Mapping Systemic Inflammation and Antibody Responses in Multisystem Inflammatory Syndrome in Children (MIS-C).

Initially, children were thought to be spared from disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). However, a month into the epidemic, a novel multisystem inflammatory syndrome in children (MIS-C) emerged. Herein, we report on the immune profiles of nine MIS-C cases. All MIS-C patients had evidence of prior SARS-CoV-2 exposure, mounting an antibody response with intact neutralization capability. Cytokine profiling identified elevated signatures of inflammation (IL-18 and IL-6), lymphocytic and myeloid chemotaxis and activation (CCL3, CCL4, and CDCP1), and mucosal immune dysregulation (IL-17A, CCL20, and CCL28). Immunophenotyping of peripheral blood revealed reductions of non-classical monocytes, and subsets of NK and T lymphocytes, suggesting extravasation to affected tissues. Finally, profiling the autoantigen reactivity of MIS-C plasma revealed both known disease-associated autoantibodies (anti-La) and novel candidates that recognize endothelial, gastrointestinal, and immune-cell antigens. All patients were treated with anti-IL-6R antibody and/or IVIG, which led to rapid disease resolution.

Exome-wide association study to identify rare variants influencing COVID-19 outcomes: Results from the Host Genetics Initiative.

Host genetics is a key determinant of COVID-19 outcomes. Previously, the COVID-19 Host Genetics Initiative genome-wide association study used common variants to identify multiple loci associated with COVID-19 outcomes. However, variants with the largest impact on COVID-19 outcomes are expected to be rare in the population. Hence, studying rare variants may provide additional insights into disease susceptibility and pathogenesis, thereby informing therapeutics development. Here, we combined whole-exome and whole-genome sequencing from 21 cohorts across 12 countries and performed rare variant exome-wide burden analyses for COVID-19 outcomes. In an analysis of 5,085 severe disease cases and 571,737 controls, we observed that carrying a rare deleterious variant in the SARS-CoV-2 sensor toll-like receptor TLR7 (on chromosome X) was associated with a 5.3-fold increase in severe disease (95% CI: 2.75-10.05, p = 5.41x10-7). This association was consistent across sexes. These results further support TLR7 as a genetic determinant of severe disease and suggest that larger studies on rare variants influencing COVID-19 outcomes could provide additional insights.

Differentiation of Prior SARS-CoV-2 Infection and Postacute Sequelae by Standard Clinical Laboratory Measurements in the RECOVER Cohort.

BACKGROUND: There are currently no validated clinical biomarkers of postacute sequelae of SARS-CoV-2 infection (PASC). OBJECTIVE: To investigate clinical laboratory markers of SARS-CoV-2 and PASC. DESIGN: Propensity score-weighted linear regression models were fitted to evaluate differences in mean laboratory measures by prior infection and PASC index (≥12 vs. 0). (ClinicalTrials.gov: NCT05172024). SETTING: 83 enrolling sites. PARTICIPANTS: RECOVER-Adult cohort participants with or without SARS-CoV-2 infection with a study visit and laboratory measures 6 months after the index date (or at enrollment if >6 months after the index date). Participants were excluded if the 6-month visit occurred within 30 days of reinfection. MEASUREMENTS: Participants completed questionnaires and standard clinical laboratory tests. RESULTS: Among 10 094 participants, 8746 had prior SARS-CoV-2 infection, 1348 were uninfected, 1880 had a PASC index of 12 or higher, and 3351 had a PASC index of zero. After propensity score adjustment, participants with prior infection had a lower mean platelet count (265.9 × 109 cells/L [95% CI, 264.5 to 267.4 × 109 cells/L]) than participants without known prior infection (275.2 × 109 cells/L [CI, 268.5 to 282.0 × 109 cells/L]), as well as higher mean hemoglobin A1c (HbA1c) level (5.58% [CI, 5.56% to 5.60%] vs. 5.46% [CI, 5.40% to 5.51%]) and urinary albumin-creatinine ratio (81.9 mg/g [CI, 67.5 to 96.2 mg/g] vs. 43.0 mg/g [CI, 25.4 to 60.6 mg/g]), although differences were of modest clinical significance. The difference in HbA1c levels was attenuated after participants with preexisting diabetes were excluded. Among participants with prior infection, no meaningful differences in mean laboratory values were found between those with a PASC index of 12 or higher and those with a PASC index of zero. LIMITATION: Whether differences in laboratory markers represent consequences of or risk factors for SARS-CoV-2 infection could not be determined. CONCLUSION: Overall, no evidence was found that any of the 25 routine clinical laboratory values assessed in this study could serve as a clinically useful biomarker of PASC. PRIMARY FUNDING SOURCE: National Institutes of Health.

