Ying Yin

Objective: Alzheimer’s disease (AD) is a leading cause of death and disability, and treatment options for Alzheimer’s disease and related dementias (ADRD) remain limited. We applied a data-driven, mechanism-agnostic Medication-Wide Association Study Plus (MWAS+) framework to identify candidate medications associated with ADRD using longitudinal electronic health record data and explainable artificial intelligence (AI). Methods: We used Veterans Health Administration electronic health record data from January 1999 to May 2022. The initial study population comprised 8,424,715 Veterans aged 65 years or older. Cases were defined by ADRD-related diagnosis codes or ADRD-related medication prescriptions, and controls were free of ADRD diagnosis and ADRD-related medication use. After exclusions and matching on sex, race, age at first encounter, and duration of follow-up, the primary analytic cohort included 505,817 matched case-control pairs (1:1; 1,011,634 Veterans). Longitudinal features were extracted from historical data up to 1 year before the index date and aggregated into 1-year intervals. We developed an upgraded Hybrid Value-Aware Transformer (HVAT 2.0) to jointly learn from longitudinal and nonlongitudinal clinical data while incorporating numerical values associated with clinical concepts, including cumulative medication dose. To enhance interpretability, we applied a medication-specific impact score method to estimate model-derived associations between medication exposure and ADRD risk. Findings: The model demonstrated stable performance across data partitions, with area under the receiver operating characteristic curve values of 0.791 in the training set, 0.772 in the validation set, and 0.775 in the testing set. Metolazone and varenicline were identified as the top 2 candidate medications with negative impact scores, suggesting potentially protective associations with new-onset ADRD. The impact score was -0.196 per unit of cumulative dose for metolazone (1800 mg) and -0.134 per unit for varenicline (280 mg). Although individual-level impact scores varied, most exposed patients had negative scores, including 12,020 of 12,480 metolazone users (96%) and 8,341 of 8,786 varenicline users (95%). Implications: This study demonstrates the feasibility of combining a medication-wide association framework, longitudinal dose-aware modeling, and explainable AI to identify candidate medications for ADRD from real-world electronic health record data. The findings should be interpreted as signals for hypothesis generation rather than evidence of causality. This framework may support prioritization of repurposing candidates for expert review, follow-up cohort validation, and future clinical investigation.

Importance: Missed outpatient appointments, including no-shows and cancellations, may disrupt continuity of care and be associated with worse outcomes, but long-term system-wide patterns and clinical implications are not well characterized. Objective: To characterize variation in missed appointment rates in the Veterans Health Administration (VHA) over time and by geographic location, visit modality, and preexisting conditions, and to evaluate associations between missed appointment rates and adverse outcomes among veterans with posttraumatic stress disorder (PTSD) or traumatic brain injury (TBI). Design: Cohort study using VHA Corporate Data Warehouse outpatient appointment data from January 1, 2000, through December 31, 2024. Setting: National integrated health care system of the VHA. Participants: System analysis includes all scheduled outpatient appointments with a valid status, and outcome analysis includes veterans with PTSD (n = 1 429 890) or TBI (n = 554 553), diagnosed before 2023. Exposures: For system -level analyses, missed appointment rates were calculated. In outcome analyses, 2023 missed appointment rates were categorized into tertiles within the cohort and appointment type. Main Outcomes and Measures: One year risks of all-cause hospitalization, all-cause mortality, and hospitalization or death beginning January 1, 2024. Results: Among 2,162,520,880 outpatient appointments from 2000 to 2024, 6.5% were no-shows and 25.4% were canceled. Across facilities, no-show rates ranged from 3.5% to 14.1%, patient-initiated cancellation rates from 9.7% to 26.0%, and clinic-initiated cancellation rates from 8.5% to 17.9%. In 2023, veterans with amputation, Parkinson disease, PTSD, or TBI had higher missed appointment rates than veterans without these conditions. Among veterans with PTSD, the highest no-show tertile, compared with none, was associated with higher mortality (HR, 1.91; 95% CI, 1.84-1.98) and hospitalization or death (HR, 1.07; 95% CI, 1.05-1.08). Among veterans with TBI, the highest no-show tertile was associated with hospitalization or death (HR, 1.65; 95% CI, 1.61-1.69). Conclusions and Relevance: Missed outpatient appointments were common in the VHA and varied substantially across facilities and over time. Among veterans with PTSD or TBI, higher missed appointment rates, particularly no-shows, were associated with increased risks of hospitalization and mortality, suggesting that these patterns may help identify high-risk veterans for targeted outreach. Key Points: Question: What patterns and sources of variation in missed outpatient appointments were observed in the Veterans Health Administration, and were higher missed appointment rates associated with one year hospitalization and mortality among veterans with PTSD or TBI? Findings: In this cohort study of 2,162,520,880 outpatient appointments from 2000 to 2024, no-shows accounted for 6.5% and cancellations for 25.4%, with substantial temporal and geographic variation. Higher no-show rates were associated with increased hospitalization and mortality among veterans with PTSD or TBI. Meaning: Higher missed appointment rates, particularly no-shows, may signal disengagement from care and elevated clinical risk, supporting targeted outreach for high-risk veterans.

