Search

Background: Although the prescription of physical activity in clinical care has been advocated worldwide, in the Netherlands, "Exercise is Medicine" (E = M) is not yet routinely implemented in clinical care. Methods: A set of implementation strategies was pilot implemented to test its feasibility for use in routine care by clinicians in 2 departments of a university medical center. An extensive learning process evaluation was performed, using structured mixed methods methodology, in accordance with the Reach, Effect, Adoption, Implementation, and Maintenance framework. Results: From 5 implementation strategies employed (education, E = M tool embedded in the electronic medical records, lifestyle coach situated within the department, overviews of referral options, and project support), the presence of adequate project support was a strong facilitator of the implementation of E = M. Also, the presence of the lifestyle coach within the department seemed essential for referral rate. Although clinicians appreciated the E = M tool, barriers hampered its use in practice. Conclusions: Specific implementation strategies, tailored to the setting, are effective in facilitating the implementation of E = M with specific regard to education for clinicians on E = M, deployment of a lifestyle coach within a department, and project coordination. Care providers do see a future for lifestyle coaches who are structurally embedded in the hospital, to whom they can easily refer. [ABSTRACT FROM AUTHOR]

This paper explains how value co-creation is affected by the introduction of tools to digitalise healthcare. In particular, this study examines how pregnant women in France collect, utilise, and share their health records after the launch of a new Electronic Health Record (EHR). The paper combines methods from the design field (cultural probes) and micro-phenomenological interviews to capture value co-creation and value co-destruction dynamics. Through analysing nine cases, we highlight the role of patients' expectations in potential value co-destruction with an EHR. We describe why it is important to know by whom and how co-creation is carried out to improve the launch of digital health applications. Finally, the paper emphasises that value co-creation is a long-term process that needs to be studied longitudinally. [ABSTRACT FROM AUTHOR]

BACKGROUND: Family and unpaid caregivers play a crucial role in supporting people living with dementia; yet, they are not systematically identified and documented by health systems. OBJECTIVE: The aims of the study are to determine the extent to which caregivers are currently identified and documented in the electronic health record (EHR) and to elicit the perspectives of caregivers and clinical staff on how to best identify, engage, and support caregivers of people living with dementia through the EHR. METHODS: People with dementia were identified based on International Classification of Diseases, Tenth Revision (ICD-10) codes or dementia medications in the EHR. A chart review of people with dementia characterized how caregiver information was documented and whether caregivers had shared access to the patient portal. Caregivers of eligible people with dementia were then recruited through mailed letters and follow-up calls to the homes of people with dementia. We conducted semistructured interviews with caregivers, clinicians, and staff involved in the care of people with dementia within 2 health systems in Maryland and Colorado. Transcripts were analyzed using a mixed inductive and deductive approach. RESULTS: Caregivers of people with dementia (N=22) were usually identified in the contact information or patient contacts tab (n=20, 91%) by their name and relation to the people with dementia; this tab did not specify the caregivers role. Caregivers were also mentioned, and their roles were described to a varying degree in clinical notes (n=21, 96%). Of the 22 caregivers interviewed, the majority (n=17, 77%) reported that the people with dementia had additional caregivers. The presence of multiple caregivers could be gleaned from most charts (n=16, 73%); however, this information was not captured systematically, and caregivers individual contributions were not explicitly recorded. Interviews with 22 caregivers and 16 clinical staff revealed two major themes: (1) caregiving arrangements are complex and not systematically captured or easy to locate in the EHR and (2) health systems should develop standardized processes to obtain and document caregiver information in the EHR. CONCLUSIONS: This exploratory chart review and qualitative interview study found that people with dementia frequently have multiple caregivers, whose roles and needs are captured inconsistently in the EHR. To address this concern, caregivers and clinical staff suggested that health systems should develop and test workflows to identify caregivers, assess their needs at multiple touchpoints, and record their information in extractable EHR fields.

BackgroundHIV is associated with increased risk of heart failure (HF) but data regarding phenotypes of HF and outcomes after HF diagnosis, especially within the safety net where half of people with HIV in the United States receive care, are less clear.Methods and resultsUsing an electronic health record cohort of all individuals with HF within a municipal safety-net system from 2001 to 2019 linked to the National Death Index Plus, we compared HF phenotypes, all-cause mortality, HF hospitalization, and cause of death for individuals with and without HIV. Among people with HF (n=14 829), 697 individuals had HIV (4.7%). People with HIV were diagnosed with HF 10 years younger on average. A higher proportion of people with HIV had a reduced ejection fraction at diagnosis (37.9% versus 32.7%). Adjusted for age, sex, and risk factors, coronary artery disease on angiography was similar by HIV status. HIV was associated with 55% higher risk of all-cause mortality (hazard ratio [HR], 1.55 [95% CI, 1.37-1.76]; P

