Retrieval-Augmented Generation for Extracting CHA2DS2-VASc Risk Factors from Unstructured Clinical Notes in Patients with Atrial Fibrillation.

Background: Assessment of stroke risk in patients with atrial fibrillation (AF) is crucial for guiding anticoagulation therapy. CHA2DS2-VASc is a widely used score for defining this risk, but current assessments rely on manual calculation by clinicians or approximations from structured EHR data elements. Unstructured clinical notes contain rich information that could enhance risk assessment. We developed and validated a Retrieval-Augmented Generation (RAG) approach to extract CHA2DS2-VASc risk factors from unstructured notes in patients with AF. Methods: We employed a RAG architecture paired with the large language model, Llama3.1, to extract features relevant to CHA2DS2-VASc scores from unstructured notes. The model was deployed on a random set of 1,000 clinical notes (934 AF patients) from Yale New Haven Health System (YNHHS). To establish a gold standard, 2 clinicians manually reviewed and labeled CHA2DS2-VASc risk factors in a random subset of 200 notes. The CHA2DS2-VASc scores were calculated for each patient using structured data alone and by incorporating risk factors identified with RAG. We assessed performance across risk factors using macro-averaged area under the receiver operating characteristic (AUROC). For external validation, we utilized 100 manually labeled clinical notes from the MIMIC-IV database. Results: The RAG model demonstrated robust performance in extracting risk factors from clinical notes. In the 1000 clinical notes, RAG identified several risk factors more frequently than structured elements, including hypertension (82.4% vs 26.2%), stroke/TIA (62.9% vs 45.5%), vascular disease (83.4% vs 56.6%), and diabetes (84.1% vs 47.2%). In the 200 expert-annotated notes, the RAG approach achieved high performance for various risk factors, with AUROCs ranging from 0.96 to 0.98 for hypertension, diabetes, and age ≥75 years. Incorporating risk factors identified by RAG increased CHA2DS2-VASc scores compared with using structured data alone. Conclusion: An LLM-optimized RAG can accurately extract CHA2DS2-VASc risk factors from unstructured clinical notes in AF patients. This approach can enable computable risk assessment and guide appropriate anticoagulation therapy.

A Deep Learning Approach for Automated Extraction of Functional Status and New York Heart Association Class for Heart Failure Patients During Clinical Encounters.

Introduction: Serial functional status assessments are critical to heart failure (HF) management but are often described narratively in documentation, limiting their use in quality improvement or patient selection for clinical trials. We developed and validated a deep learning-based natural language processing (NLP) strategy to extract functional status assessments from unstructured clinical notes. Methods: We identified 26,577 HF patients across outpatient services at Yale New Haven Hospital (YNHH), Greenwich Hospital (GH), and Northeast Medical Group (NMG) (mean age 76.1 years; 52.0% women). We used expert annotated notes from YNHH for model development/internal testing and from GH and NMG for external validation. The primary outcomes were NLP models to detect (a) explicit New York Heart Association (NYHA) classification, (b) HF symptoms during activity or rest, and (c) functional status assessment frequency. Results: Among 3,000 expert-annotated notes, 13.6% mentioned NYHA class, and 26.5% described HF symptoms. The model to detect NYHA classes achieved a class-weighted AUROC of 0.99 (95% CI: 0.98-1.00) at YNHH, 0.98 (0.96-1.00) at NMG, and 0.98 (0.92-1.00) at GH. The activity-related HF symptom model achieved an AUROC of 0.94 (0.89-0.98) at YNHH, 0.94 (0.91-0.97) at NMG, and 0.95 (0.92-0.99) at GH. Deploying the NYHA model among 166,655 unannotated notes from YNHH identified 21,528 (12.9%) with NYHA mentions and 17,642 encounters (10.5%) classifiable into functional status groups based on activity-related symptoms. Conclusions: We developed and validated an NLP approach to extract NYHA classification and activity-related HF symptoms from clinical notes, enhancing the ability to track optimal care and identify trial-eligible patients.

Automated Identification of Heart Failure With Reduced Ejection Fraction Using Deep Learning-Based Natural Language Processing.

