natriuretic peptide (BNP) as a biomarker in the management and diagnostic evaluation of heart failure in various patient populations. Methods: A comparison of BNP levels between patients with different types of heart diseases was conducted using ROC curve analysis to assess how well BNP could predict the degree of heart failure. Results: The results established an important correlation between increased BNP, with risk of elevated BNP levels, and increased severity of the heart failure, proposing effectiveness of the peptide in the risk stratification and clinical decision-making. Conclusion: Our findings confirm the necessity of BNP level testing implementation in practical clinical activity to provide enhanced options for shortening the diagnosis time and further treatment beginning among the heart failure patient population in order to improve their prognosis. The research in the future is assessing the potential of BNP in terms of this prediction in relation to different population demographics and, therefore, conducting a modification in terms of broader clinical applications. This study's findings add to strong and growing evidence-based support for BNP as a functional biomarker in cardiovascular health. [ABSTRACT FROM AUTHOR]

Objective To investigate the predictive value of National Institutes of Health Stroke Scale (NIHSS) score, serum brain-derived neurotrophic factor (BDNF) and interleukin-6 (IL-6) in post-stroke depression (PSD). Methods A total of 180 patients with stroke were selected and divided into the PSD group (n=80, HAMD≥8 points) and the non-PSD (NPSD) group (n=100, HAMD＜8 points), according to HAMD score at 3 months after stroke. The basic information, NIHSS score, serum BDNF and IL-6 were compared between the two groups. The influencing factors of PSD were analyzed by Logistic regression method. Receiver operating characteristic (ROC) curves were plotted to evaluate the predictive value of NIHSS score, serum BDNF and IL-6 for PSD. Results Compared with the NPSD grope, low density lipoprotein cholesterol (LDL-C) and serum BDNF level were significantly lower, NIHSS score and serum IL-6 level were significantly increased in the PSD group (P＜0.05). Results of Logistic regression analysis showed that increased NIHSS score and serum IL-6 were risk factors for PSD, and increased serum BDNF was the protective factor in patents with PSD (P＜0.05). The area under curve (AUC) of NIHSS score, serum BDNF and IL-6 and their combination prediction of PSD were 0.762, 0.746, 0.796 and 0.839, respectively. The sensitivity of the combined prediction was 86.0% and a specificity was 95.0%. Conclusion Compared with NPSD patients, the NIHSS score and serum IL-6 level are increased, and the serum BDNF level is decreased in patients with PSD. The combination of all three has a high predictive value for patients of PSD. [ABSTRACT FROM AUTHOR]

Background: Depression is present in individuals with type 2 diabetes mellitus. Objective : We evaluated the sociodemographic, anthropometric, and clinical features of Mexican individuals with clinical depressive symptoms in order to identify predictors for depression symptoms; finally, we evaluated if HbA1c levels could be used as a probable diagnostic of depressive symptoms in individuals with type 2 diabetes mellitus. Methods: The population studied consisted of 376 Mexicans with diabetes who were interviewed to collect information about comorbidities and habits. The evaluation of depressive symptoms was performed using the Hamilton scale. For a possible clinical association between HbA1c levels and depressive symptoms, we performed chi-square tests (χ2)/ t tests. A multivariate logistic regression model with the backward conditional method was used to identify predictors of depressive symptoms. An ROC curve was plotted to assess the possible role of HbA1c as a diagnostic predictive test of depression symptoms. Results: A total of 42.8% (n = 161) individuals showed clinical depressive symptoms. When comparing individuals with and without depression symptoms, those with depression symptoms showed higher levels of glucose and HbA1c; additionally, gender (p = 0.04), age (p = 0.006), HbA1c (p < 0.01), and complications related to diabetes were predictive factors for clinical depressive symptoms (p < 0.01). However, HbA1c showed a low diagnostic accuracy for depressive symptoms, with an area under the ROC curve of 0.59. Conclusions: Our findings provided evidence of the sex, age, HbA1c levels, and medical complications as predictors of clinical depressive symptoms in individuals with diabetes mellitus. Nevertheless, HbA1c levels are not useful as a diagnostic instrument for depressive symptom severity in these Mexican individuals. [ABSTRACT FROM AUTHOR]