PurposeWe examined the effectiveness of proprietary and open large language models (LLMs) in detecting disease presence, location, and treatment response in pancreatic cancer from radiology reports.MethodsWe analyzed 203 deidentified radiology reports, manually annotated for disease status, location, and indeterminate nodules needing follow-up. Using generative pre-trained transformer (GPT)-4, GPT-3.5-turbo, and open models such as Gemma-7B and Llama3-8B, we employed strategies such as ablation and prompt engineering to boost accuracy. Discrepancies between human and model interpretations were reviewed by a secondary oncologist.ResultsAmong 164 patients with pancreatic tumor, GPT-4 showed the highest accuracy in inferring disease status, achieving a 75.5% correctness (F1-micro). Open models Mistral-7B and Llama3-8B performed comparably, with accuracies of 68.6% and 61.4%, respectively. Mistral-7B excelled in deriving correct inferences from objective findings directly. Most tested models demonstrated proficiency in identifying disease containing anatomic locations from a list of choices, with GPT-4 and Llama3-8B showing near-parity in precision and recall for disease site identification. However, open models struggled with differentiating benign from malignant postsurgical changes, affecting their precision in identifying findings indeterminate for cancer. A secondary review occasionally favored GPT-3.5's interpretations, indicating the variability in human judgment.ConclusionLLMs, especially GPT-4, are proficient in deriving oncologic insights from radiology reports. Their performance is enhanced by effective summarization strategies, demonstrating their potential in clinical support and health care analytics. This study also underscores the possibility of zero-shot open model utility in environments where proprietary models are restricted. Finally, by providing a set of annotated radiology reports, this paper presents a valuable data set for further LLM research in oncology.

Introduction: Emergency departments (ED) play a central role in defining the effectiveness and quality of the overall hospital’s mass casualty incident (MCI) response. The use of electronic health records (EHR) in hospital settings has been rapidly growing globally. There is, however, a paucity of literature on the use and performance of EHR during MCIs.Methods: In this study we aimed to describe EHR use, as well as the challenges and lessons learnt in response to the 2020 explosion in the Port of Beirut, Lebanon, during which the hospital received over 360 casualties.Results: Information technology support, reducing EHR system restrictions, cross-function training, focus on registration and patient identification, patient flow and tracking, mobility and bedside access, and alternate sites of care are all important areas to focus on during emergency/disaster response planning.Conclusion: Innovative solutions that help address logistical challenges for different aspects of the disaster response are needed.

PURPOSE: Electronic patient-reported outcome (ePRO) tools are increasingly used to provide first-hand information on patients symptoms and quality of life. This study explored how patients and health care providers (HCPs) perceive the use of a digital real-time ePRO tool, coupled with digital analytics at a cancer center located in a majority-minority county. Furthermore, we described the implementation barriers and facilitators identified from the participants perspectives. METHODS: We conducted a qualitative substudy as part of a larger implementation study conducted at University of California Irvine Chao Family Comprehensive Cancer Center. Patients and HCPs completed semistructured interviews and a focus group discussion. Thematic analysis was used to identify key themes regarding perceived impact of the intervention on patients care and implementation factors. RESULTS: A total of 31 participants, comprising 15 patients (67% English-speaking, 33% Spanish-speaking) and 16 HCPs (43.8% pharmacists, 37.5% physicians, 18.8% nurses), were interviewed. The utilization of real-time ePRO was perceived to beneficially affect patient care, improve patient-provider communication, and increase symptom awareness. Implementation facilitators included ease of comprehension and completion within the infusion center. Barriers included the need to incorporate results in electronic medical records and create real-time referral pathways to address patients needs. CONCLUSION: The use of real-time ePRO in a majority-minority population was perceived to enhance patient-centered oncology care, yet implementation barriers must be addressed for successful integration in clinical settings. The findings from this study may inform implementation strategies to reduce health disparities.

BACKGROUND: The mechanism for recording International Classification of Diseases (ICD) and diagnosis related groups (DRG) codes in a patients chart is through a certified medical coder who manually reviews the medical record at the completion of an admission. High-acuity ICD codes justify DRG modifiers, indicating the need for escalated hospital resources. In this manuscript, we demonstrate that value of rules-based computer algorithms that audit for omission of administrative codes and quantifying the downstream effects with regard to financial impacts and demographic findings did not indicate significant disparities. METHODS: All study data were acquired via the UCLA Department of Anesthesiology and Perioperative Medicines Perioperative Data Warehouse. The DataMart is a structured reporting schema that contains all the relevant clinical data entered into the EPIC (EPIC Systems, Verona, WI) electronic health record. Computer algorithms were created for eighteen disease states that met criteria for DRG modifiers. Each algorithm was run against all hospital admissions with completed billing from 2019. The algorithms scanned for the existence of disease, appropriate ICD coding, and DRG modifier appropriateness. Secondarily, the potential financial impact of ICD omissions was estimated by payor class and an analysis of ICD miscoding was done by ethnicity, sex, age, and financial class. RESULTS: Data from 34,104 hospital admissions were analyzed from January 1, 2019, to December 31, 2019. 11,520 (32.9%) hospital admissions were algorithm positive for a disease state with no corresponding ICD code. 1,990 (5.8%) admissions were potentially eligible for DRG modification/upgrade with an estimated lost revenue of $22,680,584.50. ICD code omission rates compared against reference groups (private payors, Caucasians, middle-aged patients) demonstrated significant p-values