Background: Individuals with heart failure (HF) are at increased risk of magnesium deficiency. Magnesium supplements are widely available and being used without clear evidence of efficacy in HF. Methods: We emulated a target trial to assess the association between magnesium supplements and adverse outcomes in U.S. veterans with newly diagnosed HF. Eligible patients were outpatients who received ambulatory care in the Veterans Health Administration between 1 January 2000 and 31 December 2020. Veterans with a hospitalization within 30 days prior to the eligible date, previous magnesium supplement or replacement use, or end-stage renal disease were ineligible for the trial. Initial self-reported magnesium supplement use (measured at eligible date) was identified in medical records using natural language processing and then checked repeatedly to confirm continuous use. The outcome was all-cause hospitalization or death. Patients were followed for up to five years from the eligible date and were censored if they changed from the assigned treatment strategy or initiated prescribed magnesium replacement. We applied inverse probability treatment weighting and Cox’s regression to estimate hazard ratios (HRs), with sensitivity analyses in patients surviving ≥ 6 months and those with continuous documentation of magnesium supplement use. Results: We enrolled 9900 magnesium supplement users and 9900 matched non-users. In the weighted cohort (mean age 72.6 years; 12.6% African American; 3.4% women; median follow-up 0.7 years), users had significantly better survival in both primary and sensitivity analyses (HR in primary analysis: 0.81 [0.77–0.86], p < 0.0001; HRs in sensitivity analyses: 0.91 [0.85–0.97], p = 0.0025 and 0.77 [0.72–0.82], p < 0.0001, respectively). Conclusions: magnesium supplement use was associated with a reduced risk of all-cause mortality or hospitalization among veterans with HF.

Objectives: To investigate the relationship between serum magnesium levels, prescribed oral magnesium replacement, and major adverse cardiovascular events (MACE) in type-2 diabetes mellitus (T2D). Research design and methods: This nationwide retrospective study analyzed 1,284,940 US Veterans (≥18 years) with T2D who had outpatient serum magnesium testing between 1999–2021 in the Veterans Health Administration. The relationship between serum magnesium levels and MACE (hospitalizations for acute myocardial infarction, heart failure, ischemic stroke, or all-cause mortality) was determined using multivariable-adjusted Cox-regression models. Using a new-user-design and propensity-score-matching approach, we further related the use of prescribed oral magnesium and MACE among patients with hypomagnesemia (serum magnesium 2.3 mg/dL). Compared to patients with normomagnesemia (serum magnesium 1.8–2.3 mg/dL), those with either hypomagnesemia or hypermagnesemia had elevated hazards for MACE. The risk increased with the severity of serum magnesium abnormalities in both directions—low (hazard ratios [HRs] 1.11–1.20) and high (HRs 1.04–1.39)—in a parabolic pattern. Oral magnesium was prescribed to 9.7% and 0.7% of patients with hypomagnesemia and normomagnesemia, respectively. After propensity-score-matching balanced across 64 baseline characteristics, oral magnesium was associated with a lower MACE risk in 40,766 matched patients with hypomagnesemia (HR 0.89; 95% confidence interval [CI], 0.84–0.93), especially those on proton-pump-inhibitors or thiazides. Oral magnesium was not related to MACE in 11,838 matched patients with normomagnesemia (HR 1.07; 95% CI, 0.97–1.17). Conclusions: In patients with T2D, both hypomagnesemia and hypermagnesemia were associated with higher one-year MACE risks compared to normomagnesemia. Prescribed oral magnesium was associated with a reduced MACE risk in hypomagnesemia but not in normomagnesemia.