Background Clinicians need a tool to gauge patients' ability to understand health conditions and treatment options. The Short-form Test of Functional Health Literacy in Adults (S-TOFHLA) is the gold standard for this, but its length is prohibitive for use in clinical settings. This study seeks to validate a novel three-item question set for predicting health literacy. Methods This cross-sectional study utilized an in-person questionnaire alongside the S-TOFHLA. The sample included 2027 English- and Spanish-speaking adults (≥18 years) recruited from primary care practices serving a low-income eastern Pennsylvania community. Most patients (57.7%) identified as Hispanic. Diagnostic accuracy of each question and aggregated scores were assessed against the validated survey by calculating the area under the receiver operating characteristic (AUROC) curve. Results Questions in the 'Problems Learning' and 'Help Reading' domains (AUROC 0.66 for each) performed better than the 'Confident Forms' question (AUROC 0.64). Summing all three scores resulted in an even higher AUROC curve (0.71). Cronbach's alpha of the combined items was 0.696. Conclusions Study results suggest that any of the three questions are viable options for screening health literacy levels of diverse patients in primary care clinical settings. However, they perform better as a summed score than when used individually. [ABSTRACT FROM AUTHOR]

We leverage telematics data on driving behavior variables to assess driver risk and predict future insurance claims in a case study utilising a representative telematics sample. In the study, we aim to categorise drivers according to their driving habits and establish premiums that accurately reflect their driving risk. To accomplish our goal, we employ the two-stage Poisson model, the Poisson mixture model, and the Zero-Inflated Poisson model to analyse the telematics data. These models are further enhanced by incorporating regularisation techniques such as lasso, adaptive lasso, elastic net, and adaptive elastic net. Our empirical findings demonstrate that the Poisson mixture model with the adaptive lasso regularisation outperforms other models. Based on predicted claim frequencies and drivers' risk groups, we introduce a novel usage-based experience rating premium pricing method. This method enables more frequent premium updates based on recent driving behaviour, providing instant rewards and incentivising responsible driving practices. Consequently, it helps to alleviate cross-subsidization among risky drivers and improves the accuracy of loss reserving for auto insurance companies. [ABSTRACT FROM AUTHOR]

Landslides are among the most prevalent geological hazards and are characterized by their high frequency, significant destructive potential, and considerable incident rate. Annually, these events lead to substantial casualties and property losses. Thus, conducting landslide susceptibility assessments in the regions vulnerable to such hazards has become crucial. In recent years, the coupling of traditional statistical methods with machine learning techniques has shown significant advantages in assessing landslide risk. This study focused on Sichuan Province, China, a region characterized by its vast area and diverse climatic and geological conditions. We selected 13 influencing factors for the analysis: elevation, slope, aspect, plan curve, profile curve, valley depth, precipitation, the stream power index (SPI), the topographic wetness index (TWI), the topographic position index (TPI), surface roughness, fractional vegetation cover (FVC), and slope height. This study incorporated the certainty factor method (CF), the information value method (IV), and their coupling with the decision tree C5.0 model (DT) and a logistic regression model (LR) as follows: IV-LR, IV-DT, CF-LR, and CF-DT. The results, validated by an ROC curve analysis, demonstrate that the evaluation accuracy of all six models exceeded 0.750 (AUC > 0.750). The IV-LR model exhibited the highest accuracy, with an AUC of 0.848. When comparing the accuracy among the models, it is evident that the coupling models outperformed the individual statistical models. Based on the results of the six models, a landslide susceptibility map was generated, categorized into five levels. High and very high landslide risk zones are mainly concentrated in the eastern and southeastern regions, covering nearly half of Sichuan Province. Medium-risk areas form linear distributions from northeast to southwest, occupying a smaller proportion of the area. Extremely low- and low-risk zones are predominantly located in the western and northwestern regions. The density of the landslide points increases with higher risk levels across the regions. This further validates the suitability of this research methodology for landslide susceptibility studies on a large scale. Consequently, this methodology can provide crucial insights for landslide prevention and mitigation efforts in this region. [ABSTRACT FROM AUTHOR]