BACKGROUND: Outcome measures are crucial to support a treat-to-target approach to rheumatoid arthritis (RA) care, yet their integration into clinical practice remains inconsistent. We developed an Electronic Heath Record-integrated, patient-facing side-car application to display RA outcomes (disease activity, functional status, pain scores), medications, and lab results during clinical visits (RA PRO Dashboard). The study aimed to evaluate patient perceptions and attitudes towards the implementation of a novel patient-facing dashboard during clinical visits using a mixed-methods approach. METHODS: RA patients whose clinicians used the dashboard at least once during their clinical visit were invited to complete a survey regarding its usefulness in care. We also conducted semi-structured interviews with a subset of patients to assess their perceptions of the dashboard. The interviews were transcribed verbatim and analyzed thematically using deductive and inductive techniques. Emerging themes and subthemes were organized into four domains of the Ecological Model of Health. RESULTS: Out of 173 survey respondents, 79% were interested in seeing the dashboard again at a future visit, 71% felt it improved their understanding of their disease, and 65% believed it helped with decision-making about their RA care. Many patients reported that the dashboard helped them discuss their RA symptoms (76%) and medications (72%) with their clinician. Interviews with 29 RA patients revealed 10 key themes: the dashboard was perceived as a valuable visual tool that improved patients understanding of RA outcome measures, enhanced their involvement in care, and increased their trust in clinicians and the clinic. Common reported limitations included concerns about reliability of RA outcome questionnaires for some RA patients and inconsistent collection and explanation of these measures by clinicians. CONCLUSIONS: In both the quantitative and qualitative components of the study, patients reported that the dashboard improved their understanding of their RA, enhanced patient-clinician communication, supported shared decision-making, and increased patient engagement in care. These findings support the use of dashboards or similar data visualization tools in RA care and can be used in future interventions to address challenges in data collection and patient education.

ObjectivesThis study describes the development and deployment of a machine learning (ML) model called Vent.io to predict mechanical ventilation (MV).Materials and methodsWe trained Vent.io using electronic health record data of adult patients admitted to the intensive care units (ICUs) of the University of California San Diego (UCSD) Health System. We prospectively deployed Vent.io using a real-time platform at UCSD and evaluated the performance of Vent.io for a 1-month period in silent mode and on the MIMIC-IV dataset. As part of deployment, we included a Predetermined Changed Control Plan (PCCP) for continuous model monitoring that triggers model fine-tuning if performance drops below a specified area under the receiver operating curve (AUC) threshold of 0.85.ResultsThe Vent.io model had a median AUC of 0.897 (IQR: 0.892-0.904) with specificity of 0.81 (IQR: 0.812-0.841) and positive predictive value (PPV) of 0.174 (IQR: 0.148-0.176) at a fixed sensitivity of 0.6 during 10-fold cross validation and an AUC of 0.908, sensitivity of 0.632, specificity of 0.849, and PPV of 0.235 during prospective deployment. Vent.io had an AUC of 0.73 on the MIMIC-IV dataset, triggering model fine-tuning per the PCCP as the AUC was below the minimum of 0.85. The fine-tuned Vent.io model achieved an AUC of 0.873.DiscussionDeterioration of model performance is a significant challenge when deploying ML models prospectively or at different sites. Implementation of a PCCP can help models adapt to new patterns in data and maintain generalizability.ConclusionVent.io is a generalizable ML model that has the potential to improve patient care and resource allocation for ICU patients with need for MV.

ObjectivesIn 2016, the Department of Veterans Affairs (VA) and the Department of Energy (DOE) established an Interagency Agreement (IAA), the Million Veteran Program-Computational Health Analytics for Medical Precision to Improve Outcomes Now (MVP-CHAMPION) research collaboration.Materials and methodsOversight fell under the VA Office of Research Development (VA ORD) and DOE headquarters. An Executive Committee and 2 senior scientific liaisons work with VA and DOE leadership to optimize efforts in the service of shared scientific goals. The program supported centralized data management and genomic analysis including creation of a scalable approach to cataloging phenotypes. Cross-cutting methods including natural language processing, image processing, and reusable code were developed.ResultsThe 79.6 million dollar collaboration has supported centralized data management and genomic analysis including a scalable approach to cataloging phenotypes and launched over 10 collaborative scientific projects in health conditions highly prevalent in veterans. A ground-breaking analysis on the Summit and Andes supercomputers at the Oak Ridge National Laboratory (ORNL) of the genetic underpinnings of over 2000 health conditions across 44 million genetic variants which resulted in the identification of 38 270 independent genetic variants associating with one or more health traits. Of these, over 2000 identified associations were unique to non-European ancestry. Cross-cutting methods have advanced state-of-the-art artificial intelligence (AI) including large language natural language processing and a system biology study focused on opioid addiction awarded the 2018 Gordon Bell Prize for outstanding achievement in high-performance computing. The collaboration has completed work in prostate cancer, suicide prevention, and cardiovascular disease, and cross-cutting data science. Predictive models developed in these projects are being tested for application in clinical management.DiscussionEight new projects were launched in 2023, taking advantage of the momentum generated by the previous collaboration. A major challenge has been limitations in the scope of appropriated funds at DOE which cannot currently be used for health research.ConclusionExtensive multidisciplinary interactions take time to establish and are essential to continued progress. New funding models for maintaining high-performance computing infrastructure at the ORNL and for supporting continued collaboration by joint VA-DOE research teams are needed.

