Temporal and Geographic Patterns of Documentation of Sexual Orientation and Gender Identity Keywords in Clinical Notes.

OBJECTIVE: Disclosure of sexual orientation and gender identity correlates with better outcomes, yet data may not be available in structured fields in electronic health record data. To gain greater insight into the care of sexual and gender-diverse patients in the Veterans Health Administration (VHA), we examined the documentation patterns of sexual orientation and gender identity through extraction and analyses of data contained in unstructured electronic health record clinical notes. METHODS: Salient terms were identified through authoritative vocabularies, the research team's expertise, and frequencies, and the use of consistency in VHA clinical notes. Term frequencies were extracted from VHA clinical notes recorded from 2000 to 2018. Temporal analyses assessed usage changes in normalized frequencies as compared with nonclinical use, relative growth rates, and geographic variations. RESULTS: Over time most terms increased in use, similar to Google ngram data, especially after the repeal of the "Don't Ask Don't Tell" military policy in 2010. For most terms, the usage adoption consistency also increased by the study's end. Aggregated use of all terms increased throughout the United States. CONCLUSION: Term usage trends may provide a view of evolving care in a temporal continuum of changing policy. These findings may be useful for policies and interventions geared toward sexual and gender-diverse individuals. Despite the lack of structured data, the documentation of sexual orientation and gender identity terms is increasing in clinical notes.

Impact of the COVID-19 Pandemic on the Provision of Dialysis Service and Mortality in Veterans Receiving Maintenance Hemodialysis in the VA: An Interrupted Time-Series Analysis.

INTRODUCTION: According to the US Renal Data System (USRDS), patients with end-stage kidney disease (ESKD) on maintenance dialysis had higher mortality during early COVID-19 pandemic. Less is known about the effect of the pandemic on the delivery of outpatient maintenance hemodialysis and its impact on death. We examined the effect of pandemic-related disruption on the delivery of dialysis treatment and mortality in patients with ESKD receiving maintenance hemodialysis in the Veterans Health Administration (VHA) facilities, the largest integrated national healthcare system in the USA. METHODS: Using national VHA electronic health records data, we identified 7,302 Veterans with ESKD who received outpatient maintenance hemodialysis in VHA healthcare facilities during the COVID-19 pandemic (February 1, 2020, to December 31, 2021). We estimated the average change in the number of hemodialysis treatments received and deaths per 1,000 patients per month during the pandemic by conducting interrupted time-series analyses. We used seasonal autoregressive moving average (SARMA) models, in which February 2020 was used as the conditional intercept and months thereafter as conditional slope. The models were adjusted for seasonal variations and trends in rates during the pre-pandemic period (January 1, 2007, to January 31, 2020). RESULTS: The number (95% CI) of hemodialysis treatments received per 1,000 patients per month during the pre-pandemic and pandemic periods were 12,670 (12,525-12,796) and 12,865 (12,729-13,002), respectively. Respective all-cause mortality rates (95% CI) were 17.1 (16.7-17.5) and 19.6 (18.5-20.7) per 1,000 patients per month. Findings from SARMA models demonstrate that there was no reduction in the dialysis treatments delivered during the pandemic (rate ratio: 0.999; 95% CI: 0.998-1.001), but there was a 2.3% (95% CI: 1.5-3.1%) increase in mortality. During the pandemic, the non-COVID hospitalization rate was 146 (95% CI: 143-149) per 1,000 patients per month, which was lower than the pre-pandemic rate of 175 (95% CI: 173-176). In contrast, there was evidence of higher use of telephone encounters during the pandemic (3,023; 95% CI: 2,957-3,089), compared with the pre-pandemic rate (1,282; 95% CI: 1,241-1,324). CONCLUSIONS: We found no evidence that there was a disruption in the delivery of outpatient maintenance hemodialysis treatment in VHA facilities during the COVID-19 pandemic and that the modest rise in deaths during the pandemic is unlikely to be due to missed dialysis.