BACKGROUND: The lack of automated tools for measuring care quality limits the implementation of a national program to assess guideline-directed care in heart failure with reduced ejection fraction (HFrEF). OBJECTIVES: The authors aimed to automate the identification of patients with HFrEF at hospital discharge, an opportunity to evaluate and improve the quality of care. METHODS: The authors developed a novel deep-learning language model for identifying patients with HFrEF from discharge summaries of hospitalizations with heart failure at Yale New Haven Hospital during 2015 to 2019. HFrEF was defined by left ventricular ejection fraction <40% on antecedent echocardiography. The authors externally validated the model at Northwestern Medicine, community hospitals of Yale, and the MIMIC-III (Medical Information Mart for Intensive Care III) database. RESULTS: A total of 13,251 notes from 5,392 unique individuals (age 73 ± 14 years, 48% women), including 2,487 patients with HFrEF (46.1%), were used for model development (train/held-out: 70%/30%). The model achieved an area under receiver-operating characteristic curve (AUROC) of 0.97 and area under precision recall curve (AUPRC) of 0.97 in detecting HFrEF on the held-out set. The model had high performance in identifying HFrEF with AUROC = 0.94 and AUPRC = 0.91 on 19,242 notes from Northwestern Medicine, AUROC = 0.95 and AUPRC = 0.96 on 139 manually abstracted notes from Yale community hospitals, and AUROC = 0.91 and AUPRC = 0.92 on 146 manually reviewed notes from MIMIC-III. Model-based predictions of HFrEF corresponded to a net reclassification improvement of 60.2 ± 1.9% compared with diagnosis codes (P < 0.001). CONCLUSIONS: The authors developed a language model that identifies HFrEF from clinical notes with high precision and accuracy, representing a key element in automating quality assessment for individuals with HFrEF.

Study Protocol for the Artificial Intelligence-Driven Evaluation of Structural Heart Diseases Using Wearable Electrocardiogram (ID-SHD).

Introduction: Portable devices capable of electrocardiogram (ECG) acquisition have the potential to enhance structural heart disease (SHD) management by enabling early detection through artificial intelligence-ECG (AI-ECG) algorithms. However, the performance of these AI algorithms for identifying SHD in a real-world screening setting is unknown. To address this gap, we aim to evaluate the validity of our wearable-adapted AI algorithm, which has been previously developed and validated for detecting SHD from single-lead portable ECGs in patients undergoing routine echocardiograms in the Yale New Haven Hospital (YNHH). Research Methods and Analysis: This is the protocol for a cross-sectional study in the echocardiographic laboratories of YNHH. The study will enroll 585 patients referred for outpatient transthoracic echocardiogram (TTE) as part of their routine clinical care. Patients expressing interest in participating in the study will undergo a screening interview, followed by enrollment upon meeting eligibility criteria and providing informed consent. During their routine visit, patients will undergo a 1-lead ECG with two devices - one with an Apple Watch and the second with another portable 1-lead ECG device. With participant consent, these 1-lead ECG data will be linked to participant demographic and clinical data recorded in the YNHH electronic health records (EHR). The study will assess the performance of the AI-ECG algorithm in identifying SHD, including left ventricular systolic dysfunction (LVSD), valvular disease and severe left ventricular hypertrophy (LVH), by comparing the algorithm's results with data obtained from TTE, which is the established gold standard for diagnosing SHD. Ethics and Dissemination: All patient EHR data required for assessing eligibility and conducting the AI-ECG will be accessed through secure servers approved for protected health information. Data will be maintained on secure, encrypted servers for a minimum of five years after the publication of our findings in a peer-reviewed journal, and any unanticipated adverse events or risks will be reported by the principal investigator to the Yale Institutional Review Board, which has reviewed and approved this protocol (Protocol Number: 2000035532).

Comparative Effectiveness of Second-line Antihyperglycemic Agents for Cardiovascular Outcomes: A Large-scale, Multinational, Federated Analysis of the LEGEND-T2DM Study.