The release of GPT-4 and other large language models (LLMs) has the potential to transform healthcare. However, existing research evaluating LLM performance on real-world clinical notes is limited. Here, we conduct a highly-powered study to determine whether LLMs can provide clinical recommendations for three tasks (admission status, radiological investigation(s) request status, and antibiotic prescription status) using clinical notes from the Emergency Department. We randomly selected 10,000 Emergency Department visits to evaluate the accuracy of zero-shot, GPT-3.5-turbo- and GPT-4-turbo-generated clinical recommendations across four different prompting strategies. We found that both GPT-4-turbo and GPT-3.5-turbo performed poorly compared to a resident physician, with accuracy scores 8% and 24%, respectively, lower than physician on average. Both LLMs tended to be overly cautious in its recommendations, with high sensitivity at the cost of specificity. Our findings demonstrate that, while early evaluations of the clinical use of LLMs are promising, LLM performance must be significantly improved before their deployment as decision support systems for clinical recommendations and other complex tasks.

ObjectiveAlthough supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs could reduce the need for large-scale data annotations.Materials and methodsWe curated a dataset of 769 breast cancer pathology reports, manually labeled with 12 categories, to compare zero-shot classification capability of the following LLMs: GPT-4, GPT-3.5, Starling, and ClinicalCamel, with task-specific supervised classification performance of 3 models: random forests, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model.ResultsAcross all 12 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, LSTM-Att (average macro F1-score of 0.86 vs 0.75), with advantage on tasks with high label imbalance. Other LLMs demonstrated poor performance. Frequent GPT-4 error categories included incorrect inferences from multiple samples and from history, and complex task design, and several LSTM-Att errors were related to poor generalization to the test set.DiscussionOn tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of data labeling. However, if the use of LLMs is prohibitive, the use of simpler models with large annotated datasets can provide comparable results.ConclusionsGPT-4 demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in clinical studies.

AIMS: Heart failure (HF) is a clinical syndrome with no definitive diagnostic tests. HF registries are often based on manual reviews of medical records of hospitalized HF patients identified using International Classification of Diseases (ICD) codes. However, most HF patients are not hospitalized, and manual review of big electronic health record (EHR) data is not practical. The US Department of Veterans Affairs (VA) has the largest integrated healthcare system in the nation, and an estimated 1.5 million patients have ICD codes for HF (HF ICD-code universe) in their VA EHR. The objective of our study was to develop artificial intelligence (AI) models to phenotype HF in these patients. METHODS AND RESULTS: The model development cohort (n = 20 000: training, 16 000; validation 2000; testing, 2000) included 10 000 patients with HF and 10 000 without HF who were matched by age, sex, race, inpatient/outpatient status, hospital, and encounter date (within 60 days). HF status was ascertained by manual chart reviews in VAs External Peer Review Program for HF (EPRP-HF) and non-HF status was ascertained by the absence of ICD codes for HF in VA EHR. Two clinicians annotated 1000 random snippets with HF-related keywords and labelled 436 as HF, which was then used to train and test a natural language processing (NLP) model to classify HF (positive predictive value or PPV, 0.81; sensitivity, 0.77). A machine learning (ML) model using linear support vector machine architecture was trained and tested to classify HF using EPRP-HF as cases (PPV, 0.86; sensitivity, 0.86). From the HF ICD-code universe, we randomly selected 200 patients (gold standard cohort) and two clinicians manually adjudicated HF (gold standard HF) in 145 of those patients by chart reviews. We calculated NLP, ML, and NLP + ML scores and used weighted F scores to derive their optimal threshold values for HF classification, which resulted in PPVs of 0.83, 0.77, and 0.85 and sensitivities of 0.86, 0.88, and 0.83, respectively. HF patients classified by the NLP + ML model were characteristically and prognostically similar to those with gold standard HF. All three models performed better than ICD code approaches: one principal hospital discharge diagnosis code for HF (PPV, 0.97; sensitivity, 0.21) or two primary outpatient encounter diagnosis codes for HF (PPV, 0.88; sensitivity, 0.54). CONCLUSIONS: These findings suggest that NLP and ML models are efficient AI tools to phenotype HF in big EHR data to create contemporary HF registries for clinical studies of effectiveness, quality improvement, and hypothesis generation.

OBJECTIVES: This study aimed to develop a machine learning (ML) model to predict disengagement from HIV care, high viral load or death among people living with HIV (PLHIV) with the goal of enabling proactive support interventions in Tanzania. The algorithm addressed common challenges when applying ML to electronic medical record (EMR) data: (1) imbalanced outcome distribution; (2) heterogeneity across multisite EMR data and (3) evolving virological suppression thresholds. DESIGN: Observational study using a national EMR database. SETTING: Conducted in two regions in Tanzania, using data from the National HIV Care database. PARTICIPANTS: The study included over 6 million HIV care visit records from 295 961 PLHIV in two regions in Tanzanias National HIV Care database from January 2015 to May 2023. RESULTS: Our ML model effectively identified PLHIV at increased risk of adverse outcomes. Key predictors included past disengagement from care, antiretroviral therapy (ART) status (which tracks a patients engagement with ART across visits), age and time on ART. The downsampling approach we implemented effectively managed imbalanced data to reduce prediction bias. Site-specific algorithms performed better compared with a universal approach, highlighting the importance of tailoring ML models to local contexts. A sensitivity analysis confirmed the models robustness to changes in viral load suppression thresholds. CONCLUSIONS: ML models leveraging large-scale databases of patient data offer significant potential to identify PLHIV for interventions to enhance engagement in HIV care in resource-limited settings. Tailoring algorithms to local contexts and flexibility towards evolving clinical guidelines are essential for maximising their impact.