Cardiorespiratory fitness and risk of Alzheimer's disease and related dementias among American veterans.

INTRODUCTION: Cardiorespiratory fitness (CRF) is associated with improved health and survival. Less is known about its association with Alzheimer's disease and related dementias (ADRD). METHODS: We identified 649,605 US veterans 30 to 95 years of age and free of ADRD who completed a standardized exercise tolerance test between 2000 and 2017 with no evidence of ischemia. We examined the association between five age- and sex-specific CRF categories and ADRD incidence using multivariate Cox regression models. RESULTS: During up to 20 (median 8.3) years of follow-up, incident ADRD occurred in 44,105 (6.8%) participants, with an incidence rate of 7.7/1000 person-years. Compared to the least-fit, multivariable-adjusted hazard ratios (95% confidence intervals) for incident ADRD were: 0.87 (0.85-0.90), 0.80 (0.78-0.83), 0.74 (0.72-0.76), and 0.67 (0.65-0.70), for low-fit, moderate-fit, fit, and high-fit individuals, respectively. DISSCUSSION: These findings demonstrate an independent, inverse, and graded association between CRF and incident ADRD. Future studies may determine the amount and duration of physical activity needed to optimize ADRD risk reduction.

Severity Trajectories of Pediatric Inpatients Using the Criticality Index.

OBJECTIVES: To assess severity of illness trajectories described by the Criticality Index for survivors and deaths in five patient groups defined by the sequence of patient care in ICU and routine patient care locations. DESIGN: The Criticality Index developed using a calibrated, deep neural network, measures severity of illness using physiology, therapies, and therapeutic intensity. Criticality Index values in sequential 6-hour time periods described severity trajectories. SETTING: Hospitals with pediatric inpatient and ICU care. PATIENTS: Pediatric patients never cared for in an ICU (n = 20,091), patients only cared for in the ICU (n = 2,096) and patients cared for in both ICU and non-ICU care locations (n = 17,023) from 2009 to 2016 Health Facts database (Cerner Corporation, Kansas City, MO). INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Criticality Index values were consistent with clinical experience. The median (25-75th percentile) ICU Criticality Index values (0.878 [0.696-0.966]) were more than 80-fold higher than the non-ICU values (0.010 [0.002-0.099]). Non-ICU Criticality Index values for patients transferred to the ICU were 40-fold higher than those never transferred to the ICU (0.164 vs 0.004). The median for ICU deaths was higher than ICU survivors (0.983 vs 0.875) (p < 0.001). The severity trajectories for the five groups met expectations based on clinical experience. Survivors had increasing Criticality Index values in non-ICU locations prior to ICU admission, decreasing Criticality Index values in the ICU, and decreasing Criticality Index values until hospital discharge. Deaths had higher Criticality Index values than survivors, steeper increases prior to the ICU, and worsening values in the ICU. Deaths had a variable course, especially those who died in non-ICU care locations, consistent with deaths associated with both active therapies and withdrawals/limitations of care. CONCLUSIONS: Severity trajectories measured by the Criticality Index showed strong validity, reflecting the expected clinical course for five diverse patient groups.

Shedding Light on the Black Box: Explaining Deep Neural Network Prediction of Clinical Outcomes.

Deep neural network models are emerging as an important method in healthcare delivery, following the recent success in other domains such as image recognition. Due to the multiple non-linear inner transformations, deep neural networks are viewed by many as black boxes. For practical use, deep learning models require explanations that are intuitive to clinicians. In this study, we developed a deep neural network model to predict outcomes following major cardiovascular procedures, using temporal image representation of past medical history as input. We created a novel explanation for the prediction of the model by defining impact scores that associate clinical observations with the outcome. For comparison, a logistic regression model was fitted to the same dataset. We compared the impact scores and log odds ratios by calculating three types of correlations, which provided a partial validation of the impact scores. The deep neural network model achieved an area under the receiver operating characteristics curve (AUC) of 0.787, compared to 0.746 for the logistic regression model. Moderate correlations were found between the impact scores and the log odds ratios. Impact scores generated by the explanation algorithm has the potential to shed light on the "black box" deep neural network model and could facilitate its adoption by clinicians.