Implications of the Use of Artificial Intelligence Predictive Models in Health Care Settings : A Simulation Study.

BACKGROUND: Substantial effort has been directed toward demonstrating uses of predictive models in health care. However, implementation of these models into clinical practice may influence patient outcomes, which in turn are captured in electronic health record data. As a result, deployed models may affect the predictive ability of current and future models. OBJECTIVE: To estimate changes in predictive model performance with use through 3 common scenarios: model retraining, sequentially implementing 1 model after another, and intervening in response to a model when 2 are simultaneously implemented. DESIGN: Simulation of model implementation and use in critical care settings at various levels of intervention effectiveness and clinician adherence. Models were either trained or retrained after simulated implementation. SETTING: Admissions to the intensive care unit (ICU) at Mount Sinai Health System (New York, New York) and Beth Israel Deaconess Medical Center (Boston, Massachusetts). PATIENTS: 130 000 critical care admissions across both health systems. INTERVENTION: Across 3 scenarios, interventions were simulated at varying levels of clinician adherence and effectiveness. MEASUREMENTS: Statistical measures of performance, including threshold-independent (area under the curve) and threshold-dependent measures. RESULTS: At fixed 90% sensitivity, in scenario 1 a mortality prediction model lost 9% to 39% specificity after retraining once and in scenario 2 a mortality prediction model lost 8% to 15% specificity when created after the implementation of an acute kidney injury (AKI) prediction model; in scenario 3, models for AKI and mortality prediction implemented simultaneously, each led to reduced effective accuracy of the other by 1% to 28%. LIMITATIONS: In real-world practice, the effectiveness of and adherence to model-based recommendations are rarely known in advance. Only binary classifiers for tabular ICU admissions data were simulated. CONCLUSION: In simulated ICU settings, a universally effective model-updating approach for maintaining model performance does not seem to exist. Model use may have to be recorded to maintain viability of predictive modeling. PRIMARY FUNDING SOURCE: National Center for Advancing Translational Sciences.

Targeting the coronavirus nucleocapsid protein through GSK-3 inhibition.

The coronaviruses responsible for severe acute respiratory syndrome (SARS-CoV), COVID-19 (SARS-CoV-2), Middle East respiratory syndrome-CoV, and other coronavirus infections express a nucleocapsid protein (N) that is essential for viral replication, transcription, and virion assembly. Phosphorylation of N from SARS-CoV by glycogen synthase kinase 3 (GSK-3) is required for its function and inhibition of GSK-3 with lithium impairs N phosphorylation, viral transcription, and replication. Here we report that the SARS-CoV-2 N protein contains GSK-3 consensus sequences and that this motif is conserved in diverse coronaviruses, raising the possibility that SARS-CoV-2 may be sensitive to GSK-3 inhibitors, including lithium. We conducted a retrospective analysis of lithium use in patients from three major health systems who were PCR-tested for SARS-CoV-2. We found that patients taking lithium have a significantly reduced risk of COVID-19 (odds ratio = 0.51 [0.35-0.74], P = 0.005). We also show that the SARS-CoV-2 N protein is phosphorylated by GSK-3. Knockout of GSK3A and GSK3B demonstrates that GSK-3 is essential for N phosphorylation. Alternative GSK-3 inhibitors block N phosphorylation and impair replication in SARS-CoV-2 infected lung epithelial cells in a cell-type-dependent manner. Targeting GSK-3 may therefore provide an approach to treat COVID-19 and future coronavirus outbreaks.

The importance of social activity to risk of major depression in older adults.