RATIONALE: Research studies typically quantify acute respiratory exacerbation episodes (AECOPD) among people with chronic obstructive pulmonary disease (COPD) based on self-report elicited by survey questionnaire. However, AECOPD quantification by self-report could be inaccurate, potentially rendering it an imprecise tool for identification of those with exacerbation tendency. OBJECTIVE: Determine the agreement between self-reported and health records-documented quantification of AECOPD and their association with airway inflammation. METHODS: We administered a questionnaire to elicit the incidence and severity of respiratory exacerbations in the three years preceding the survey among current or former heavy smokers with or without diagnosis of COPD. We then examined electronic health records (EHR) of those with COPD and those without (tobacco-exposed persons with preserved spirometry or TEPS) to determine whether the documentation of the three-year incidence of moderate to very severe respiratory exacerbations was consistent with self-report using Kappa Interrater statistic. A subgroup of participants also underwent bronchoalveolar lavage (BAL) to quantify their airway inflammatory cells. We further used multivariable regressions analysis to estimate the association between respiratory exacerbations and BAL inflammatory cell composition with adjustment for covariates including age, sex, height, weight, smoking status (current versus former) and burden (pack-years). RESULTS: Overall, a total of 511 participants completed the questionnaire, from whom 487 had EHR available for review. Among the 222 participants with COPD (70 ± 7 years-old; 96% male; 70 ± 38 pack-years smoking; 42% current smoking), 57 (26%) reported having any moderate to very severe AECOPD (m/s-AECOPD) while 66 (30%) had EHR documentation of m/s-AECOPD. However, 42% of those with EHR-identified m/s-AECOPD had none by self-report, and 33% of those who reported m/s-AECOPD had none by EHR, suggesting only moderate agreement (Cohens Kappa = 0.47 ± 0.07; P

BACKGROUND: The consent protocol is now a critical part in the overall orchestration of clinical research. We aimed to demonstrate the feasibility of an Ethereum-based informed consent system, which includes an immutable and automated channel of consent matching, to simultaneously assure patient privacy and increase the efficiency of researchers data access. METHOD: We simulated a multi-site scenario, each assigned 10000 consent records. A consent record contained one patients data-sharing preference with regards to seven data categories. We developed a blockchain-based infrastructure with a smart contract to record consents on-chain, and to query consenting patients corresponding to specific criteria. We measured our systems recording efficiency against a baseline design and verified accuracy by testing an exhaustive list of possible queries. RESULTS: Our method achieved ∼3-4% lead with an average insertion speed of ∼2 s per record per node on either a 3-, 4- or 5-node network, and 100 % accuracy. It also outperformed other solutions in external validation. DISCUSSION: The speed we achieved is reasonable in a real-world system under the realistic assumption that patients may not change their minds too frequently, with the added benefit of immutability. Furthermore, the per-insertion time did improve slightly as the number of network nodes increased, attesting to the benefit of node parallelism as it suggests no attrition of insertion efficiency due to scale of nodes. CONCLUSIONS: Our work confirms the technical feasibility of a blockchain-based consent mechanism, assuring patients with an immutable audit trail, and providing researchers with an efficient way to reach their cohorts.

INTRODUCTION: Niraparib first-line maintenance (1LM) therapy has demonstrated clinical benefit for patients with ovarian cancer (OC) in clinical trial and real-world settings, but data on factors associated with real-world patient outcomes remain limited. This analysis identified patient characteristics associated with time to next treatment (TTNT), a proxy for real-world progression-free survival, in patients with OC treated with 1LM niraparib monotherapy. METHODS: This retrospective observational study used a USA nationwide electronic health record-derived deidentified database and included adult patients diagnosed with OC who initiated 1LM niraparib monotherapy after first-line platinum-based chemotherapy. Patients were followed until the earliest occurrence of last clinical activity, death, or end of study period. TTNT was measured from 1LM niraparib initiation to the start of second-line treatment or death. Cox proportional hazards models assessed univariable and multivariable associations between baseline characteristics and TTNT. RESULTS: Of 7872 patients diagnosed with OC, 526 met the eligibility criteria and were included in this analysis. Median (IQR) duration of follow-up was 14.1 (7.4-23.6) months. In univariable analyses, age, BRCA/homologous recombination deficiency (HRD) status, socioeconomic status, stage at initial diagnosis, cytoreductive surgery type, and residual disease status were significantly associated with observed TTNT and were introduced into the multivariable model with other clinically relevant variables. In the multivariable analysis, BRCA/HRD status, cytoreductive surgery type, and residual disease status were significantly associated with observed TTNT after covariate adjustment. Conversely, age, Eastern Cooperative Oncology Group performance status, disease stage, niraparib starting dose status, and first-line bevacizumab use were not associated with observed TTNT. CONCLUSION: This real-world, retrospective, observational analysis offers valuable insights on prognostic factors associated with TTNT in patients with OC treated with 1LM niraparib monotherapy after first-line platinum-based chemotherapy. Future studies are needed to examine how additional patient characteristics associated with clinical outcomes may guide treatment decisions and improve outcomes.