Background: SGLT2 inhibitors (SGLT2is) and GLP-1 receptor agonists (GLP1-RAs) reduce major adverse cardiovascular events (MACE) in patients with type 2 diabetes mellitus (T2DM). However, their effectiveness relative to each other and other second-line antihyperglycemic agents is unknown, without any major ongoing head-to-head trials. Methods: Across the LEGEND-T2DM network, we included ten federated international data sources, spanning 1992-2021. We identified 1,492,855 patients with T2DM and established cardiovascular disease (CVD) on metformin monotherapy who initiated one of four second-line agents (SGLT2is, GLP1-RAs, dipeptidyl peptidase 4 inhibitor [DPP4is], sulfonylureas [SUs]). We used large-scale propensity score models to conduct an active comparator, target trial emulation for pairwise comparisons. After evaluating empirical equipoise and population generalizability, we fit on-treatment Cox proportional hazard models for 3-point MACE (myocardial infarction, stroke, death) and 4-point MACE (3-point MACE + heart failure hospitalization) risk, and combined hazard ratio (HR) estimates in a random-effects meta-analysis. Findings: Across cohorts, 16·4%, 8·3%, 27·7%, and 47·6% of individuals with T2DM initiated SGLT2is, GLP1-RAs, DPP4is, and SUs, respectively. Over 5·2 million patient-years of follow-up and 489 million patient-days of time at-risk, there were 25,982 3-point MACE and 41,447 4-point MACE events. SGLT2is and GLP1-RAs were associated with a lower risk for 3-point MACE compared with DPP4is (HR 0·89 [95% CI, 0·79-1·00] and 0·83 [0·70-0·98]), and SUs (HR 0·76 [0·65-0·89] and 0·71 [0·59-0·86]). DPP4is were associated with a lower 3-point MACE risk versus SUs (HR 0·87 [0·79-0·95]). The pattern was consistent for 4-point MACE for the comparisons above. There were no significant differences between SGLT2is and GLP1-RAs for 3-point or 4-point MACE (HR 1·06 [0·96-1·17] and 1·05 [0·97-1·13]). Interpretation: In patients with T2DM and established CVD, we found comparable cardiovascular risk reduction with SGLT2is and GLP1-RAs, with both agents more effective than DPP4is, which in turn were more effective than SUs. These findings suggest that the use of GLP1-RAs and SGLT2is should be prioritized as second-line agents in those with established CVD. Funding: National Institutes of Health, United States Department of Veterans Affairs.

Comparative Effectiveness of Second-Line Antihyperglycemic Agents for Cardiovascular Outcomes: A Multinational, Federated Analysis of LEGEND-T2DM.

BACKGROUND: Sodium-glucose cotransporter 2 inhibitors (SGLT2is) and glucagon-like peptide-1 receptor agonists (GLP-1 RAs) reduce the risk of major adverse cardiovascular events (MACE) in patients with type 2 diabetes mellitus (T2DM). However, their effectiveness relative to each other and other second-line antihyperglycemic agents is unknown, without any major ongoing head-to-head clinical trials. OBJECTIVES: The aim of this study was to compare the cardiovascular effectiveness of SGLT2is, GLP-1 RAs, dipeptidyl peptidase-4 inhibitors (DPP4is), and clinical sulfonylureas (SUs) as second-line antihyperglycemic agents in T2DM. METHODS: Across the LEGEND-T2DM (Large-Scale Evidence Generation and Evaluation Across a Network of Databases for Type 2 Diabetes Mellitus) network, 10 federated international data sources were included, spanning 1992 to 2021. In total, 1,492,855 patients with T2DM and cardiovascular disease (CVD) on metformin monotherapy were identified who initiated 1 of 4 second-line agents (SGLT2is, GLP-1 RAs, DPP4is, or SUs). Large-scale propensity score models were used to conduct an active-comparator target trial emulation for pairwise comparisons. After evaluating empirical equipoise and population generalizability, on-treatment Cox proportional hazards models were fit for 3-point MACE (myocardial infarction, stroke, and death) and 4-point MACE (3-point MACE plus heart failure hospitalization) risk and HR estimates were combined using random-effects meta-analysis. RESULTS: Over 5.2 million patient-years of follow-up and 489 million patient-days of time at risk, patients experienced 25,982 3-point MACE and 41,447 4-point MACE. SGLT2is and GLP-1 RAs were associated with lower 3-point MACE risk than DPP4is (HR: 0.89 [95% CI: 0.79-1.00] and 0.83 [95% CI: 0.70-0.98]) and SUs (HR: 0.76 [95% CI: 0.65-0.89] and 0.72 [95% CI: 0.58-0.88]). DPP4is were associated with lower 3-point MACE risk than SUs (HR: 0.87; 95% CI: 0.79-0.95). The pattern for 3-point MACE was also observed for the 4-point MACE outcome. There were no significant differences between SGLT2is and GLP-1 RAs for 3-point or 4-point MACE (HR: 1.06 [95% CI: 0.96-1.17] and 1.05 [95% CI: 0.97-1.13]). CONCLUSIONS: In patients with T2DM and CVD, comparable cardiovascular risk reduction was found with SGLT2is and GLP-1 RAs, with both agents more effective than DPP4is, which in turn were more effective than SUs. These findings suggest that the use of SGLT2is and GLP-1 RAs should be prioritized as second-line agents in those with established CVD.