Sedation, Analgesia, and Neuromuscular Blockade: An Assessment of Practices From 2009 to 2016 in a National Sample of 66,443 Pediatric Patients Cared for in the ICU.

OBJECTIVES: To describe the pharmaceutical management of sedation, analgesia, and neuromuscular blockade medications administered to children in ICUs. DESIGN: A retrospective analysis using data extracted from the national database Health Facts. SETTING: One hundred sixty-one ICUs in the United States with pediatric admissions. PATIENTS: Children in ICUs receiving medications from 2009 to 2016. EXPOSURE/INTERVENTION: Frequency and duration of administration of sedation, analgesia, and neuromuscular blockade medications. MEASUREMENTS AND MAIN RESULTS: Of 66,443 patients with a median age of 1.3 years (interquartile range, 0-14.5), 63.3% (n = 42,070) received nonopioid analgesic, opioid analgesic, sedative, and/or neuromuscular blockade medications consisting of 83 different agents. Opioid and nonopioid analgesics were dispensed to 58.4% (n = 38,776), of which nonopioid analgesics were prescribed to 67.4% (n = 26,149). Median duration of opioid analgesic administration was 32 hours (interquartile range, 7-92). Sedatives were dispensed to 39.8% (n = 26,441) for a median duration of 23 hours (interquartile range, 3-84), of which benzodiazepines were most common (73.4%; n = 19,426). Neuromuscular-blocking agents were dispensed to 17.3% (n = 11,517) for a median duration of 2 hours (interquartile range, 1-15). Younger age was associated with longer durations in all medication classes. A greater proportion of operative patients received these medication classes for a longer duration than nonoperative patients. A greater proportion of patients with musculoskeletal and hematologic/oncologic diseases received these medication classes. CONCLUSIONS: Analgesic, sedative, and neuromuscular-blocking medications were prescribed to 63.3% of children in ICUs. The durations of opioid analgesic and sedative medication administration found in this study can be associated with known complications, including tolerance and withdrawal. Several medications dispensed to pediatric patients in this analysis are in conflict with Food and Drug Administration warnings, suggesting that there is potential risk in current sedation and analgesia practice that could be reduced with practice changes to improve efficacy and minimize risks.

Medications for Children Receiving Intensive Care: A National Sample.

OBJECTIVE: To examine medication administration records through electronic health record data to provide a broad description of the pharmaceutical exposure of critically ill children. DESIGN: Retrospective cohort study using the Cerner Health Facts database. SETTING: United States. PATIENTS: A total of 43,374 children 7 days old to less than 22 years old receiving intensive care with available pharmacy data. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: A total of 907,440 courses of 1,080 unique medications were prescribed with a median of nine medications (range, 1-99; 25-75th percentile, 5-16) per patient. The most common medications were acetaminophen, ondansetron, and morphine. Only 45 medications (4.2%) were prescribed to more than 5% of patients, and these accounted for 442,067 (48.7%) of the total courses of medications. Each additional medication was associated with increased univariate risk of mortality (odds ratio, 1.05; 95% CI, 1.05-1.06; p < 0.001). CONCLUSIONS: Children receiving intensive care receive a median of nine medications per patient and one quarter are prescribed at least than 16 medications. Only 45 medications were prescribed to more than 5% of patients, but these accounted for almost half of all medication courses.

Will Artificial Intelligence Translate Big Data Into Improved Medical Care or Be a Source of Confusing Intrusion? A Discussion Between a (Cautious) Physician Informatician and an (Optimistic) Medical Informatics Researcher.