BACKGROUND: Several social determinants of health (SDoH) have been associated with the onset of major depressive disorder (MDD). However, prior studies largely focused on individual SDoH and thus less is known about the relative importance (RI) of SDoH variables, especially in older adults. Given that risk factors for MDD may differ across the lifespan, we aimed to identify the SDoH that was most strongly related to newly diagnosed MDD in a cohort of older adults. METHODS: We used self-reported health-related survey data from 41 174 older adults (50-89 years, median age = 67 years) who participated in the Mayo Clinic Biobank, and linked ICD codes for MDD in the participants' electronic health records. Participants with a history of clinically documented or self-reported MDD prior to survey completion were excluded from analysis (N = 10 938, 27%). We used Cox proportional hazards models with a gradient boosting machine approach to quantify the RI of 30 pre-selected SDoH variables on the risk of future MDD diagnosis. RESULTS: Following biobank enrollment, 2073 older participants were diagnosed with MDD during the follow-up period (median duration = 6.7 years). The most influential SDoH was perceived level of social activity (RI = 0.17). Lower level of social activity was associated with a higher risk of MDD [hazard ratio = 2.27 (95% CI 2.00-2.50) for highest v. lowest level]. CONCLUSION: Across a range of SDoH variables, perceived level of social activity is most strongly related to MDD in older adults. Monitoring changes in the level of social activity may help identify older adults at an increased risk of MDD.

The genetic contribution to the comorbidity of depression and anxiety: a multi-site electronic health records study of almost 178 000 people.

BACKGROUND: Depression and anxiety are common and highly comorbid, and their comorbidity is associated with poorer outcomes posing clinical and public health concerns. We evaluated the polygenic contribution to comorbid depression and anxiety, and to each in isolation. METHODS: Diagnostic codes were extracted from electronic health records for four biobanks [N = 177 865 including 138 632 European (77.9%), 25 612 African (14.4%), and 13 621 Hispanic (7.7%) ancestry participants]. The outcome was a four-level variable representing the depression/anxiety diagnosis group: neither, depression-only, anxiety-only, and comorbid. Multinomial regression was used to test for association of depression and anxiety polygenic risk scores (PRSs) with the outcome while adjusting for principal components of ancestry. RESULTS: In total, 132 960 patients had neither diagnosis (74.8%), 16 092 depression-only (9.0%), 13 098 anxiety-only (7.4%), and 16 584 comorbid (9.3%). In the European meta-analysis across biobanks, both PRSs were higher in each diagnosis group compared to controls. Notably, depression-PRS (OR 1.20 per s.d. increase in PRS; 95% CI 1.18-1.23) and anxiety-PRS (OR 1.07; 95% CI 1.05-1.09) had the largest effect when the comorbid group was compared with controls. Furthermore, the depression-PRS was significantly higher in the comorbid group than the depression-only group (OR 1.09; 95% CI 1.06-1.12) and the anxiety-only group (OR 1.15; 95% CI 1.11-1.19) and was significantly higher in the depression-only group than the anxiety-only group (OR 1.06; 95% CI 1.02-1.09), showing a genetic risk gradient across the conditions and the comorbidity. CONCLUSIONS: This study suggests that depression and anxiety have partially independent genetic liabilities and the genetic vulnerabilities to depression and anxiety make distinct contributions to comorbid depression and anxiety.

Mapping anorexia nervosa genes to clinical phenotypes.

BACKGROUND: Anorexia nervosa (AN) is a psychiatric disorder with complex etiology, with a significant portion of disease risk imparted by genetics. Traditional genome-wide association studies (GWAS) produce principal evidence for the association of genetic variants with disease. Transcriptomic imputation (TI) allows for the translation of those variants into regulatory mechanisms, which can then be used to assess the functional outcome of genetically regulated gene expression (GReX) in a broader setting through the use of phenome-wide association studies (pheWASs) in large and diverse clinical biobank populations with electronic health record phenotypes. METHODS: Here, we applied TI using S-PrediXcan to translate the most recent PGC-ED AN GWAS findings into AN-GReX. For significant genes, we imputed AN-GReX in the Mount Sinai BioMe™ Biobank and performed pheWASs on over 2000 outcomes to test the clinical consequences of aberrant expression of these genes. We performed a secondary analysis to assess the impact of body mass index (BMI) and sex on AN-GReX clinical associations. RESULTS: Our S-PrediXcan analysis identified 53 genes associated with AN, including what is, to our knowledge, the first-genetic association of AN with the major histocompatibility complex. AN-GReX was associated with autoimmune, metabolic, and gastrointestinal diagnoses in our biobank cohort, as well as measures of cholesterol, medications, substance use, and pain. Additionally, our analyses showed moderation of AN-GReX associations with measures of cholesterol and substance use by BMI, and moderation of AN-GReX associations with celiac disease by sex. CONCLUSIONS: Our BMI-stratified results provide potential avenues of functional mechanism for AN-genes to investigate further.