Cardiovascular Care Innovation through Data-Driven Discoveries in the Electronic Health Record.

The electronic health record (EHR) represents a rich source of patient information, increasingly being leveraged for cardiovascular research. Although its primary use remains the seamless delivery of health care, the various longitudinally aggregated structured and unstructured data elements for each patient within the EHR can define the computational phenotypes of disease and care signatures and their association with outcomes. Although structured data elements, such as demographic characteristics, laboratory measurements, problem lists, and medications, are easily extracted, unstructured data are underused. The latter include free text in clinical narratives, documentation of procedures, and reports of imaging and pathology. Rapid scaling up of data storage and rapid innovation in natural language processing and computer vision can power insights from unstructured data streams. However, despite an array of opportunities for research using the EHR, specific expertise is necessary to adequately address confidentiality, accuracy, completeness, and heterogeneity challenges in EHR-based research. These often require methodological innovation and best practices to design and conduct successful research studies. Our review discusses these challenges and their proposed solutions. In addition, we highlight the ongoing innovations in federated learning in the EHR through a greater focus on common data models and discuss ongoing work that defines such an approach to large-scale, multicenter, federated studies. Such parallel improvements in technology and research methods enable innovative care and optimization of patient outcomes.

Nonexercise machine learning models for maximal oxygen uptake prediction in national population surveys.

OBJECTIVE: Nonexercise algorithms are cost-effective methods to estimate cardiorespiratory fitness (CRF), but the existing models have limitations in generalizability and predictive power. This study aims to improve the nonexercise algorithms using machine learning (ML) methods and data from US national population surveys. MATERIALS AND METHODS: We used the 1999-2004 data from the National Health and Nutrition Examination Survey (NHANES). Maximal oxygen uptake (VO2 max), measured through a submaximal exercise test, served as the gold standard measure for CRF in this study. We applied multiple ML algorithms to build 2 models: a parsimonious model using commonly available interview and examination data, and an extended model additionally incorporating variables from Dual-Energy X-ray Absorptiometry (DEXA) and standard laboratory tests in clinical practice. Key predictors were identified using Shapley additive explanation (SHAP). RESULTS: Among the 5668 NHANES participants in the study population, 49.9% were women and the mean (SD) age was 32.5 years (10.0). The light gradient boosting machine (LightGBM) had the best performance across multiple types of supervised ML algorithms. Compared with the best existing nonexercise algorithms that could be applied to the NHANES, the parsimonious LightGBM model (RMSE: 8.51 ml/kg/min [95% CI: 7.73-9.33]) and the extended LightGBM model (RMSE: 8.26 ml/kg/min [95% CI: 7.44-9.09]) significantly reduced the error by 15% and 12% (P < .001 for both), respectively. DISCUSSION: The integration of ML and national data source presents a novel approach for estimating cardiovascular fitness. This method provides valuable insights for cardiovascular disease risk classification and clinical decision-making, ultimately leading to improved health outcomes. CONCLUSION: Our nonexercise models provide improved accuracy in estimating VO2 max within NHANES data as compared to existing nonexercise algorithms.