Artificial intelligence (AI), the computerized capability of doing tasks, which until recently was thought to be the exclusive domain of human intelligence, has demonstrated great strides in the past decade. The abilities to play games, provide piloting for an automobile, and respond to spoken language are remarkable successes. How are the challenges and opportunities of medicine different from these challenges and how can we best apply these data-driven techniques to patient care and outcomes? A New England Journal of Medicine paper published in 1980 suggested that more well-defined "specialized" tasks of medical care were more amenable to computer assistance, while the breadth of approach required for defining a problem and narrowing down the problem space was less so, and perhaps, unachievable. On the other hand, one can argue that the modern version of AI, which uses data-driven approaches, will be the most useful in tackling tasks such as outcome prediction that are often difficult for clinicians and patients. The ability today to collect large volumes of data about a single individual (eg, through a wearable device) and the accumulation of large datasets about multiple persons receiving medical care has the potential to apply to the care of individuals. As these techniques of analysis, enumeration, aggregation, and presentation are brought to bear in medicine, the question arises as to their utility and applicability in that domain. Early efforts in decision support were found to be helpful; as the systems proliferated, later experiences have shown difficulties such as alert fatigue and physician burnout becoming more prevalent. Will something similar arise from data-driven predictions? Will empowering patients by equipping them with information gained from data analysis help? Patients, providers, technology, and policymakers each have a role to play in the development and utilization of AI in medicine. Some of the challenges, opportunities, and tradeoffs implicit here are presented as a dialog between a clinician (SJN) and an informatician (QZT).

Detecting Secular Trends in Clinical Treatment through Temporal Analysis.

Medical treatments change over time for multiple reasons, including introduction of new treatments, availability of new scientific evidence, change in institutional guidelines, and market efforts by pharmaceutical and medical device companies. Monitoring and analyzing these secular trends will also inform the evaluation of evidence based practice as well as outcome research. Using a large national clinical dataset from the United States Veterans Health Administration (VHA), we measured the change in prevalence of all diseases, medications, and procedures by year from 2001 to 2014. To assess statistical significance, we used a generalized linear model. Among the large number of changes that were observed, multiple significant changes were related to diabetes mellitus type II (DM2). Prevalence of DM2 in the VHA increased after 2001 but plateaued by 2008; blood sugar testing by glycosylated hemoglobin increased consistently while glucose testing decreased; and the trend of insulin and metformin use was consistent with the trend in DM2 prevalence, while glyburide and rosiglitazone use dropped sharply.

Patient needs and preferences for herb-drug-disease interaction alerts: a structured interview study.

BACKGROUND: While complementary and alternative medicine (CAM) is commonly used in the United States and elsewhere, and hazardous interactions with prescription drugs can occur, patients do not regularly communicate with physicians about their CAM use. The objective of this study was to discover patient information needs and preferences for herb-drug-disease interaction alerts. METHODS: We recruited 50 people from several locations within the University of Utah Hospital to participate in this structured interview study. They were asked to provide their preferences for the herb-drug-disease interaction alerts. Qualitative methods were used to reveal the themes that emerged from the interviews. RESULTS: Most participants reported they had previously used, or they were currently using, CAM therapies. The majority had made the effort to inform their healthcare provider(s) about their CAM usage, although some had not. We found that most respondents were interested in receiving alerts and information about potential interactions. Many preferred to receive the alerts in a variety of ways, both in person and electronically. CONCLUSIONS: In addition to conventional medicine, many patients regularly use complementary and alternative therapies. And yet, communication between patients and providers about CAM use is not consistent. There is a demand for interventions in health care that provide timely, integrative communication support. Delivering the herb-drug-disease alerts through multiple channels could help meet critical patient information needs.

Regular expression-based learning to extract bodyweight values from clinical notes.