Development of a Definition of Postacute Sequelae of SARS-CoV-2 Infection.

Importance: SARS-CoV-2 infection is associated with persistent, relapsing, or new symptoms or other health effects occurring after acute infection, termed postacute sequelae of SARS-CoV-2 infection (PASC), also known as long COVID. Characterizing PASC requires analysis of prospectively and uniformly collected data from diverse uninfected and infected individuals. Objective: To develop a definition of PASC using self-reported symptoms and describe PASC frequencies across cohorts, vaccination status, and number of infections. Design, Setting, and Participants: Prospective observational cohort study of adults with and without SARS-CoV-2 infection at 85 enrolling sites (hospitals, health centers, community organizations) located in 33 states plus Washington, DC, and Puerto Rico. Participants who were enrolled in the RECOVER adult cohort before April 10, 2023, completed a symptom survey 6 months or more after acute symptom onset or test date. Selection included population-based, volunteer, and convenience sampling. Exposure: SARS-CoV-2 infection. Main Outcomes and Measures: PASC and 44 participant-reported symptoms (with severity thresholds). Results: A total of 9764 participants (89% SARS-CoV-2 infected; 71% female; 16% Hispanic/Latino; 15% non-Hispanic Black; median age, 47 years [IQR, 35-60]) met selection criteria. Adjusted odds ratios were 1.5 or greater (infected vs uninfected participants) for 37 symptoms. Symptoms contributing to PASC score included postexertional malaise, fatigue, brain fog, dizziness, gastrointestinal symptoms, palpitations, changes in sexual desire or capacity, loss of or change in smell or taste, thirst, chronic cough, chest pain, and abnormal movements. Among 2231 participants first infected on or after December 1, 2021, and enrolled within 30 days of infection, 224 (10% [95% CI, 8.8%-11%]) were PASC positive at 6 months. Conclusions and Relevance: A definition of PASC was developed based on symptoms in a prospective cohort study. As a first step to providing a framework for other investigations, iterative refinement that further incorporates other clinical features is needed to support actionable definitions of PASC.

AKI in Hospitalized Patients with COVID-19.

BACKGROUND: Early reports indicate that AKI is common among patients with coronavirus disease 2019 (COVID-19) and associated with worse outcomes. However, AKI among hospitalized patients with COVID-19 in the United States is not well described. METHODS: This retrospective, observational study involved a review of data from electronic health records of patients aged ≥18 years with laboratory-confirmed COVID-19 admitted to the Mount Sinai Health System from February 27 to May 30, 2020. We describe the frequency of AKI and dialysis requirement, AKI recovery, and adjusted odds ratios (aORs) with mortality. RESULTS: Of 3993 hospitalized patients with COVID-19, AKI occurred in 1835 (46%) patients; 347 (19%) of the patients with AKI required dialysis. The proportions with stages 1, 2, or 3 AKI were 39%, 19%, and 42%, respectively. A total of 976 (24%) patients were admitted to intensive care, and 745 (76%) experienced AKI. Of the 435 patients with AKI and urine studies, 84% had proteinuria, 81% had hematuria, and 60% had leukocyturia. Independent predictors of severe AKI were CKD, men, and higher serum potassium at admission. In-hospital mortality was 50% among patients with AKI versus 8% among those without AKI (aOR, 9.2; 95% confidence interval, 7.5 to 11.3). Of survivors with AKI who were discharged, 35% had not recovered to baseline kidney function by the time of discharge. An additional 28 of 77 (36%) patients who had not recovered kidney function at discharge did so on posthospital follow-up. CONCLUSIONS: AKI is common among patients hospitalized with COVID-19 and is associated with high mortality. Of all patients with AKI, only 30% survived with recovery of kidney function by the time of discharge.

Characterization of Patients Who Return to Hospital Following Discharge from Hospitalization for COVID-19.