Groundwater is under stress due to the growth of population, urbanization and industrialization, especially in developing countries. Consequently, there is a shortage of water in many parts of Indian cities. Thus, monitoring and assessing groundwater are crucial for effective management of water resources. The main objectives of our study is to explore the effectiveness of machine learning models for assessing groundwater potential in Lidder watershed in India. The site-specific factors influencing groundwater potential were selected for preparing groundwater potential zones in the study area. These factors were integrated for preparing the groundwater potential map using three models, namely logistic regression (LR), ensemble of random forest (LR-RF) and multilayer perceptron layer (LR-MLP). The area under curve of receiver operating characteristic (ROC) and several statistical performance measures were used to validate and compare the performance of the models. The validation revealed that the maximum value of AUC-ROC (0.946) was found for LR-RF for assessing groundwater potential than the LR and LR-MLP models. The results revealed low groundwater potential mostly found in the northern part of the watershed. High elevation, steep slope, highly alkaline and acidic soils, snow cover, barren land and hard basaltic rocks are attributed to low groundwater potential. Rainfall, vegetation, low elevation, younger alluvial plain, low drainage density and high lineament density have made groundwater potential high and very high in the southern part of the watershed. The central part of the watershed experienced moderate groundwater potential due to the piedmont alluvial plain, basal gravel, moderate rainfall, moderate drainage density, and scrub vegetation. We argue that the other geographical areas that are interested in properly managing groundwater resources can make use of the logistic regression and ensemble models of random forest and multilayer perceptron (MLP) for groundwater potential assessment. [ABSTRACT FROM AUTHOR]

Aim: This research aimed to construct a clinical model for forecasting the likelihood of lung metastases in differentiated thyroid carcinoma (DTC) with intermediate- to high-risk. Methods: In this study, 375 DTC patients at intermediate to high risk were included. They were randomly divided into a training set (70%) and a validation set (30%). A nomogram was created using the training group and then validated in the validation set using calibration, decision curve analysis (DCA) and receiver operating characteristic (ROC) curve. Results: The calibration curves demonstrated excellent consistency between the predicted and the actual probability. ROC analysis showed that the area under the curve in the training cohort was 0.865 and 0.845 in the validation cohort. Also, the DCA curve indicated that this nomogram had good clinical utility. Conclusion: A user-friendly nomogram was constructed to predict the lung metastases probability with a high net benefit. Article highlights The study aimed to develop a predictive model for lung metastases in patients with differentiated thyroid cancer (DTC) who are at intermediate- to high-risk. Through univariate and multivariate analyses, histological type, multifocality, tumor size, BRAFV600E mutation and ps-Tg levels were identified as independent factors influencing the development of lung metastases. A nomogram was constructed based on these risk factors, with a high C-index of 0.86, indicating strong predictive accuracy for lung metastases. Calibration curves showed excellent consistency between predicted and actual probabilities of lung metastases, further validating the nomogram's reliability. Receiver operating characteristic analysis demonstrated high discrimination ability of the nomogram, with an area under the curve of 0.865 in the training cohort and 0.845 in the validation cohort. Decision curve analysis indicated that the nomogram had better clinical utility in predicting lung metastases rates compared with other models. The nomogram provides clinicians with a tool to assess the risk of lung metastases in DTC patients, incorporating factors such as histological type, tumor size, genetic mutations and ps-Tg levels to guide treatment decisions and improve patient outcomes. [ABSTRACT FROM AUTHOR]