BACKGROUND: Bodyweight related measures (weight, height, BMI, abdominal circumference) are extremely important for clinical care, research and quality improvement. These and other vitals signs data are frequently missing from structured tables of electronic health records. However they are often recorded as text within clinical notes. In this project we sought to develop and validate a learning algorithm that would extract bodyweight related measures from clinical notes in the Veterans Administration (VA) Electronic Health Record to complement the structured data used in clinical research. METHODS: We developed the Regular Expression Discovery Extractor (REDEx), a supervised learning algorithm that generates regular expressions from a training set. The regular expressions generated by REDEx were then used to extract the numerical values of interest. To train the algorithm we created a corpus of 268 outpatient primary care notes that were annotated by two annotators. This annotation served to develop the annotation process and identify terms associated with bodyweight related measures for training the supervised learning algorithm. Snippets from an additional 300 outpatient primary care notes were subsequently annotated independently by two reviewers to complete the training set. Inter-annotator agreement was calculated. REDEx was applied to a separate test set of 3561 notes to generate a dataset of weights extracted from text. We estimated the number of unique individuals who would otherwise not have bodyweight related measures recorded in the CDW and the number of additional bodyweight related measures that would be additionally captured. RESULTS: REDEx's performance was: accuracy=98.3%, precision=98.8%, recall=98.3%, F=98.5%. In the dataset of weights from 3561 notes, 7.7% of notes contained bodyweight related measures that were not available as structured data. In addition 2 additional bodyweight related measures were identified per individual per year. CONCLUSION: Bodyweight related measures are frequently stored as text in clinical notes. A supervised learning algorithm can be used to extract this data. Implications for clinical care, epidemiology, and quality improvement efforts are discussed.

Assessing Pictograph Recognition: A Comparison of Crowdsourcing and Traditional Survey Approaches.

BACKGROUND: Compared to traditional methods of participant recruitment, online crowdsourcing platforms provide a fast and low-cost alternative. Amazon Mechanical Turk (MTurk) is a large and well-known crowdsourcing service. It has developed into the leading platform for crowdsourcing recruitment. OBJECTIVE: To explore the application of online crowdsourcing for health informatics research, specifically the testing of medical pictographs. METHODS: A set of pictographs created for cardiovascular hospital discharge instructions was tested for recognition. This set of illustrations (n=486) was first tested through an in-person survey in a hospital setting (n=150) and then using online MTurk participants (n=150). We analyzed these survey results to determine their comparability. RESULTS: Both the demographics and the pictograph recognition rates of online participants were different from those of the in-person participants. In the multivariable linear regression model comparing the 2 groups, the MTurk group scored significantly higher than the hospital sample after adjusting for potential demographic characteristics (adjusted mean difference 0.18, 95% CI 0.08-0.28, P<.001). The adjusted mean ratings were 2.95 (95% CI 2.89-3.02) for the in-person hospital sample and 3.14 (95% CI 3.07-3.20) for the online MTurk sample on a 4-point Likert scale (1=totally incorrect, 4=totally correct). CONCLUSIONS: The findings suggest that crowdsourcing is a viable complement to traditional in-person surveys, but it cannot replace them.

A Novel Explainable AI Method to Assess Associations between Temporal Patterns in Patient Trajectories and Adverse Outcome Risks: Analyzing Fitness as a Risk Factor of ADRD.

We present a novel explainable artificial intelligence (XAI) method to assess the associations between the temporal patterns in the patient trajectories recorded in longitudinal clinical data and the adverse outcome risks, through explanations for a type of deep neural network model called Hybrid Value-Aware Transformer (HVAT) model. The HVAT models can learn jointly from longitudinal and non-longitudinal clinical data, and in particular can leverage the time-varying numerical values associated with the clinical codes or concepts within the longitudinal data for outcome prediction. The key component of the XAI method is the definitions of two derived variables, the temporal mean and the temporal slope, which are defined for the clinical concepts with associated time-varying numerical values. The two variables represent the overall level and the rate of change over time, respectively, in the trajectory formed by the values associated with the clinical concept. Two operations on the original values are designed for changing the values of the two derived variables separately. The effects of the two variables on the outcome risks learned by the HVAT model are calculated in terms of impact scores and impacts. Interpretations of the impact scores and impacts as being similar to those of odds ratios are also provided. We applied the XAI method to the study of cardiorespiratory fitness (CRF) as a risk factor of Alzheimer's disease and related dementias (ADRD). Using a retrospective case-control study design, we found that each one-unit increase in the overall CRF level is associated with a 5% reduction in ADRD risk, while each one-unit increase in the changing rate of CRF over time is associated with a 1% reduction. A closer investigation revealed that the association between the changing rate of CRF level and the ADRD risk is nonlinear, or more specifically, approximately piecewise linear along the axis of the changing rate on two pieces: the piece of negative changing rates and the piece of positive changing rates.

