Search

Background: We sought to develop an automatable score to predict hospitalization, critical illness, or death for patients at risk for coronavirus disease 2019 (COVID-19) presenting for urgent care.Methods: We developed the COVID-19 Acuity Score (CoVA) based on a single-center study of adult outpatients seen in respiratory illness clinics or the emergency department. Data were extracted from the Partners Enterprise Data Warehouse, and split into development (n = 9381, 7 March-2 May) and prospective (n = 2205, 3-14 May) cohorts. Outcomes were hospitalization, critical illness (intensive care unit or ventilation), or death within 7 days. Calibration was assessed using the expected-to-observed event ratio (E/O). Discrimination was assessed by area under the receiver operating curve (AUC).Results: In the prospective cohort, 26.1%, 6.3%, and 0.5% of patients experienced hospitalization, critical illness, or death, respectively. CoVA showed excellent performance in prospective validation for hospitalization (expected-to-observed ratio [E/O]: 1.01; AUC: 0.76), for critical illness (E/O: 1.03; AUC: 0.79), and for death (E/O: 1.63; AUC: 0.93). Among 30 predictors, the top 5 were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate.Conclusions: CoVA is a prospectively validated automatable score for the outpatient setting to predict adverse events related to COVID-19 infection. [ABSTRACT FROM AUTHOR]

SUMMARY Multichannel cooperative sensing (MCS) is an effective method for dynamic spectrum access in cognitive radio networks. In contrast to most existing work on MCS that considered secondary users with homogeneous sensing ability, this paper studies the MCS problem for secondary users with heterogeneous sensing ability in terms of sensing accuracy. We further take into account different parameters of primary channels such as bandwidth, probability of being idle in each sensing period, and frequency selective fading at the sensing receiver. The MCS problem is formulated as a weapon target assignment problem, where more sensing resources are assigned to channels that are more valuable. This weapon target assignment problem is transformed to an integer generalized network flow problem with convex flow costs to obtain the lower bound solution, and then solved by the branch and bound algorithm with this bound to yield the exact scheme. To reduce computational complexity, a heuristic scheme is also proposed, which has approximate performance compared with the exact scheme. Finally, extensive simulation results for different scenarios illustrate the performance improvements of the proposed schemes over the existing scheme. Copyright © 2013 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Insulin is an important part of treatment of type 2 diabetes mellitus (T2DM). Nevertheless, reasons for discontinuation of insulin therapy are poorly understood. We conducted a real-world-evidence analysis of EMR data at Partners HealthCare to study adults with T2DM who were prescribed insulin between 2010 and 2016. Reasons for insulin discontinuation were identified from a combination of structured EMR data and natural language processing analysis of EMR notes using a validated tool (sensitivity 76.9% and positive predictive value 89.7%). The mean age of study patients was 60.2 years; 52.7% were male. Among 7,009 study patients, 2,957 (42.2%) discontinued insulin within 12 months after study start. In multivariable logistic regression analysis adjusted for demographics and comorbidities, patients were more likely to discontinue either basal or bolus insulin if they were on a basal-bolus regimen compared to basal only (OR 1.56, 95% CI 1.33 to 1.83; p < 0.001) or if they were being seen by an endocrinologist (OR 2.58; 95% CI 2.22 to 2.99; p < 0.001). Most patients (2,121/71.7%) had one or more reasons for discontinuation documented. The most common reasons were improving blood glucose (BG) control (33.2%), weight loss (likely ultimately also leading to lower BG) (18.5%) and initiation of non-insulin diabetes medications (16.7%). In multivariable analysis, patients were more likely to stop insulin due to achievement of good BG control if they were treated by an endocrinologist (OR 2.52; 95% CI 2.11 to 3.00; p < 0.001) or by a female physician (OR 1.43; 95% CI 1.26 to 1.63; p < 0.001). This study represents a successful attempt to use natural language processing to understand reasons for insulin discontinuation. Insulin discontinuation is common, and particularly so for patients on a basal-bolus regimen. Achievement of glycemic control, weight loss and initiation of other diabetes medications were the most common reasons for insulin discontinuation. Disclosure: J. Wu: None. F.J. Morrison: None. Z. Zhao: Employee; Self; Lilly Diabetes. X. He: Employee; Self; Eli Lilly and Company. M. Shubina: None. S. Malmasi: None. W. Ge: None. X. Peng: None. A. Turchin: Advisory Panel; Self; Monarch Medical Technologies. Research Support; Self; Eli Lilly and Company. Stock/Shareholder; Self; Brio Systems. Funding: Eli Lilly and Company [ABSTRACT FROM AUTHOR]