The article shares views on opportunities and challenges posed by big data (BD), mobile health and artificial intelligence to dentistry and craniofacial research. Topics discussed include concerns about privacy, security and data sharing in relation to the use of BD analysis, the Dental, Oral, Medical Epidemiological (DOME) electronic records-based BD study, and the role of combining electronic health record with mobile health tools in improving data sets and in advancing BD research.

Objective: The evidence base for the use of space maintainers is relatively sparce despite being used for decades after the premature loss of primary molars. This study aims to increase the dental evidence base via investigating retrospectively the success rates of prefabricated fixed and removable space maintainers inserted from 2019 to 2021 and followed up until February 2023 at a specialized university clinic and to identify reasons for any reported minor and major failure. The authors hypothesized that there is no significant difference in failure rates between fixed and removable space maintainers inserted after the premature loss of a single primary molar per quadrant. Method and materials: Patients' digital records were searched yielding 645 space maintainers. After the application of inclusion criteria, 157 (67%) fixed prefabricated space maintainers in 112 children and 77 (33%) removable space maintainers in 61 children were analyzed for an average of 18.4 ± 9.5 months. Results: Kaplan-Meier survival analysis with Mantel-Cox statistics showed an overall cumulative survival time of 31.6 months (SE = 1.15, 95% CI = 29.4 to 33.9). Major failure occurred significantly more in removable maintainers (n = 40/67, 59.7%), mostly due to loss of the appliance, compared to fixed space maintainers (n = 27/67, 40.3%; P < .001). The present study indicates that space maintainers were mainly placed in young children with high caries experience, where treatment was mostly possible using advanced behavior management. Conclusions: Fixed space maintainers had a significantly lower failure rate than their removable counterpart. However, both require continual repairs, preservation, or even replacement till the eruption of the permanent tooth. [ABSTRACT FROM AUTHOR]

BackgroundOne challenge for primary care providers caring for patients with nonalcoholic fatty liver disease is to identify those at the highest risk for clinically significant liver disease.AimTo derive a risk stratification tool using variables from structured electronic health record (EHR) data for use in populations which are disproportionately affected with obesity and diabetes.MethodsWe used data from 344 participants who underwent Fibroscan examination to measure liver fat and liver stiffness measurement [LSM]. Using two approaches, multivariable logistic regression and random forest classification, we assessed risk factors for any hepatic fibrosis (LSM > 7 kPa) and significant hepatic fibrosis (> 8 kPa). Possible predictors included data from the EHR for age, gender, diabetes, hypertension, FIB-4, body mass index (BMI), LDL, HDL, and triglycerides.ResultsOf 344 patients (56.4% women), 34 had any hepatic fibrosis, and 15 significant hepatic fibrosis. Three variables (BMI, FIB-4, diabetes) were identified from both approaches. When we used variable cut-offs defined by Youden's index, the final model predicting any hepatic fibrosis had an AUC of 0.75 (95% CI 0.67-0.84), NPV of 91.5% and PPV of 40.0%. The final model with variable categories based on standard clinical thresholds (i.e., BMI ≥ 30 kg/m2; FIB-4 ≥ 1.45) had lower discriminatory ability (AUC 0.65), but higher PPV (50.0%) and similar NPV (91.3%). We observed similar findings for predicting significant hepatic fibrosis.ConclusionsOur results demonstrate that standard thresholds for clinical risk factors/biomarkers may need to be modified for greater discriminatory ability among populations with high prevalence of obesity and diabetes.

OBJECTIVE: The study aimed to develop natural language processing (NLP) algorithms to automate extracting patient-centred breast cancer treatment outcomes from clinical notes in electronic health records (EHRs), particularly for women from under-represented populations. METHODS: The study used clinical notes from 2010 to 2021 from a tertiary hospital in the USA. The notes were processed through various NLP techniques, including vectorisation methods (term frequency-inverse document frequency (TF-IDF), Word2Vec, Doc2Vec) and classification models (support vector classification, K-nearest neighbours (KNN), random forest (RF)). Feature selection and optimisation through random search and fivefold cross-validation were also conducted. RESULTS: The study annotated 100 out of 1000 clinical notes, using 970 notes to build the text corpus. TF-IDF and Doc2Vec combined with RF showed the highest performance, while Word2Vec was less effective. RF classifier demonstrated the best performance, although with lower recall rates, suggesting more false negatives. KNN showed lower recall due to its sensitivity to data noise. DISCUSSION: The study highlights the significance of using NLP in analysing clinical notes to understand breast cancer treatment outcomes in under-represented populations. The TF-IDF and Doc2Vec models were more effective in capturing relevant information than Word2Vec. The study observed lower recall rates in RF models, attributed to the datasets imbalanced nature and the complexity of clinical notes. CONCLUSION: The study developed high-performing NLP pipeline to capture treatment outcomes for breast cancer in under-represented populations, demonstrating the importance of document-level vectorisation and ensemble methods in clinical notes analysis. The findings provide insights for more equitable healthcare strategies and show the potential for broader NLP applications in clinical settings.