A Comparison of Veterans with Problematic Opioid Use Identified through Natural Language Processing of Clinical Notes versus Using Diagnostic Codes.

Opioid use disorder is known to be under-coded as a diagnosis, yet problematic opioid use can be documented in clinical notes, which are included in electronic health records. We sought to identify problematic opioid use from a full range of clinical notes and compare the demographic and clinical characteristics of patients identified as having problematic opioid use exclusively in clinical notes to patients documented through ICD opioid use disorder diagnostic codes. We developed and applied a natural language processing (NLP) tool that combines rule-based pattern analysis and a trained support vector machine to the clinical notes of a patient cohort (n = 222,371) from two Veteran Affairs service regions to identify patients with problematic opioid use. We also used a set of ICD diagnostic codes to identify patients with opioid use disorder from the same cohort. The NLP tool achieved 96.6% specificity, 90.4% precision/PPV, 88.4% sensitivity/recall, and 94.4% accuracy on unseen test data. NLP exclusively identified 57,331 patients; 6997 patients had positive ICD code identifications. Patients exclusively identified through NLP were more likely to be women. Those identified through ICD codes were more likely to be male, younger, have concurrent benzodiazepine prescriptions, more comorbidities, and more care encounters, and were less likely to be married. Patients in both these groups had substantially elevated comorbidity levels compared with patients not documented through either method as experiencing problematic opioid use. Clinicians may be reluctant to code for opioid use disorder. It is therefore incumbent on the healthcare team to search for documentation of opioid concerns within clinical notes.

Sexual and Gender Minority Status and Suicide Mortality: An Explainable Artificial Intelligence Analysis.

Objectives: Suicide risk is elevated in lesbian, gay, bisexual, and transgender (LGBT) individuals. Limited data on LGBT status in healthcare systems hinder our understanding of this risk. This study used natural language processing to extract LGBT status and a deep neural network (DNN) to examine suicidal death risk factors among US Veterans. Methods: Data on 8.8 million veterans with visits between 2010 and 2017 was used. A case-control study was performed, and suicide death risk was analyzed by a DNN. Feature impacts and interactions on the outcome were evaluated. Results: The crude suicide mortality rate was higher in LGBT patients. However, after adjusting for over 200 risk and protective factors, known LGBT status was associated with reduced risk compared to LGBT-Unknown status. Among LGBT patients, black, female, married, and older Veterans have a higher risk, while Veterans of various religions have a lower risk. Conclusion: Our results suggest that disclosed LGBT status is not directly associated with an increase suicide death risk, however, other factors (e.g., depression and anxiety caused by stigma) are associated with suicide death risks.

Artificial intelligence approaches for phenotyping heart failure in U.S. Veterans Health Administration electronic health record.

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 VA's 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.

Heart Failure Among Asian American Subpopulations.