Fall-related injuries (FRIs) are a major cause of hospitalizations among older patients, but identifying them in unstructured clinical notes poses challenges for large-scale research. In this study, we developed and evaluated Natural Language Processing (NLP) models to address this issue. We utilized all available clinical notes from the Mass General Brigham for 2,100 older adults, identifying 154,949 paragraphs of interest through automatic scanning for FRI-related keywords. Two clinical experts directly labeled 5,000 paragraphs to generate benchmark-standard labels, while 3,689 validated patterns were annotated, indirectly labeling 93,157 paragraphs as validated-standard labels. Five NLP models, including vanilla BERT, RoBERTa, Clinical-BERT, Distil-BERT, and SVM, were trained using 2,000 benchmark paragraphs and all validated paragraphs. BERT-based models were trained in three stages: Masked Language Modeling, General Boolean Question Answering (QA), and QA for FRI. For validation, 500 benchmark paragraphs were used, and the remaining 2,500 for testing. Performance metrics (precision, recall, F1 scores, Area Under ROC [AUROC] or Precision-Recall [AUPR] curves) were employed by comparison, with RoBERTa showing the best performance. Precision was 0.90 [0.88-0.91], recall [0.90-0.93], F1 score 0.90 [0.89-0.92], AUROC and AUPR curves of 0.96 [0.95-0.97]. These NLP models accurately identify FRIs from unstructured clinical notes, potentially enhancing clinical notes-based research efficiency., (© The Author(s) 2024. Published by Oxford University Press on behalf of the Johns Hopkins Bloomberg School of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)

Background and Objectives: The validity of brain monitoring using electroencephalography (EEG), particularly to guide care in patients with acute or critical illness, requires that experts can reliably identify seizures and other potentially harmful rhythmic and periodic brain activity, collectively referred to as "ictal-interictal-injury continuum" (IIIC). Previous interrater reliability (IRR) studies are limited by small samples and selection bias. This study was conducted to assess the reliability of experts in identifying IIIC., Methods: This prospective analysis included 30 experts with subspecialty clinical neurophysiology training from 18 institutions. Experts independently scored varying numbers of ten-second EEG segments as "seizure (SZ)," "lateralized periodic discharges (LPDs)," "generalized periodic discharges (GPDs)," "lateralized rhythmic delta activity (LRDA)," "generalized rhythmic delta activity (GRDA)," or "other." EEGs were performed for clinical indications at Massachusetts General Hospital between 2006 and 2020. Primary outcome measures were pairwise IRR (average percent agreement [PA] between pairs of experts) and majority IRR (average PA with group consensus) for each class and beyond chance agreement (κ). Secondary outcomes were calibration of expert scoring to group consensus, and latent trait analysis to investigate contributions of bias and noise to scoring variability., Results: Among 2,711 EEGs, 49% were from women, and the median (IQR) age was 55 (41) years. In total, experts scored 50,697 EEG segments; the median [range] number scored by each expert was 6,287.5 [1,002, 45,267]. Overall pairwise IRR was moderate (PA 52%, κ 42%), and majority IRR was substantial (PA 65%, κ 61%). Noise-bias analysis demonstrated that a single underlying receiver operating curve can account for most variation in experts' false-positive vs true-positive characteristics (median [range] of variance explained ([Formula: see text]): 95 [93, 98]%) and for most variation in experts' precision vs sensitivity characteristics ([Formula: see text]: 75 [59, 89]%). Thus, variation between experts is mostly attributable not to differences in expertise but rather to variation in decision thresholds., Discussion: Our results provide precise estimates of expert reliability from a large and diverse sample and a parsimonious theory to explain the origin of disagreements between experts. The results also establish a standard for how well an automated IIIC classifier must perform to match experts., Classification of Evidence: This study provides Class II evidence that an independent expert review reliably identifies ictal-interictal injury continuum patterns on EEG compared with expert consensus., (© 2022 American Academy of Neurology.)