BACKGROUND: Data on patients with coronavirus disease 2019 (COVID-19) who return to hospital after discharge are scarce. Characterization of these patients may inform post-hospitalization care. OBJECTIVE: To describe clinical characteristics of patients with COVID-19 who returned to the emergency department (ED) or required readmission within 14 days of discharge. DESIGN: Retrospective cohort study of SARS-COV-2-positive patients with index hospitalization between February 27 and April 12, 2020, with ≥ 14-day follow-up. Significance was defined as P < 0.05 after multiplying P by 125 study-wide comparisons. PARTICIPANTS: Hospitalized patients with confirmed SARS-CoV-2 discharged alive from five New York City hospitals. MAIN MEASURES: Readmission or return to ED following discharge. RESULTS: Of 2864 discharged patients, 103 (3.6%) returned for emergency care after a median of 4.5 days, with 56 requiring inpatient readmission. The most common reason for return was respiratory distress (50%). Compared with patients who did not return, there were higher proportions of COPD (6.8% vs 2.9%) and hypertension (36% vs 22.1%) among those who returned. Patients who returned also had a shorter median length of stay (LOS) during index hospitalization (4.5 [2.9,9.1] vs 6.7 [3.5, 11.5] days; Padjusted = 0.006), and were less likely to have required intensive care on index hospitalization (5.8% vs 19%; Padjusted = 0.001). A trend towards association between absence of in-hospital treatment-dose anticoagulation on index admission and return to hospital was also observed (20.9% vs 30.9%, Padjusted = 0.06). On readmission, rates of intensive care and death were 5.8% and 3.6%, respectively. CONCLUSIONS: Return to hospital after admission for COVID-19 was infrequent within 14 days of discharge. The most common cause for return was respiratory distress. Patients who returned more likely had COPD and hypertension, shorter LOS on index-hospitalization, and lower rates of in-hospital treatment-dose anticoagulation. Future studies should focus on whether these comorbid conditions, longer LOS, and anticoagulation are associated with reduced readmissions.

Machine Learning to Predict Mortality and Critical Events in a Cohort of Patients With COVID-19 in New York City: Model Development and Validation.

BACKGROUND: COVID-19 has infected millions of people worldwide and is responsible for several hundred thousand fatalities. The COVID-19 pandemic has necessitated thoughtful resource allocation and early identification of high-risk patients. However, effective methods to meet these needs are lacking. OBJECTIVE: The aims of this study were to analyze the electronic health records (EHRs) of patients who tested positive for COVID-19 and were admitted to hospitals in the Mount Sinai Health System in New York City; to develop machine learning models for making predictions about the hospital course of the patients over clinically meaningful time horizons based on patient characteristics at admission; and to assess the performance of these models at multiple hospitals and time points. METHODS: We used Extreme Gradient Boosting (XGBoost) and baseline comparator models to predict in-hospital mortality and critical events at time windows of 3, 5, 7, and 10 days from admission. Our study population included harmonized EHR data from five hospitals in New York City for 4098 COVID-19-positive patients admitted from March 15 to May 22, 2020. The models were first trained on patients from a single hospital (n=1514) before or on May 1, externally validated on patients from four other hospitals (n=2201) before or on May 1, and prospectively validated on all patients after May 1 (n=383). Finally, we established model interpretability to identify and rank variables that drive model predictions. RESULTS: Upon cross-validation, the XGBoost classifier outperformed baseline models, with an area under the receiver operating characteristic curve (AUC-ROC) for mortality of 0.89 at 3 days, 0.85 at 5 and 7 days, and 0.84 at 10 days. XGBoost also performed well for critical event prediction, with an AUC-ROC of 0.80 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. In external validation, XGBoost achieved an AUC-ROC of 0.88 at 3 days, 0.86 at 5 days, 0.86 at 7 days, and 0.84 at 10 days for mortality prediction. Similarly, the unimputed XGBoost model achieved an AUC-ROC of 0.78 at 3 days, 0.79 at 5 days, 0.80 at 7 days, and 0.81 at 10 days. Trends in performance on prospective validation sets were similar. At 7 days, acute kidney injury on admission, elevated LDH, tachypnea, and hyperglycemia were the strongest drivers of critical event prediction, while higher age, anion gap, and C-reactive protein were the strongest drivers of mortality prediction. CONCLUSIONS: We externally and prospectively trained and validated machine learning models for mortality and critical events for patients with COVID-19 at different time horizons. These models identified at-risk patients and uncovered underlying relationships that predicted outcomes.

Genome-wide association study identifies SESTD1 as a novel risk gene for lithium-responsive bipolar disorder.