Importance: Heart failure (HF) is a leading cause of death in the US. The current evidence on the burdens of HF in Asian American populations, especially Asian American subgroups, is limited and inconsistent. Objective: To assess and compare the incidence and prevalence of HF in Asian American subgroups. Design, Setting, and Participants: This retrospective cohort study used electronic health record data from patients 40 years or older with health care encounters from January 1, 2015, to December 31, 2019, recorded in the Oracle Electronic Health Record Real-World Data database, which has more than 100 health care systems across the US contributing to the database as of February 2024. For prevalence analysis, the study samples were those who had at least 1 encounter in the study calendar year. For incidence analysis, participants were additionally limited to those without HF before the study year who also had encounter(s) the year before the study year. Data analysis was performed from August 1, 2023, to July 31, 2024. Exposure: Race and ethnicity were determined using patient self-reported data, which were categorized as Black, East Asian, South Asian, Southeast Asian, other Asian (without specified ethnicity), and White. Main Outcomes and Measures: Outcomes were incidence and prevalence of HF, identified using recorded International Classification of Diseases, Ninth Revision, Clinical Modification and International Statistical Classification of Diseases, Tenth Revision, Clinical Modification codes. Age- and sex-standardized incidence and prevalence were used to calculate the risk ratio of each racial and ethnic group compared with White patients. Results: Incidence and prevalence analyses were performed for 6 845 791 patients (mean [SD] age, 62.1 [12.5] years; 59.9% female; 2.8% Asian, 6.7% Black, and 90.5% White) and for 13 440 234 patients (mean [SD] age, 61.7 [12.7] years; 57.0% female; 2.9% Asian, 7.1% Black, and 90.0% White), respectively. Using the 2015 population as the standard, age- and sex-standardized HF incidence was 2.26% (95% CI, 2.07%-2.45%) for Southeast Asian patients, 1.56% (95% CI, 1.31%-1.82%) for South Asian patients, and 1.22% (95% CI, 1.06%-1.38%) for East Asian patients compared with 1.58% (95% CI, 1.57%-1.59%) for White patients and 2.39% (95% CI, 2.36%-2.42%) for Black patients. Similarly, heterogeneous rates in Asian American subgroups were also observed in the prevalence analysis. Conclusions and Relevance: In this study of HF outcomes, the disparities between Southeast and East Asian patients were larger than those between Black and White patients, with the estimates in Southeast Asian patients being similar to those of Black patients. These findings reinforce that individual Asian ethnicities and cardiovascular risk factors should be considered in the assessment of HF risks.

Identification and outcomes of KDIGO-defined chronic kidney disease in 1.4 million U.S. Veterans with heart failure.

AIMS: According to the Kidney Disease: Improving Global Outcomes (KDIGO) guideline, the definition of chronic kidney disease (CKD) requires the presence of abnormal kidney structure or function for >3 months with implications for health. CKD in patients with heart failure (HF) has not been defined using this definition, and less is known about the true health implications of CKD in these patients. The objective of the current study was to identify patients with HF who met KDIGO criteria for CKD and examine their outcomes. METHODS AND RESULTS: Of the 1 419 729 Veterans with HF not receiving kidney replacement therapy, 828 744 had data on ≥2 ambulatory serum creatinine >90 days apart. CKD was defined as estimated glomerular filtration rate (eGFR) <60 ml/min/1.73 m2 (n = 185 821) or urinary albumin-to-creatinine ratio (uACR) >30 mg/g (n = 32 730) present twice >3 months apart. Normal kidney function (NKF) was defined as eGFR ≥60 ml/min/1.73 m2, present for >3 months, without any uACR >30 mg/g (n = 365 963). Patients with eGFR <60 ml/min/1.73 m2 were categorized into four stages: 45-59 (n = 72 606), 30-44 (n = 74 812), 15-29 (n = 32 077), and <15 (n = 6326) ml/min/1.73 m2. Five-year all-cause mortality occurred in 40.4%, 57.8%, 65.6%, 73.3%, 69.7%, and 47.5% of patients with NKF, four eGFR stages, and uACR >30mg/g (albuminuria), respectively. Compared with NKF, hazard ratios (HR) (95% confidence intervals [CI]) for all-cause mortality associated with the four eGFR stages and albuminuria were 1.63 (1.62-1.65), 2.00 (1.98-2.02), 2.49 (2.45-2.52), 2.28 (2.21-2.35), and 1.22 (1.20-1.24), respectively. Respective age-adjusted HRs (95% CIs) were 1.13 (1.12-1.14), 1.36 (1.34-1.37), 1.87 (1.84-1.89), 2.24 (2.18-2.31) and 1.19 (1.17-1.21), and multivariable-adjusted HRs (95% CIs) were 1.11 (1.10-1.12), 1.24 (1.22-1.25), 1.46 (1.43-1.48), 1.42 (1.38-1.47), and 1.13 (1.11-1.16). Similar patterns were observed for associations with hospitalizations. CONCLUSION: Data needed to define CKD using KDIGO criteria were available in six out of ten patients, and CKD could be defined in seven out of ten patients with data. HF patients with KDIGO-defined CKD had higher risks for poor outcomes, most of which was not explained by abnormal kidney structure or function. Future studies need to examine whether CKD defined using a single eGFR is characteristically and prognostically different from CKD defined using KDIGO criteria.