Objective: Interictal epileptiform discharges on EEG are integral to diagnosing epilepsy. However, EEGs are interpreted by readers with and without specialty training, and there is no accepted method to assess skill in interpretation. We aimed to develop a test to quantify IED recognition skills., Methods: A total of 13,262 candidate IEDs were selected from EEGs and scored by eight fellowship-trained reviewers to establish a gold standard. An online test was developed to assess how well readers with different training levels could distinguish candidate waveforms. Sensitivity, false positive rate and calibration were calculated for each reader. A simple mathematical model was developed to estimate each reader's skill and threshold in identifying an IED, and to develop receiver operating characteristics curves for each reader. We investigated the number of IEDs needed to measure skill level with acceptable precision., Results: Twenty-nine raters completed the test; nine experts, seven experienced non-experts and thirteen novices. Median calibration errors for experts, experienced non-experts and novices were -0.056, 0.012, 0.046; median sensitivities were 0.800, 0.811, 0.715; and median false positive rates were 0.177, 0.272, 0.396, respectively. The number of test questions needed to measure those scores was 549. Our analysis identified that novices had a higher noise level (uncertainty) compared to experienced non-experts and experts. Using calculated noise and threshold levels, receiver operating curves were created, showing increasing median area under the curve from novices (0.735), to experienced non-experts (0.852) and experts (0.891)., Significance: Expert and non-expert readers can be distinguished based on ability to identify IEDs. This type of assessment could also be used to identify and correct differences in thresholds in identifying IEDs.

Background: We sought to develop an automatable score to predict hospitalization, critical illness, or death in patients at risk for COVID-19 presenting for urgent care during the Massachusetts outbreak., Methods: Single-center study of adult outpatients seen in respiratory illness clinics (RICs) or the emergency department (ED), including development (n = 9381, March 7-May 2) and prospective (n = 2205, May 3-14) cohorts. Data was queried from Partners Enterprise Data Warehouse. Outcomes were hospitalization, critical illness or death within 7 days. We developed the COVID-19 Acuity Score (CoVA) using automatically extracted data from the electronic medical record and learning-to-rank ordinal logistic regression modeling. Calibration was assessed using predicted-to-observed event ratio (E/O). Discrimination was assessed by C-statistics (AUC)., Results: In the development cohort, 27.3%, 7.2%, and 1.1% of patients experienced hospitalization, critical illness, or death, respectively; and in the prospective cohort, 26.1%, 6.3%, and 0.5%. CoVA showed excellent performance in the development cohort (concurrent validation) for hospitalization (E/O: 1.00, AUC: 0.80); for critical illness (E/O: 1.00, AUC: 0.82); and for death (E/O: 1.00, AUC: 0.87). Performance in the prospective cohort (prospective validation) was similar for hospitalization (E/O: 1.01, AUC: 0.76); for critical illness (E/O 1.03, AUC: 0.79); and for death (E/O: 1.63, AUC=0.93). Among 30 predictors, the top five were age, diastolic blood pressure, blood oxygen saturation, COVID-19 testing status, and respiratory rate., Conclusions: CoVA is a prospectively validated automatable score to assessing risk for adverse outcomes related to COVID-19 infection in the outpatient setting.

Most existing studies used logistic regression to establish scoring systems to predict intensive care unit (ICU) mortality. Machine learning-based approaches can achieve higher prediction accuracy but, unlike the scoring systems, frequently cannot provide explicit interpretability. We evaluated an interpretable ICU mortality prediction model based on Recurrent Neural Networks (RNN) with long short-term memory(LSTM)units. This model combines both sequential features with multiple values over the patient's hospitalization (e.g. vital signs or laboratory tests) and non-sequential features (e.g. diagnoses), while identifying features that most strongly contribute to the outcome. Using a set of 4,896 MICU admissions from a large medical center, the model achieved a c-statistic for prediction of ICU mortality of 0.7614 compared to 0.7412 for a logistic regression model that used the same data, and identified clinically valid predictors (e.g. DNR designation or diagnosis of disseminated intravascular coagulation). Further research is needed to improve interpretability of sequential features analysis and generalizability.