Background The diagnostic criteria for lateral lymph node metastasis in rectal cancer have not been established. This research aimed to investigate the risk factors for lateral lymph node metastasis and develop machine learning models combining these risk factors to improve the diagnostic performance of standard imaging. Method This multicentre prospective study included patients who underwent lateral lymph node dissection without preoperative treatment for rectal cancer between 2017 and 2019 in 15 Japanese institutions. First, preoperative clinicopathological factors and magnetic resonance imaging findings were evaluated using multivariable analyses for their correlation with lateral lymph node metastasis. Next, machine learning diagnostic models for lateral lymph node metastasis were developed combining these risk factors. The models were tested in a training set and in an internal validation cohort and their diagnostic performance was tested using receiver operating characteristic curve analyses. Results Of 212 rectal cancers, 122 patients were selected, including 232 lateral pelvic sides, 30 sides of which had pathological lateral lymph node metastasis. Multivariable analysis revealed that poorly differentiated/mucinous adenocarcinoma, extramural vascular invasion, tumour deposit and a short-axis diameter of lateral lymph node ≥ 6.0 mm were independent risk factors for lateral lymph node metastasis. Patients were randomly divided into a training cohort (139 sides) and a test cohort (93 sides) and machine learning models were computed on the basis of a combination of significant features (including: histological type, extramural vascular invasion, tumour deposit, short- and long-axis diameter of lateral lymph node, body mass index, serum carcinoembryonic antigen level, cT, cN, cM, irregular border and mixed signal intensity). The top three models with the highest sensitivity in the training cohort were as follows: support vector machine (sensitivity, 1.000; specificity, 0.773), light gradient boosting machine (sensitivity, 0.950; specificity, 0.918) and ensemble learning (sensitivity, 0.950; specificity, 0.917). The diagnostic performances of these models in the test cohort were as follows: support vector machine (sensitivity, 0.750; specificity, 0.667), light gradient boosting machine (sensitivity, 0.500; specificity, 0.852) and ensemble learning (sensitivity, 0.667; specificity, 0.864). Conclusion Machine learning models combining multiple risk factors can contribute to improving diagnostic performance of lateral lymph node metastasis. [ABSTRACT FROM AUTHOR]

Objective To screen the risk factors related to primary trigeminal neuralgia (PTN) based on radiomics. Methods A total of 48 patients with PTN admitted to Guangdong Second Provincial General Hospital from January 2017 to December 2020 were selected. The mean arterial pressure (MAP) of the patients was measured, and the neurovascular compression model was constructed by head MRI examination. Univariate and multivariate Logistic regression analyses were used to screen for risk factors associated with PTN, and the predictive efficacy was evaluated by receiver operating characteristic (ROC) curve according to the risk factors. Results Among 48 patients, 42 patients (87.50%) had unilateral lesions and 6 patients (12.50%) had bilateral lesions. The MAP was 56.89-120.44 mm Hg, with an average of (94.32 ± 11.34) mm Hg. The neurovascular compression model of 54 cases was divided into the affected side (n = 40) and the healthy side (n = 14) according to whether the disease occurred. The neurovascular compression area (Z = -2.823, P = 0.005) and neurovascular pressure (Z = -0.365, P = 0.006) on the affected side were greater than those on the healthy side. Logistic regression analyses showed that high neurovascular pressure (OR = 1.001, 95%CI: 1.0003-1.0022; P = 0.011) was a risk factor for PTN. ROC showed the area under the curve (AUC) of neurovascular compression area for predicting PTN was 0.747 (95%CI: 0.605-0.890, P = 0.006), the sensitivity was 42.50%, the specificity was 100%, and the cut-off value was 25.34 mm². The AUC of neurovascular pressure was 0.755 (95%CI: 0.616-0.895, P = 0.005), the sensitivity was 67.50%, the specificity was 78.60%, and the cut-off value was 1672.99 mm Hg⋅mm². Conclusions The neurovascular compression area and neurovascular pressure are important in the diagnosis of PTN. [ABSTRACT FROM AUTHOR]

Liver transplantation (LT) is a treatment for acute-on-chronic liver failure (ACLF), but high post-LT mortality has been reported. Existing post-LT models in ACLF have been limited. We developed an Expert-Augmented Machine Learning (EAML) model to predict post-LT outcomes. We identified ACLF patients who underwent LT in the University of California Health Data Warehouse. We applied the RuleFit machine learning (ML) algorithm to extract rules from decision trees and create intermediate models. We asked human experts to rate the rules generated by RuleFit and incorporated these ratings to generate final EAML models. We identified 1384 ACLF patients. For death at 1 year, areas under the receiver-operating characteristic curve were 0.707 (confidence interval [CI] 0.625-0.793) for EAML and 0.719 (CI 0.640-0.800) for RuleFit. For death at 90 days, areas under the receiver-operating characteristic curve were 0.678 (CI 0.581-0.776) for EAML and 0.707 (CI 0.615-0.800) for RuleFit. In pairwise comparisons, both EAML and RuleFit models outperformed cross-sectional models. Significant discrepancies between experts and ML occurred in rankings of biomarkers used in clinical practice. EAML may serve as a method for ML-guided hypothesis generation in further ACLF research.