Phenotype fingerprinting of bipolar disorder prodrome.

BACKGROUND: Detecting prodromal symptoms of bipolar disorder (BD) has garnered significant attention in recent research, as early intervention could potentially improve therapeutic efficacy and improve patient outcomes. The heterogeneous nature of the prodromal phase in BD, however, poses considerable challenges for investigators. Our study aimed to identify distinct prodromal phenotypes or "fingerprints" in patients diagnosed with BD and subsequently examine correlations between these fingerprints and relevant clinical outcomes. METHODS: 20,000 veterans diagnosed with BD were randomly selected for this study. K-means clustering analysis was performed on temporal graphs of the clinical features of each patient. We applied what we call "temporal blurring" to each patient image in order to allow clustering to focus on the clinical features, and not cluster patients based upon their varying temporal patterns in diagnosis, which lead to the desired types of clusters. We evaluated several outcomes including mortality rate, hospitalization rate, mean number of hospitalizations, mean length of stay, and the occurrence of a psychosis diagnosis within one year following the initial BD diagnosis. To determine the statistical significance of the observed differences for each outcome, we conducted appropriate tests, such as ANOVA or Chi-square. RESULTS: Our analysis yielded 8 clusters which appear to represent distinct phenotypes with differing clinical attributes. Each of these clusters also has statistically significant differences across all outcomes (p < 0.0001). The clinical features in many of the clusters were consistent with findings in the literature concerning prodromal symptoms in patients with BD. One cluster, notably characterized by patients lacking discernible prodromal symptoms, exhibited the most favorable results across all measured outcomes. CONCLUSION: Our study successfully identified distinct prodromal phenotypes in patients diagnosed with BD. We also found that these distinct prodromal phenotypes are associated with different clinical outcomes.

Enhancing Clinical Data Analysis by Explaining Interaction Effects between Covariates in Deep Neural Network Models.

Deep neural network (DNN) is a powerful technology that is being utilized by a growing number and range of research projects, including disease risk prediction models. One of the key strengths of DNN is its ability to model non-linear relationships, which include covariate interactions. We developed a novel method called interaction scores for measuring the covariate interactions captured by DNN models. As the method is model-agnostic, it can also be applied to other types of machine learning models. It is designed to be a generalization of the coefficient of the interaction term in a logistic regression; hence, its values are easily interpretable. The interaction score can be calculated at both an individual level and population level. The individual-level score provides an individualized explanation for covariate interactions. We applied this method to two simulated datasets and a real-world clinical dataset on Alzheimer's disease and related dementia (ADRD). We also applied two existing interaction measurement methods to those datasets for comparison. The results on the simulated datasets showed that the interaction score method can explain the underlying interaction effects, there are strong correlations between the population-level interaction scores and the ground truth values, and the individual-level interaction scores vary when the interaction was designed to be non-uniform. Another validation of our new method is that the interactions discovered from the ADRD data included both known and novel relationships.