Ocular complications of plasma cell dyscrasias.

Plasma cell dyscrasias are a wide range of severe monoclonal gammopathies caused by pre-malignant or malignant plasma cells that over-secrete an abnormal monoclonal antibody. These disorders are associated with various systemic findings, including ophthalmological disorders. A search of PubMed, EMBASE, Scopus and Cochrane databases was performed in March 2021 to examine evidence pertaining to ocular complications in patients diagnosed with plasma cell dyscrasias. This review outlines the ocular complications associated with smoldering multiple myeloma and monoclonal gammopathy of undetermined significance, plasmacytomas, multiple myeloma, Waldenström's macroglobulinemia, systemic amyloidosis, Polyneuropathy, Organomegaly, Endocrinopathy, Monoclonal gammopathy and Skin changes (POEMS) syndrome, and cryoglobulinemia. Although, the pathological mechanisms are not completely elucidated yet, wide-ranging ocular presentations have been identified over the years, evolving both the anterior and posterior segments of the eye. Moreover, the presenting symptoms also help in early diagnosis in asymptomatic patients. Therefore, it is imperative for the treating ophthalmologist and oncologist to maintain a high clinical suspicion for identifying the ophthalmological signs and diagnosing the underlying disease, preventing its progression through efficacious treatment strategies.

Identification of Hypertrophic Cardiomyopathy on Electrocardiographic Images with Deep Learning.

Background: Hypertrophic cardiomyopathy (HCM) affects 1 in every 200 individuals and is the leading cause of sudden cardiac death in young adults. HCM can be identified using an electrocardiogram (ECG) raw voltage data and deep learning approaches, but their point-of-care application is limited by the inaccessibility of these signal data. We developed a deep learning-based approach that overcomes this limitation and detects HCM from images of 12-lead ECGs across layouts. Methods: We identified ECGs from patients with HCM features present on cardiac magnetic resonance imaging (CMR) or those within 30 days of an echocardiogram documenting thickened interventricular septum (end-diastolic interventricular septum thickness > 15mm). Patients with CMR-confirmed HCM were considered as cases during the final model evaluation. The model was validated within clinical settings at YNHH and externally on ECG images from the prospective, population-based UK Biobank cohort. We localized class-discriminating signals in ECG images using gradient-weighted class activation mapping. Results: Overall, 124,553 ECGs from 66,987 individuals (HCM cases and controls) were used for model development. The model demonstrated high discrimination for HCM across various ECG image formats and calibrations in internal validation (area under receiving operation characteristics [AUROC] 0.96) and external sets of ECG images from UK Biobank (AUROC 0.94). A positive screen for HCM was associated with a 100-fold higher odds of CMR-confirmed HCM (OR 102.4, 95% Confidence Interval, 57.4 - 182.6) in the held-out set. Class-discriminative patterns localized to the anterior and lateral leads (V4-V5). Conclusions: We developed and externally validated a deep learning model that identifies HCM from ECG images with excellent discrimination. This approach represents an automated, efficient, and accessible screening strategy for HCM.

National Trends in Racial and Ethnic Disparities in Use of Recommended Therapies in Adults with Atherosclerotic Cardiovascular Disease, 1999-2020.