Background and aimsNonalcoholic fatty liver disease (NAFLD) has reached pandemic proportions. Early detection can identify at-risk patients who can be linked to hepatology care. The vibration-controlled transient elastography (VCTE) controlled attenuation parameter (CAP) is biopsy validated to diagnose hepatic steatosis (HS). We aimed to develop a novel clinical predictive algorithm for HS using the CAP score at a Veterans' Affairs hospital.MethodsWe identified 403 patients in the Greater Los Angeles VA Healthcare System with valid VCTEs during 1/2018-6/2020. Patients with alcohol-associated liver disease, genotype 3 hepatitis C, any malignancies, or liver transplantation were excluded. Linear regression was used to identify predictors of NAFLD. To identify a CAP threshold for HS detection, receiver operating characteristic analysis was applied using liver biopsy, MRI, and ultrasound as the gold standards.ResultsThe cohort was racially/ethnically diverse (26% Black/African American; 20% Hispanic). Significant positive predictors of elevated CAP score included diabetes, cholesterol, triglycerides, BMI, and self-identifying as Hispanic. Our predictions of CAP scores using this model strongly correlated (r = 0.61, p

BACKGROUND: No widely used stratification tool exists to predict which pediatric trauma patients may require a video-assisted thoracoscopic surgery (VATS). We sought to develop a novel VATS-In-Pediatrics (VIP) score to predict the need for early VATS (within 72 h of admission) for pediatric trauma patients. METHODS: The pediatric 2017-2020 Trauma Quality Improvement Program database was used and divided into two sets (derivation set using 2017-2019 data and validation set using 2020 data). First, multiple logistic regression models were created to determine the risk of early VATS for patients ≤ 17 years old. Second, the weighted average and relative impact of each independent predictor were used to derive a VIP score. We then validated the score using the area under the receiver operating characteristic (AROC) curve. RESULTS: From 218,628 patients in the derivation set, 2183 (1.0%) underwent early VATS. A total of 8 independent predictors of VATS were identified, and the VIP score was derived with scores ranging from 0 to 9. The AROC for this was 0.91. The VATS rate increased steadily from 12.5 to 32% then 60.5% at scores of 3, 4, and 6, respectively. In the validation set, from 70,316 patients, 887 (1.3%) underwent VATS, and the AROC was 0.91. CONCLUSIONS: VIP is a novel and validated scoring tool to predict the need for early VATS in pediatric trauma. This tool can potentially help hospital systems prepare for pediatric patients at high risk for requiring VATS during their first 72 h of admission. Future prospective research is needed to evaluate VIP as a tool that can improve clinical outcomes.

Jingwen Zhang,1,2,&ast; Guoqiang Zhang,1,2,&ast; JiaJia Wang,1,2,&ast; Yun Xiao,1,2 Xinxin Lu,1,2 Xunhong Lan,1,2 Yan Zhang,1,2 Zhang Dai1,2 1Centre of Clinical Laboratory, Zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, People’s Republic of China; 2Institute of Infectious Disease, School of Medicine, Xiamen University, Xiamen, People’s Republic of China&ast;These authors contributed equally to this workCorrespondence: Yan Zhang; Zhang Dai, Centre of Clinical Laboratory, Zhongshan Hospital of Xiamen University, School of Medicine, Xiamen University, Xiamen, People’s Republic of China, Tel +86-0592-2293046, Email zy1983@xmu.edu.cn; 180219034@qq.comBackground: Nosocomial candidemia is a life-threatening condition, and the incidence has increased in recent years. Thorough epidemiological data is still lacking in China.Methods: A retrospective cohort study was conducted to investigate the patients admitted to Zhongshan Hospital Xiamen University from 1 January 2004 to 31 December 2022. This study included 205 individuals who were diagnosed with candidemia as subjects. Additionally, 303 cases with blood cultures were negative during the same period and were from the same department as a control group. We randomly assigned them to the training and validation groups in a 7:3 ratio. The least absolute shrinkage and selection operator regression, univariate and multivariate logistic regression analyses were used to filtrate independent factors associated with nosocomial candidemia. A nomogram model was established based on the selected variables. Receiver operating characteristic (ROC) curve, calibration plots and decision curve analysis (DCA) were used to evaluate clinical utility.Results: Two hundred and five nosocomial candidemia patients were reported, containing a high proportion of Candida albicans (n = 91,44.39%), followed by Candida parapsilosis (n = 40, 19.51%), Candida tropicalis (n = 37,18.05%), Candida glabrata (n = 23, 11.22%) and Candida guilliermondii (n = 9,4.39%). Multiple organ dysfunction syndrome (OR = 10.372, 95% CI: 4.745– 24.14 P < 0.001), increased urea nitrogen of serum (OR=1.088,95% CI: 1.039– 1.144 P< 0.001), decreased albumin of serum (OR = 0.922 95% CI: 0.850– 0.997 P=0.045), mechanical ventilation (OR=4.074,95% CI: 1.397– 12.77 P=0.012), central venous indwelling catheter (OR=7.422,95% CI: 3.189– 18.41 P< 0.001) and solid tumor (OR = 3.036 95% CI: 1.276– 7.359 P=0.012) were identified as independent risk factors of candidemia. The area under the curve (AUC) of the nomogram model was 0.925 (95% CI: 0.898– 0.952) in the training group and 0.946 (95% CI: 0.881– 0.963) in the validation group. The calibration curve revealed good agreement between the probability and the observed values. DCA indicated that this nomogram might be clinically beneficial.Conclusion: The nomogram including multiple organ dysfunction syndrome, elevated blood urea nitrogen, decreased albumin, mechanical ventilation, central venous indwelling catheter and solid tumor could provide reference value to clinicians for identifying nosocomial candidemia.Keywords: candidemia, risk factors, nomogram model, ROC curve