PurposeUse of the electronic health record (EHR) has motivated the need for data standardization. A gap in knowledge exists regarding variations in existing terminologies for defining diabetic retinopathy (DR) cohorts. This study aimed to review the literature and analyze variations regarding codified definitions of DR.DesignLiterature review and quantitative analysis.SubjectsPublished manuscripts.MethodsFour graders reviewed PubMed and Google Scholar for peer-reviewed studies. Studies were included if they used codified definitions of DR (e.g., billing codes). Data elements such as author names, publication year, purpose, data set type, and DR definitions were manually extracted. Each study was reviewed by ≥ 2 authors to validate inclusion eligibility. Quantitative analyses of the codified definitions were then performed to characterize the variation between DR cohort definitions.Main outcome measuresNumber of studies included and numeric counts of billing codes used to define codified cohorts.ResultsIn total, 43 studies met the inclusion criteria. Half of the included studies used datasets based on structured EHR data (i.e., data registries, institutional EHR review), and half used claims data. All but 1 of the studies used billing codes such as the International Classification of Diseases 9th or 10th edition (ICD-9 or ICD-10), either alone or in addition to another terminology for defining disease. Of the 27 included studies that used ICD-9 and the 20 studies that used ICD-10 codes, the most common codes used pertained to the full spectrum of DR severity. Diabetic retinopathy complications (e.g., vitreous hemorrhage) were also used to define some DR cohorts.ConclusionsSubstantial variations exist among codified definitions for DR cohorts within retrospective studies. Variable definitions may limit generalizability and reproducibility of retrospective studies. More work is needed to standardize disease cohorts.Financial disclosuresProprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

OBJECTIVE: This study evaluates regularization variants in logistic regression (L1, L2, ElasticNet, Adaptive L1, Adaptive ElasticNet, Broken adaptive ridge [BAR], and Iterative hard thresholding [IHT]) for discrimination and calibration performance, focusing on both internal and external validation. MATERIALS AND METHODS: We use data from 5 US claims and electronic health record databases and develop models for various outcomes in a major depressive disorder patient population. We externally validate all models in the other databases. We use a train-test split of 75%/25% and evaluate performance with discrimination and calibration. Statistical analysis for difference in performance uses Friedmans test and critical difference diagrams. RESULTS: Of the 840 models we develop, L1 and ElasticNet emerge as superior in both internal and external discrimination, with a notable AUC difference. BAR and IHT show the best internal calibration, without a clear external calibration leader. ElasticNet typically has larger model sizes than L1. Methods like IHT and BAR, while slightly less discriminative, significantly reduce model complexity. CONCLUSION: L1 and ElasticNet offer the best discriminative performance in logistic regression for healthcare predictions, maintaining robustness across validations. For simpler, more interpretable models, L0-based methods (IHT and BAR) are advantageous, providing greater parsimony and calibration with fewer features. This study aids in selecting suitable regularization techniques for healthcare prediction models, balancing performance, complexity, and interpretability.

BACKGROUND: Language in nonmedical data sets is known to transmit human-like biases when used in natural language processing (NLP) algorithms that can reinforce disparities. It is unclear if NLP algorithms of medical notes could lead to similar transmissions of biases. RESEARCH QUESTION: Can we identify implicit bias in clinical notes, and are biases stable across time and geography? STUDY DESIGN AND METHODS: To determine whether different racial and ethnic descriptors are similar contextually to stigmatizing language in ICU notes and whether these relationships are stable across time and geography, we identified notes on critically ill adults admitted to the University of California, San Francisco (UCSF), from 2012 through 2022 and to Beth Israel Deaconess Hospital (BIDMC) from 2001 through 2012. Because word meaning is derived largely from context, we trained unsupervised word-embedding algorithms to measure the similarity (cosine similarity) quantitatively of the context between a racial or ethnic descriptor (eg, African-American) and a stigmatizing target word (eg, nonco-operative) or group of words (violence, passivity, noncompliance, nonadherence). RESULTS: In UCSF notes, Black descriptors were less likely to be similar contextually to violent words compared with White descriptors. Contrastingly, in BIDMC notes, Black descriptors were more likely to be similar contextually to violent words compared with White descriptors. The UCSF data set also showed that Black descriptors were more similar contextually to passivity and noncompliance words compared with Latinx descriptors. INTERPRETATION: Implicit bias is identifiable in ICU notes. Racial and ethnic group descriptors carry different contextual relationships to stigmatizing words, depending on when and where notes were written. Because NLP models seem able to transmit implicit bias from training data, use of NLP algorithms in clinical prediction could reinforce disparities. Active debiasing strategies may be necessary to achieve algorithmic fairness when using language models in clinical research.

BACKGROUND: Physician communication failures during transfers of patients from the intensive care unit (ICU) to the general ward are common and can lead to adverse events. Efforts to improve written handoffs during these transfers are increasingly prominent, but no instruments have been developed to assess the quality of physician ICU-ward transfer notes. OBJECTIVE: To collect validity evidence for the modified nine-item Physician Documentation Quality Instrument (mPDQI-9) for assessing ICU-ward transfer note usefulness across several hospitals. METHODS: Twenty-four physician raters independently used the mPDQI-9 to grade 12 notes collected from three academic hospitals. A priori, we excluded the up-to-date and accurate domains, because these could not be assessed without giving the rater access to the complete patient chart. Assessments therefore used the domains thorough, useful, organized, comprehensible, succinct, synthesized, and consistent. Raters scored each domain on a Likert scale ranging from 1 (low) to 5 (high). The total mPDQI-9 was the sum of these domain scores. The primary outcome was the raters perceived clinical utility of the notes, and the primary measures of interest were criterion validity (Spearmans ρ) and interrater reliability (intraclass correlation [ICC]). RESULTS: Mean mPDQI-9 scores by note ranged from 19 (SD = 5.5) to 30 (SD = 4.2). Mean note ratings did not systematically differ by rater expertise (for interaction, P = 0.15). The proportion of raters perceiving each note as independently sufficient for patient care (the primary outcome) ranged from 33% to 100% across the set of notes. We found a moderately positive correlation between mPDQI-9 ratings and raters overall assessments of each notes clinical utility (ρ = 0.48, P