Lithium is the mainstay prophylactic treatment for bipolar disorder (BD), but treatment response varies considerably across individuals. Patients who respond well to lithium treatment might represent a relatively homogeneous subtype of this genetically and phenotypically diverse disorder. Here, we performed genome-wide association studies (GWAS) to identify (i) specific genetic variations influencing lithium response and (ii) genetic variants associated with risk for lithium-responsive BD. Patients with BD and controls were recruited from Sweden and the United Kingdom. GWAS were performed on 2698 patients with subjectively defined (self-reported) lithium response and 1176 patients with objectively defined (clinically documented) lithium response. We next conducted GWAS comparing lithium responders with healthy controls (1639 subjective responders and 8899 controls; 323 objective responders and 6684 controls). Meta-analyses of Swedish and UK results revealed no significant associations with lithium response within the bipolar subjects. However, when comparing lithium-responsive patients with controls, two imputed markers attained genome-wide significant associations, among which one was validated in confirmatory genotyping (rs116323614, P=2.74 × 10(-8)). It is an intronic single-nucleotide polymorphism (SNP) on chromosome 2q31.2 in the gene SEC14 and spectrin domains 1 (SESTD1), which encodes a protein involved in regulation of phospholipids. Phospholipids have been strongly implicated as lithium treatment targets. Furthermore, we estimated the proportion of variance for lithium-responsive BD explained by common variants ('SNP heritability') as 0.25 and 0.29 using two definitions of lithium response. Our results revealed a genetic variant in SESTD1 associated with risk for lithium-responsive BD, suggesting that the understanding of BD etiology could be furthered by focusing on this subtype of BD.

Applications of large language models in psychiatry: a systematic review.

Background: With their unmatched ability to interpret and engage with human language and context, large language models (LLMs) hint at the potential to bridge AI and human cognitive processes. This review explores the current application of LLMs, such as ChatGPT, in the field of psychiatry. Methods: We followed PRISMA guidelines and searched through PubMed, Embase, Web of Science, and Scopus, up until March 2024. Results: From 771 retrieved articles, we included 16 that directly examine LLMs' use in psychiatry. LLMs, particularly ChatGPT and GPT-4, showed diverse applications in clinical reasoning, social media, and education within psychiatry. They can assist in diagnosing mental health issues, managing depression, evaluating suicide risk, and supporting education in the field. However, our review also points out their limitations, such as difficulties with complex cases and potential underestimation of suicide risks. Conclusion: Early research in psychiatry reveals LLMs' versatile applications, from diagnostic support to educational roles. Given the rapid pace of advancement, future investigations are poised to explore the extent to which these models might redefine traditional roles in mental health care.

A novel method leveraging time series data to improve subphenotyping and application in critically ill patients with COVID-19.

Computational subphenotyping, a data-driven approach to understanding disease subtypes, is a prominent topic in medical research. Numerous ongoing studies are dedicated to developing advanced computational subphenotyping methods for cross-sectional data. However, the potential of time-series data has been underexplored until now. Here, we propose a Multivariate Levenshtein Distance (MLD) that can account for address correlation in multiple discrete features over time-series data. Our algorithm has two distinct components: it integrates an optimal threshold score to enhance the sensitivity in discriminating between pairs of instances, and the MLD itself. We have applied the proposed distance metrics on the k-means clustering algorithm to derive temporal subphenotypes from time-series data of biomarkers and treatment administrations from 1039 critically ill patients with COVID-19 and compare its effectiveness to standard methods. In conclusion, the Multivariate Levenshtein Distance metric is a novel method to quantify the distance from multiple discrete features over time-series data and demonstrates superior clustering performance among competing time-series distance metrics.

Assessing Retrieval-Augmented Large Language Model Performance in Emergency Department ICD-10-CM Coding Compared to Human Coders.