Abstract The minimal clinically important difference (MCID) is an important concept with big appeal in a field struggling to interpret quality of life (QOL) and other patient-reported outcomes (PRO), is also a bridge between statistics and clinical medicine. This study uses the ROC curve to formulate the MCID value of the Quality of Life Instruments for Chronic Diseases of Systemic lupus erythematosus (QLICD-SLE V2.0) scale. Using the representative item “In general, would you say your health is” of the MOS item short form health survey(SF-36) as an anchor, the questionnaire of QLICD-SLE V2.0 and the anchor item were used to investigate the patients on the first day of hospitalization, and the day before the patient was discharged. 279 patients with lupus erythematosus were participated in this longitudinal follow-up study. The ROC curve was constructed by using the classification based on the anchor item as the gold standard and the difference score of the scale as the test variable. The cut-off point corresponding to the maximum value of the Youden index in the ROC curve is taken as the minimum clinical importance difference (MCID) value of the QLICD-SLE (V2.0) scale. The Results showed that the MCID of physical domain, psychological domain, social domain, general module, specific module and QLICD-SLE (V2.0) total scale are 8.3, 2.3, 2.5, 2.7, 9.2 and 3.2, respectively. Area under the ROC curve of QLICD-SLE (V2.0) is 0.898, P (Area = 0.5)

AIM: To analyze and screen influencing factors of diabetic patients complicated with retinopathy, and establish and validate prediction model of nomogram.METHODS: A total of 1 252 patients from the Diabetes Complications Early Warning Dataset of the National Population Health Data Archive(PHDA)between January 2013 to January 2021 were selected and randomly divided into a modeling group(n=941)and a validation group(n=311). Univariate analysis, LASSO regression and Logistic regression analysis were used to screen out the influencing factors of diabetic retinopathy, and a nomogram prediction model was established. The receiver operating characteristic curve, Hosmer-Lemeshow test and calibration curve were used to evaluate the model. The clinical benefit was evaluated by the decision curve analysis(DCA).RESULTS: Age, hypertension, nephropathy, systolic blood pressure(SBP), glycated hemoglobin(HbA1c), high-density lipoprotein cholesterol(HDL-C), and blood urea(BU)were the influencing factors of diabetic retinopathy. The area under the curve(AUC)of the modeling group was 0.792(95%CI: 0.763-0.821), and the AUC of the validation group was 0.769(95%CI: 0.716-0.822). The Hosmer-Lemeshow goodness of fit test and calibration curve suggested that the theoretical value of the model was in good agreement(modeling group: χ2=14.520, P=0.069; validation group: χ2=14.400, P=0.072). The DCA results showed that the threshold probabilities range was 0.09-0.89 for modeling group and 0.07-0.84 for the validation group, which suggested the clinical net benefit was higher.CONCLUSION: This study constructed a risk prediction model including age, hypertension, nephropathy, SBP, HbA1c, HDL-C, and BU. The model has a high discrimination and consistency, and can be used to predict the risk of diabetic retinopathy in patients with diabetes.