Acute COVID-19 infection can be followed by diverse clinical manifestations referred to as Post Acute Sequelae of SARS-CoV2 Infection (PASC). Studies have shown an increased risk of being diagnosed with new-onset psychiatric disease following a diagnosis of acute COVID-19. However, it was unclear whether non-psychiatric PASC-associated manifestations (PASC-AMs) are associated with an increased risk of new-onset psychiatric disease following COVID-19. A retrospective electronic health record (EHR) cohort study of 2,391,006 individuals with acute COVID-19 was performed to evaluate whether non-psychiatric PASC-AMs are associated with new-onset psychiatric disease. Data were obtained from the National COVID Cohort Collaborative (N3C), which has EHR data from 76 clinical organizations. EHR codes were mapped to 151 non-psychiatric PASC-AMs recorded 28-120 days following SARS-CoV-2 diagnosis and before diagnosis of new-onset psychiatric disease. Association of newly diagnosed psychiatric disease with age, sex, race, pre-existing comorbidities, and PASC-AMs in seven categories was assessed by logistic regression. There were significant associations between a diagnosis of any psychiatric disease and five categories of PASC-AMs with odds ratios highest for neurological, cardiovascular, and constitutional PASC-AMs with odds ratios of 1.31, 1.29, and 1.23 respectively. Secondary analysis revealed that the proportions of 50 individual clinical features significantly differed between patients diagnosed with different psychiatric diseases. Our study provides evidence for association between non-psychiatric PASC-AMs and the incidence of newly diagnosed psychiatric disease. Significant associations were found for features related to multiple organ systems. This information could prove useful in understanding risk stratification for new-onset psychiatric disease following COVID-19. Prospective studies are needed to corroborate these findings.

BackgroundIschemic cardiomyopathy is the leading cause of heart failure (HF). Most patients do not undergo coronary assessment after HF diagnosis. There are no randomized clinical trials of coronary assessment after HF diagnosis.MethodsUsing an electronic health record cohort of all individuals with HF within the San Francisco Health Network from 2001 to 2019, we identified factors associated with coronary assessment. Then, we studied the association of coronary assessment within 30 days of HF diagnosis with all-cause mortality and a composite of mortality and emergent angiography using a target trial emulation observational comparative-effectiveness approach. Target trial emulation is an approach to causal inference based on creating a hypothetical randomized clinical trial protocol and using observational data to emulate the protocol. We used propensity scores for covariate adjustment. We used national death records to improve the ascertainment of mortality and included falsification end points for the cause of death.ResultsAmong 14 829 individuals with HF (median, 62 years old; 5855 [40%] women), 3987 (26.9%) ever completed coronary assessment, with 2467/13 301 (18.5%) with unknown coronary artery disease status at HF diagnosis assessed. Women, older individuals, and people without stable housing were less likely to complete coronary assessment. Among 5972 eligible persons of whom 627 underwent early elective coronary assessment, coronary assessment was associated with lower mortality (hazard ratio, 0.84 [95% CI, 0.72-0.97]; P=0.025), reduced risk of the composite outcome (hazard ratio, 0.86 [95% CI, 0.73-1.00]), higher rates of revascularization (odds ratio, 7.6 [95% CI, 5.4-10.6]), and higher use of medical therapy (odds ratio, 2.5 [95% CI, 1.7-3.6]), but not the falsification end points.ConclusionsIn a safety-net population, disparities in coronary assessment after HF diagnosis are not fully explained by coronary artery disease risk factors. Early coronary assessment is associated with improved HF outcomes possibly related to higher rates of revascularization and guideline-directed medical therapy but with low certainty that this finding is not attributable to unmeasured confounding.

Tobacco use disorder (TUD) is the most prevalent substance use disorder in the world. Genetic factors influence smoking behaviours and although strides have been made using genome-wide association studies to identify risk variants, most variants identified have been for nicotine consumption, rather than TUD. Here we leveraged four US biobanks to perform a multi-ancestral meta-analysis of TUD (derived via electronic health records) in 653,790 individuals (495,005 European, 114,420 African American and 44,365 Latin American) and data from UK Biobank (ncombined = 898,680). We identified 88 independent risk loci; integration with functional genomic tools uncovered 461 potential risk genes, primarily expressed in the brain. TUD was genetically correlated with smoking and psychiatric traits from traditionally ascertained cohorts, externalizing behaviours in children and hundreds of medical outcomes, including HIV infection, heart disease and pain. This work furthers our biological understanding of TUD and establishes electronic health records as a source of phenotypic information for studying the genetics of TUD.