Importance: Despite efforts to improve the quality of care for patients with atherosclerotic cardiovascular disease (ASCVD), it is unclear whether the US has made progress in reducing racial and ethnic differences in utilization of guideline-recommended therapies for secondary prevention. Objective: To evaluate 21-year trends in racial and ethnic differences in utilization of guideline-recommended pharmacological medications and lifestyle modifications among US adults with ASCVD. Design, Setting, and Participants: This cross-sectional study includes data from the National Health and Nutrition Examination Survey between 1999 and 2020. Eligible participants were adults aged 18 years or older with a history of ASCVD. Data were analyzed between March 2022 and May 2023. Exposure: Self-reported race and ethnicity. Main Outcome and Measures: Rates and racial and ethnic differences in the use of guideline-recommended pharmacological medications and lifestyle modifications. Results: The study included 5218 adults with a history of ASCVD (mean [SD] age, 65.5 [13.2] years, 2148 women [weighted average, 44.2%]), among whom 1170 (11.6%) were Black, 930 (7.7%) were Hispanic or Latino, and 3118 (80.7%) were White in the weighted sample. Between 1999 and 2020, there was a significant increase in total cholesterol control and statin use in all racial and ethnic subgroups, and in angiotensin-converting enzyme inhibitor (ACEI) and angiotensin receptor blocker (ARB) utilization in non-Hispanic White individuals and Hispanic and Latino individuals (Hispanic and Latino individuals: 17.12 percentage points; 95% CI, 0.37-37.88 percentage points; P = .046; non-Hispanic White individuals: 12.14 percentage points; 95% CI, 6.08-18.20 percentage points; P < .001), as well as smoking cessation within the Hispanic and Latino population (-27.13 percentage points; 95% CI, -43.14 to -11.12 percentage points; P = .002). During the same period, the difference in smoking cessation between Hispanic and Latino individuals and White individuals was reduced (-24.85 percentage points; 95% CI, -38.19 to -11.51 percentage points; P < .001), but racial and ethnic differences for other metrics did not change significantly. Notably, substantial gaps persisted between current care and optimal care throughout the 2 decades of data analyzed. In the period of 2017 to 2020, optimal regimens were observed in 47.4% (95% CI, 39.3%-55.4%), 48.7% (95% CI, 36.7%-60.6%), and 53.0% (95% CI, 45.6%-60.4%) of Black, Hispanic and Latino, and White individuals, respectively. Conclusions and Relevance: In this cross-sectional study of US adults with ASCVD, significant disparities persisted between current care and optimal care, surpassing any differences observed among demographic groups. These findings highlight the critical need for sustained efforts to bridge these gaps and achieve better outcomes for all patients, regardless of their racial and ethnic backgrounds.

Multinational patterns of second line antihyperglycaemic drug initiation across cardiovascular risk groups: federated pharmacoepidemiological evaluation in LEGEND-T2DM.

Objective: To assess the uptake of second line antihyperglycaemic drugs among patients with type 2 diabetes mellitus who are receiving metformin. Design: Federated pharmacoepidemiological evaluation in LEGEND-T2DM. Setting: 10 US and seven non-US electronic health record and administrative claims databases in the Observational Health Data Sciences and Informatics network in eight countries from 2011 to the end of 2021. Participants: 4.8 million patients (≥18 years) across US and non-US based databases with type 2 diabetes mellitus who had received metformin monotherapy and had initiated second line treatments. Exposure: The exposure used to evaluate each database was calendar year trends, with the years in the study that were specific to each cohort. Main outcomes measures: The outcome was the incidence of second line antihyperglycaemic drug use (ie, glucagon-like peptide-1 receptor agonists, sodium-glucose cotransporter-2 inhibitors, dipeptidyl peptidase-4 inhibitors, and sulfonylureas) among individuals who were already receiving treatment with metformin. The relative drug class level uptake across cardiovascular risk groups was also evaluated. Results: 4.6 million patients were identified in US databases, 61 382 from Spain, 32 442 from Germany, 25 173 from the UK, 13 270 from France, 5580 from Scotland, 4614 from Hong Kong, and 2322 from Australia. During 2011-21, the combined proportional initiation of the cardioprotective antihyperglycaemic drugs (glucagon-like peptide-1 receptor agonists and sodium-glucose cotransporter-2 inhibitors) increased across all data sources, with the combined initiation of these drugs as second line drugs in 2021 ranging from 35.2% to 68.2% in the US databases, 15.4% in France, 34.7% in Spain, 50.1% in Germany, and 54.8% in Scotland. From 2016 to 2021, in some US and non-US databases, uptake of glucagon-like peptide-1 receptor agonists and sodium-glucose cotransporter-2 inhibitors increased more significantly among populations with no cardiovascular disease compared with patients with established cardiovascular disease. No data source provided evidence of a greater increase in the uptake of these two drug classes in populations with cardiovascular disease compared with no cardiovascular disease. Conclusions: Despite the increase in overall uptake of cardioprotective antihyperglycaemic drugs as second line treatments for type 2 diabetes mellitus, their uptake was lower in patients with cardiovascular disease than in people with no cardiovascular disease over the past decade. A strategy is needed to ensure that medication use is concordant with guideline recommendations to improve outcomes of patients with type 2 diabetes mellitus.