Retinal hemorrhages in pediatric patients can be a diagnostic challenge for ophthalmologists. These hemorrhages can occur due to various underlying etiologies, including abusive head trauma, accidental trauma, and medical conditions. Accurate identification of the etiology is crucial for appropriate management and legal considerations. In recent years, deep learning techniques have shown promise in assisting healthcare professionals in making more accurate and timely diagnosis of a variety of disorders. We explore the potential of deep learning approaches for differentiating etiologies of pediatric retinal hemorrhages. Our study, which spanned multiple centers, analyzed 898 images, resulting in a final dataset of 597 retinal hemorrhage fundus photos categorized into medical (49.9%) and trauma (50.1%) etiologies. Deep learning models, specifically those based on ResNet and transformer architectures, were applied; FastViT-SA12, a hybrid transformer model, achieved the highest accuracy (90.55%) and area under the receiver operating characteristic curve (AUC) of 90.55%, while ResNet18 secured the highest sensitivity value (96.77%) on an independent test dataset. The study highlighted areas for optimization in artificial intelligence (AI) models specifically for pediatric retinal hemorrhages. While AI proves valuable in diagnosing these hemorrhages, the expertise of medical professionals remains irreplaceable. Collaborative efforts between AI specialists and pediatric ophthalmologists are crucial to fully harness AIs potential in diagnosing etiologies of pediatric retinal hemorrhages.

Background & aimsWe conducted an individual patient data meta-analysis to establish stiffness cut-off values for magnetic resonance elastography (MRE) in staging liver fibrosis and to assess potential confounding factors.MethodsA systematic review of the literature identified studies reporting MRE data in patients with NAFLD. Data were obtained from the corresponding authors. The pooled diagnostic cut-off value for the various fibrosis stages was determined in a two-stage meta-analysis. Multilevel modelling methods were used to analyse potential confounding factors influencing the diagnostic accuracy of MRE in staging liver fibrosis.ResultsEight independent cohorts comprising 798 patients were included in the meta-analysis. The area under the receiver operating characteristic curve (AUROC) for MRE in detecting significant fibrosis was 0.92 (sensitivity, 79%; specificity, 89%). For advanced fibrosis, the AUROC was 0.92 (sensitivity, 87%; specificity, 88%). For cirrhosis, the AUROC was 0.94 (sensitivity, 88%, specificity, 89%). Cut-offs were defined to explore concordance between MRE and histopathology: ≥F2, 3.14 kPa (pretest probability, 39.4%); ≥F3, 3.53 kPa (pretest probability, 24.1%); and F4, 4.45 kPa (pretest probability, 8.7%). In generalized linear mixed model analysis, histological steatohepatitis with higher inflammatory activity (odds ratio 2.448, 95% CI 1.180-5.079, p 120U/L) (odds ratio 3.388, 95% CI 1.577-7.278, p