Background: Accurate medical coding is essential for clinical and administrative purposes but complicated, time-consuming, and biased. This study compares Retrieval-Augmented Generation (RAG)-enhanced LLMs to provider-assigned codes in producing ICD-10-CM codes from emergency department (ED) clinical records. Methods: Retrospective cohort study using 500 ED visits randomly selected from the Mount Sinai Health System between January and April 2024. The RAG system integrated past 1,038,066 ED visits data (2021-2023) into the LLMs' predictions to improve coding accuracy. Nine commercial and open-source LLMs were evaluated. The primary outcome was a head-to-head comparison of the ICD-10-CM codes generated by the RAG-enhanced LLMs and those assigned by the original providers. A panel of four physicians and two LLMs blindly reviewed the codes, comparing the RAG-enhanced LLM and provider-assigned codes on accuracy and specificity. Findings: RAG-enhanced LLMs demonstrated superior performance to provider coders in both the accuracy and specificity of code assignments. In a targeted evaluation of 200 cases where discrepancies existed between GPT-4 and provider-assigned codes, human reviewers favored GPT-4 for accuracy in 447 instances, compared to 277 instances where providers' codes were preferred (p<0.001). Similarly, GPT-4 was selected for its superior specificity in 509 cases, whereas human coders were preferred in only 181 cases (p<0.001). Smaller open-access models, such as Llama-3.1-70B, also demonstrated substantial scalability when enhanced with RAG, with 218 instances of accuracy preference compared to 90 for providers' codes. Furthermore, across all models, the exact match rate between LLM-generated and provider-assigned codes significantly improved following RAG integration, with Qwen-2-7B increasing from 0.8% to 17.6% and Gemma-2-9b-it improving from 7.2% to 26.4%. Interpretation: RAG-enhanced LLMs improve medical coding accuracy in EDs, suggesting clinical workflow applications. These findings show that generative AI can improve clinical outcomes and reduce administrative burdens. Funding: This work was supported in part through the computational and data resources and staff expertise provided by Scientific Computing and Data at the Icahn School of Medicine at Mount Sinai and supported by the Clinical and Translational Science Awards (CTSA) grant UL1TR004419 from the National Center for Advancing Translational Sciences. Research reported in this publication was also supported by the Office of Research Infrastructure of the National Institutes of Health under award number S10OD026880 and S10OD030463. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. The funders played no role in study design, data collection, analysis and interpretation of data, or the writing of this manuscript. Twitter Summary: A study showed AI models with retrieval-augmented generation outperformed human doctors in ED diagnostic coding accuracy and specificity. Even smaller AI models perform favorably when using RAG. This suggests potential for reducing administrative burden in healthcare, improving coding efficiency, and enhancing clinical documentation.

Quantitative Prediction of Right Ventricular Size and Function From the ECG.

BACKGROUND: Right ventricular ejection fraction (RVEF) and end-diastolic volume (RVEDV) are not readily assessed through traditional modalities. Deep learning-enabled ECG analysis for estimation of right ventricular (RV) size or function is unexplored. METHODS AND RESULTS: We trained a deep learning-ECG model to predict RV dilation (RVEDV >120 mL/m2), RV dysfunction (RVEF ≤40%), and numerical RVEDV and RVEF from a 12-lead ECG paired with reference-standard cardiac magnetic resonance imaging volumetric measurements in UK Biobank (UKBB; n=42 938). We fine-tuned in a multicenter health system (MSHoriginal [Mount Sinai Hospital]; n=3019) with prospective validation over 4 months (MSHvalidation; n=115). We evaluated performance with area under the receiver operating characteristic curve for categorical and mean absolute error for continuous measures overall and in key subgroups. We assessed the association of RVEF prediction with transplant-free survival with Cox proportional hazards models. The prevalence of RV dysfunction for UKBB/MSHoriginal/MSHvalidation cohorts was 1.0%/18.0%/15.7%, respectively. RV dysfunction model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.86/0.81/0.77, respectively. The prevalence of RV dilation for UKBB/MSHoriginal/MSHvalidation cohorts was 1.6%/10.6%/4.3%. RV dilation model area under the receiver operating characteristic curve for UKBB/MSHoriginal/MSHvalidation cohorts was 0.91/0.81/0.92, respectively. MSHoriginal mean absolute error was RVEF=7.8% and RVEDV=17.6 mL/m2. The performance of the RVEF model was similar in key subgroups including with and without left ventricular dysfunction. Over a median follow-up of 2.3 years, predicted RVEF was associated with adjusted transplant-free survival (hazard ratio, 1.40 for each 10% decrease; P=0.031). CONCLUSIONS: Deep learning-ECG analysis can identify significant cardiac magnetic resonance imaging RV dysfunction and dilation with good performance. Predicted RVEF is associated with clinical outcome.

Evaluating the accuracy of a state-of-the-art large language model for prediction of admissions from the emergency room.