Estimating the impact of health systems factors on antimicrobial resistance in priority pathogens.

OBJECTIVES: Antimicrobial resistance (AMR) is the next big pandemic that threatens humanity. The One Health approach to AMR requires quantification of interactions between health, demographic, socioeconomic, environmental, and geopolitical factors to design interventions. This study is focused on learning health system factors on global AMR. METHODS: This study analysed longitudinal data (2004-2017) of AMR having 6 33 820 isolates from 70 middle and high-income countries. We integrated AMR data with the Global Burden of Disease (GBD), Governance (WGI), and Finance data sets to find AMR's unbiased and actionable determinants. We chose a Bayesian decision network (BDN) approach within the causal modelling framework to quantify determinants of AMR. Further, we integrated Bayesian networks' global knowledge discovery approach with discriminative machine learning to predict individual-level antibiotic susceptibility in patients. RESULTS: From MAR (multiple antibiotic resistance) scores, we found a non-uniform spread pattern of AMR. Components-level analysis revealed that governance, finance, and disease burden variables strongly correlate with AMR. From the Bayesian network analysis, we found that access to immunization, obstetric care, and government effectiveness are strong, actionable factors in reducing AMR, confirmed by what-if analysis. Finally, our discriminative machine learning models achieved an individual-level AUROC (Area under receiver operating characteristic curve) of 0.94 (SE = 0.01) and 0.89 (SE = 0.002) to predict Staphylococcus aureus resistance to ceftaroline and oxacillin, respectively. CONCLUSION: Causal machine learning revealed that immunisation strategies and quality of governance are vital, actionable interventions to reduce AMR.

National Trends in Racial and Ethnic Disparities in Antihypertensive Medication Use and Blood Pressure Control Among Adults With Hypertension, 2011-2018.

Poor hypertension awareness and underuse of guideline-recommended medications are critical factors contributing to poor hypertension control. Using data from 8095 hypertensive people aged ≥18 years from the National Health and Nutrition Examination Survey (2011-2018), we examined recent trends in racial and ethnic differences in awareness and antihypertensive medication use, and their association with racial and ethnic differences in hypertension control. Between 2011 and 2018, age-adjusted hypertension awareness declined for Black, Hispanic, and White individuals, but the 3 outcomes increased or did not change for Asian individuals. Compared with White individuals, Black individuals had a similar awareness (odds ratio, 1.20 [0.96-1.45]) and overall treatment rates (1.04 [0.84-1.25]), and received more intensive antihypertensive medication if treated (1.41 [1.27-1.56]), but had a lower control rate (0.72 [0.61-0.83]). Asian and Hispanic individuals had significantly lower awareness rates (0.69 [0.52-0.85] and 0.74 [0.59-0.89]), overall treatment rates (0.72 [0.57-0.88] and 0.69 [0.55-0.82]), received less intensive medication if treated (0.60 [0.50-0.72] and 0.86 [0.75-0.96]), and had lower control rates (0.66 [0.54-0.79] and 0.69 [0.57-0.81]). The racial and ethnic differences in awareness, treatment, and control persisted over the study period and were consistent across age, sex, and income strata. Lower awareness and treatment were significantly associated with lower control in Asian and Hispanic individuals (P<0.01 for all) but not in Black individuals. These findings highlight the need for interventions to improve awareness and treatment among Asian and Hispanic individuals, and more investigation into the downstream factors that may contribute to the poor hypertension control among Black individuals.

A machine learning application for raising WASH awareness in the times of COVID-19 pandemic.