We used machine learning (ML) to characterize 894,154 medical records of outpatient visits from the Veterans Administration Central Data Warehouse (VA CDW) by the likelihood of assignment of 200 International Classification of Diseases (ICD) code blocks. Using four different predictive models, we found the ML-derived predictions for the code blocks were consistently more effective in predicting death or 90-day rehospitalization than the assigned code block in the record. We reviewed records of ICD chapter assignments. The review revealed that the ML-predicted chapter assignments were consistently better than those humanly assigned. Impact factor analysis, a method of explanation of AI findings that was developed in our group, demonstrated little effect on any one assigned ICD code block but a marked impact on the ML-derived code blocks of kidney disease as well as several other morbidities. In this study, machine learning was much better than human code assignment at predicting the relatively rare outcomes of death or rehospitalization. Future work will address generalizability using other datasets, as well as addressing coding that is more nuanced than that of the categorization provided by code blocks.

Individuals with a history of incarceration face many barriers to accessing resources to meet their basic needs when returning to community settings. Digital health tools have potential to reduce health inequities by facilitating connections to health and social services, and peer support. This study aimed to employ a user-centered design approach to create a digital Personal Health Library (PerHL) for previously incarcerated individuals. The design process included in-depth interviews followed by rapid analysis, interpretation sessions, and user experience/user interface (UX/UI) design of a highfidelity prototype. Semi-structured interviews were conducted with individuals with a history of incarceration (n=20) to understand their experience rejoining their communities. Findings highlight the need for an app that allows users to easily access resources for employment, housing, healthcare and medical needs, formal and informal support, and legal counsel.

Objective: International Classification of Diseases (ICD) codes recorded in electronic health records (EHRs) are frequently used to create patient cohorts or define phenotypes. Inconsistent assignment of codes may reduce the utility of such cohorts. We assessed the reliability across time and location of the assignment of ICD codes in a US health system at the time of the transition from ICD-9-CM (ICD, 9th Revision, Clinical Modification) to ICD-10-CM (ICD, 10th Revision, Clinical Modification). Materials and methods: Using clusters of equivalent codes derived from the US Centers for Disease Control and Prevention General Equivalence Mapping (GEM) tables, ICD assignments occurring during the ICD-9-CM to ICD-10-CM transition were investigated in EHR data from the US Veterans Administration Central Data Warehouse using deep learning and statistical models. These models were then used to detect abrupt changes across the transition; additionally, changes at each VA station were examined. Results: Many of the 687 most-used code clusters had ICD-10-CM assignments differing greatly from that predicted from the codes used in ICD-9-CM. Manual reviews of a random sample found that 66% of the clusters showed problematic changes, with 37% having no apparent explanations. Notably, the observed pattern of changes varied widely across care locations. Discussion and conclusion: The observed coding variability across time and across location suggests that ICD codes in EHRs are insufficient to establish a semantically reliable cohort or phenotype. While some variations might be expected with a changing in coding structure, the inconsistency across locations suggests other difficulties. Researchers should consider carefully how cohorts and phenotypes of interest are selected and defined.