BACKGROUND: In suspected myocardial infarction (MI), guidelines recommend using high-sensitivity cardiac troponin (hs-cTn)-based approaches. These require fixed assay-specific thresholds and timepoints, without directly integrating clinical information. Using machine-learning techniques including hs-cTn and clinical routine variables, we aimed to build a digital tool to directly estimate the individual probability of MI, allowing for numerous hs-cTn assays. METHODS: In 2,575 patients presenting to the emergency department with suspected MI, two ensembles of machine-learning models using single or serial concentrations of six different hs-cTn assays were derived to estimate the individual MI probability (ARTEMIS model). Discriminative performance of the models was assessed using area under the receiver operating characteristic curve (AUC) and logLoss. Model performance was validated in an external cohort with 1688 patients and tested for global generalizability in 13 international cohorts with 23,411 patients. RESULTS: Eleven routinely available variables including age, sex, cardiovascular risk factors, electrocardiography, and hs-cTn were included in the ARTEMIS models. In the validation and generalization cohorts, excellent discriminative performance was confirmed, superior to hs-cTn only. For the serial hs-cTn measurement model, AUC ranged from 0.92 to 0.98. Good calibration was observed. Using a single hs-cTn measurement, the ARTEMIS model allowed direct rule-out of MI with very high and similar safety but up to tripled efficiency compared to the guideline-recommended strategy. CONCLUSION: We developed and validated diagnostic models to accurately estimate the individual probability of MI, which allow for variable hs-cTn use and flexible timing of resampling. Their digital application may provide rapid, safe and efficient personalized patient care. TRIAL REGISTRATION NUMBERS: Data of following cohorts were used for this project: BACC ( www. CLINICALTRIALS: gov ; NCT02355457), stenoCardia ( www. CLINICALTRIALS: gov ; NCT03227159), ADAPT-BSN ( www.australianclinicaltrials.gov.au ; ACTRN12611001069943), IMPACT ( www.australianclinicaltrials.gov.au , ACTRN12611000206921), ADAPT-RCT ( www.anzctr.org.au ; ANZCTR12610000766011), EDACS-RCT ( www.anzctr.org.au ; ANZCTR12613000745741); DROP-ACS ( https://www.umin.ac.jp , UMIN000030668); High-STEACS ( www. CLINICALTRIALS: gov ; NCT01852123), LUND ( www. CLINICALTRIALS: gov ; NCT05484544), RAPID-CPU ( www. CLINICALTRIALS: gov ; NCT03111862), ROMI ( www. CLINICALTRIALS: gov ; NCT01994577), SAMIE ( https://anzctr.org.au ; ACTRN12621000053820), SEIGE and SAFETY ( www. CLINICALTRIALS: gov ; NCT04772157), STOP-CP ( www. CLINICALTRIALS: gov ; NCT02984436), UTROPIA ( www. CLINICALTRIALS: gov ; NCT02060760).

OBJECTIVE: To develop easy to use and validated predictive models to identify beneficiaries experiencing homelessness from administrative data. DATA SOURCES: We pooled enrollment and claims data from enrollees of the California Whole Person Care (WPC) Medicaid demonstration program that coordinated the care of a subset of Medicaid beneficiaries identified as high utilizers in 26 California counties (25 WPC Pilots). We also used public directories of social service and health care facilities. STUDY DESIGN: Using WPC Pilot-reported homelessness status, we trained seven supervised learning algorithms with different specifications to identify beneficiaries experiencing homelessness. The list of predictors included address- and claims-based indicators, demographics, health status, health care utilization, and county-level homelessness rate. We then assessed model performance using measures of balanced accuracy (BA), sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiver operating characteristic curve (area under the curve [AUC]). DATA COLLECTION/EXTRACTION METHODS: We included 93,656 WPC enrollees from 2017 to 2018, 37,441 of whom had a WPC Pilot-reported homelessness indicator. PRINCIPAL FINDINGS: The random forest algorithm with all available indicators had the best performance (87% BA and 0.95 AUC), but a simpler Generalized Linear Model (GLM) also performed well (74% BA and 0.83 AUC). Reducing predictors to the top 20 and top five most important indicators in a GLM model yields only slightly lower performance (86% BA and 0.94 AUC for the top 20 and 86% BA and 0.91 AUC for the top five). CONCLUSIONS: Large samples can be used to accurately predict homelessness in Medicaid administrative data if a validated homelessness indicator for a small subset can be obtained. In the absence of a validated indicator, the likelihood of homelessness can be calculated using county rate of homelessness, address- and claim-based indicators, and beneficiary age using a prediction model presented here. These approaches are needed given the rising prevalence of homelessness and the focus of Medicaid and other payers on addressing homelessness and its outcomes.

We aim to clarify the usefulness of different measures of economic resilience in the context of global shocks. In relation to the Great Recession, Oil& European migrant crises, and COVID-19, we compute and validate from a statistical point of view, then characterize five metrics on 317 NUTS2 regions and 21 years. ROC curves and Cox regression compare them by the capacity to predict the post-shock state. Heterogenous behavior characterizes resistance, recovery, and loss. Furthermore, the non-linear resistance performs best in future state prediction, while the composite index has the lowest efficiency as a predictor of the regions' recovery. [ABSTRACT FROM AUTHOR]