The COVID-19 pandemic has revealed the power of internet disinformation in influencing global health. The deluge of information travels faster than the epidemic itself and is a threat to the health of millions across the globe. Health apps need to leverage machine learning for delivering the right information while constantly learning misinformation trends and deliver these effectively in vernacular languages in order to combat the infodemic at the grassroot levels in the general public. Our application, WashKaro, is a multi-pronged intervention that uses conversational Artificial Intelligence (AI), machine translation, and natural language processing to combat misinformation (NLP). WashKaro uses AI to provide accurate information matched against WHO recommendations and delivered in an understandable format in local languages. The primary aim of this study was to assess the use of neural models for text summarization and machine learning for delivering WHO matched COVID-19 information to mitigate the misinfodemic. The secondary aim of this study was to develop a symptom assessment tool and segmentation insights for improving the delivery of information. A total of 5026 people downloaded the app during the study window; among those, 1545 were actively engaged users. Our study shows that 3.4 times more females engaged with the App in Hindi as compared to males, the relevance of AI-filtered news content doubled within 45 days of continuous machine learning, and the prudence of integrated AI chatbot "Satya" increased thus proving the usefulness of a mHealth platform to mitigate health misinformation. We conclude that a machine learning application delivering bite-sized vernacular audios and conversational AI is a practical approach to mitigate health misinformation.

Patient Experience of a Neurology Tele-Follow-Up Program Initiated During the Coronavirus Disease 2019 Pandemic: A Questionnaire-Based Study.

Background: Teleneurology consultations can be highly advantageous since neurological diseases and disabilities often limit patient's access to health care, particularly in a setting where they need to travel long distances for specialty consults. Patient satisfaction is an important outcome assessing success of a telemedicine program. Materials and Methods: A cross-sectional study was conducted to determine satisfaction and perception of patients toward an audio call based teleneurology follow-up initiated during the coronavirus disease 2019 pandemic. Primary outcomes were satisfaction to tele-consult, and proportion of patients preferring telemedicine for future follow-up. Results: A total of 261 patients who received tele-consult were enrolled. Satisfaction was highest for domain technological quality, followed by patient-physician dialogue (PPD) and least to quality of care (QoC). Median (interquartile range) patient satisfaction on a 5-point Likert scale was 4 (3-5). Eighty-five (32.6%; 95% confidence interval 26.9-38.6%) patients preferred telemedicine for future follow-up. Higher overall satisfaction was associated with health condition being stable/better, change in treatment advised on tele-consult, diagnosis not requiring follow-up examination, higher scores on domains QoC and PPD (p < 0.05). Future preference for telemedicine was associated with patient him-/herself consulting with doctor, less duration of follow-up, higher overall satisfaction, and higher scores on domain QoC (p < 0.05). On thematic analysis, telemedicine was found convenient, reduced expenditure, and had better physician attention; in-person visits were comprehensive, had better patient-physician relationship, and better communication. Discussion: Patient satisfaction was lower in our study than what has been observed earlier, which may be explained by the primitive nature of our platform. Several variables related to the patients' disease process have an effect on patient satisfaction. Conclusion: Development of robust, structured platforms is necessary to fully utilize the potential of telemedicine in developing countries.

Predicting Hemodynamic Shock from Thermal Images using Machine Learning.

Proactive detection of hemodynamic shock can prevent organ failure and save lives. Thermal imaging is a non-invasive, non-contact modality to capture body surface temperature with the potential to reveal underlying perfusion disturbance in shock. In this study, we automate early detection and prediction of shock using machine learning upon thermal images obtained in a pediatric intensive care unit of a tertiary care hospital. 539 images were recorded out of which 253 had concomitant measurement of continuous intra-arterial blood pressure, the gold standard for shock monitoring. Histogram of oriented gradient features were used for machine learning based region-of-interest segmentation that achieved 96% agreement with a human expert. The segmented center-to-periphery difference along with pulse rate was used in longitudinal prediction of shock at 0, 3, 6 and 12 hours using a generalized linear mixed-effects model. The model achieved a mean area under the receiver operating characteristic curve of 75% at 0 hours (classification), 77% at 3 hours (prediction) and 69% at 12 hours (prediction) respectively. Since hemodynamic shock associated with critical illness and infectious epidemics such as Dengue is often fatal, our model demonstrates an affordable, non-invasive, non-contact and tele-diagnostic decision support system for its reliable detection and prediction.