BACKGROUND: Artificial intelligence (AI) and large language models (LLMs) can play a critical role in emergency room operations by augmenting decision-making about patient admission. However, there are no studies for LLMs using real-world data and scenarios, in comparison to and being informed by traditional supervised machine learning (ML) models. We evaluated the performance of GPT-4 for predicting patient admissions from emergency department (ED) visits. We compared performance to traditional ML models both naively and when informed by few-shot examples and/or numerical probabilities. METHODS: We conducted a retrospective study using electronic health records across 7 NYC hospitals. We trained Bio-Clinical-BERT and XGBoost (XGB) models on unstructured and structured data, respectively, and created an ensemble model reflecting ML performance. We then assessed GPT-4 capabilities in many scenarios: through Zero-shot, Few-shot with and without retrieval-augmented generation (RAG), and with and without ML numerical probabilities. RESULTS: The Ensemble ML model achieved an area under the receiver operating characteristic curve (AUC) of 0.88, an area under the precision-recall curve (AUPRC) of 0.72 and an accuracy of 82.9%. The naïve GPT-4's performance (0.79 AUC, 0.48 AUPRC, and 77.5% accuracy) showed substantial improvement when given limited, relevant data to learn from (ie, RAG) and underlying ML probabilities (0.87 AUC, 0.71 AUPRC, and 83.1% accuracy). Interestingly, RAG alone boosted performance to near peak levels (0.82 AUC, 0.56 AUPRC, and 81.3% accuracy). CONCLUSIONS: The naïve LLM had limited performance but showed significant improvement in predicting ED admissions when supplemented with real-world examples to learn from, particularly through RAG, and/or numerical probabilities from traditional ML models. Its peak performance, although slightly lower than the pure ML model, is noteworthy given its potential for providing reasoning behind predictions. Further refinement of LLMs with real-world data is necessary for successful integration as decision-support tools in care settings.

Derivation, External Validation and Clinical Implications of a deep learning approach for intracranial pressure estimation using non-cranial waveform measurements.

Importance: Increased intracranial pressure (ICP) is associated with adverse neurological outcomes, but needs invasive monitoring. Objective: Development and validation of an AI approach for detecting increased ICP (aICP) using only non-invasive extracranial physiological waveform data. Design: Retrospective diagnostic study of AI-assisted detection of increased ICP. We developed an AI model using exclusively extracranial waveforms, externally validated it and assessed associations with clinical outcomes. Setting: MIMIC-III Waveform Database (2000-2013), a database derived from patients admitted to an ICU in an academic Boston hospital, was used for development of the aICP model, and to report association with neurologic outcomes. Data from Mount Sinai Hospital (2020-2022) in New York City was used for external validation. Participants: Patients were included if they were older than 18 years, and were monitored with electrocardiograms, arterial blood pressure, respiratory impedance plethysmography and pulse oximetry. Patients who additionally had intracranial pressure monitoring were used for development (N=157) and external validation (N=56). Patients without intracranial monitors were used for association with outcomes (N=1694). Exposures: Extracranial waveforms including electrocardiogram, arterial blood pressure, plethysmography and SpO2. Main Outcomes and Measures: Intracranial pressure > 15 mmHg. Measures were Area under receiver operating characteristic curves (AUROCs), sensitivity, specificity, and accuracy at threshold of 0.5. We calculated odds ratios and p-values for phenotype association. Results: The AUROC was 0.91 (95% CI, 0.90-0.91) on testing and 0.80 (95% CI, 0.80-0.80) on external validation. aICP had accuracy, sensitivity, and specificity of 73.8% (95% CI, 72.0%-75.6%), 99.5% (95% CI 99.3%-99.6%), and 76.9% (95% CI, 74.0-79.8%) on external validation. A ten-percentile increment was associated with stroke (OR=2.12; 95% CI, 1.27-3.13), brain malignancy (OR=1.68; 95% CI, 1.09-2.60), subdural hemorrhage (OR=1.66; 95% CI, 1.07-2.57), intracerebral hemorrhage (OR=1.18; 95% CI, 1.07-1.32), and procedures like percutaneous brain biopsy (OR=1.58; 95% CI, 1.15-2.18) and craniotomy (OR = 1.43; 95% CI, 1.12-1.84; P < 0.05 for all). Conclusions and Relevance: aICP provides accurate, non-invasive estimation of increased ICP, and is associated with neurological outcomes and neurosurgical procedures in patients without intracranial monitoring.