Objective: To analyze the mental health and erectile function status of men using sperm donor during pregnancy after ICSI failure in severe oligoasthenospermia and to provide reference for clinical implementation of more targeted psychological intervention and nursing for this group. Methods: A total of 410 sterile men who received assisted pregnancy treatment in our hospital from December 2020 to December 2022 and met the inclusion and exclusion criteria were collected as the study subjects. Among them, 68 patients with severe oligoasthenospermia who used donor assisted pregnancy after ICSI failure were used as the study group. Sixty-eight patients with severe oligoasthenospermia who continued to receive ICSI assisted pregnancy were matched by propensity score 1:1 as control group. General data questionnaire, self-rating Anxiety Scale (SAS), self-rating Depression Scale (SDS), Chinese version of perceived Stress Scale (CPSS) and International Erectile Function Index Rating Scale (IIEF-5) were used to conduct a cross-sectional investigation to compare the mental health and erectile function status of the two groups. Results: There were statistical differences in age and occupational status between the two groups before PSM (P < 0.05), but there was no statistical significance in social demographic data between the two groups after matching (P > 0.05). The incidence of anxiety, depression, stress and erectile dysfunction (ED) in the study group was higher than that in the control group, and there were statistical differences between the two groups (P < 0.05). Conclusion: The use of donor sperm to assist pregnancy has a great impact on the mental health and erectile function of infertile men. Medical personnel should pay attention to the mental health and erectile function of these men, and formulate targeted measures to help these patients actively cope with infertility, so as to improve the life and marriage quality of this group and improve their mental health status.

Background: Individuals released from carceral facilities have high rates of hospitalization and death, especially in the weeks immediately after their return to community settings. During this transitional process, individuals leaving incarceration are expected to engage with multiple providers working in separate, complex systems, including health care clinics, social service agencies, community-based organizations, and probation and parole services. This navigation is often complicated by individuals’ physical and mental health, literacy and fluency, and socioeconomic status. Personal health information technology, which can help people access and organize their health information, could improve the transition from carceral systems to the community and mitigate health risks upon release. Yet, personal health information technologies have not been designed to meet the needs and preferences of this population nor tested for acceptability or use. Objective: The objective of our study is to develop a mobile app to create personal health libraries for individuals returning from incarceration to help bridge the transition from carceral settings to community living. Methods: Participants were recruited through Transitions Clinic Network clinic encounters and professional networking with justice-involved organizations. We used qualitative research methods to assess the facilitators and barriers to developing and using personal health information technology for individuals returning from incarceration. We conducted individual interviews with people just released from carceral facilities (n=~20) and providers (n=~10) from the local community and carceral facilities involved with the transition for returning community members. We used rigorous rapid qualitative analysis to generate thematic output characterizing the unique circumstances impacting the development and use of personal health information technology for individuals returning from incarceration and to identify content and features for the mobile app based on the preferences and needs of our participants. Results: As of February 2023, we have completed 27 qualitative interviews with individuals recently released from carceral systems (n=20) and stakeholders (n=7) who support justice-involved individuals from various organizations in the community. Conclusions: We anticipate that the study will characterize the experiences of people transitioning from prison and jails to community settings; describe the information, technology resources, and needs upon reentry to the community; and create potential pathways for fostering engagement with personal health information technology. International Registered Report Identifier (IRRID): DERR1-10.2196/44748

BACKGROUND Individuals released from carceral facilities have high rates of hospitalization and death, especially in the weeks immediately after their return to community settings. During this transitional process, individuals leaving incarceration are expected to engage with multiple providers working in separate, complex systems, including health care clinics, social service agencies, community-based organizations, and probation and parole services. This navigation is often complicated by individuals’ physical and mental health, literacy and fluency, and socioeconomic status. Personal health information technology, which can help people access and organize their health information, could improve the transition from carceral systems to the community and mitigate health risks upon release. Yet, personal health information technologies have not been designed to meet the needs and preferences of this population nor tested for acceptability or use. OBJECTIVE The objective of our study is to develop a mobile app to create personal health libraries for individuals returning from incarceration to help bridge the transition from carceral settings to community living. METHODS Participants were recruited through Transitions Clinic Network clinic encounters and professional networking with justice-involved organizations. We used qualitative research methods to assess the facilitators and barriers to developing and using personal health information technology for individuals returning from incarceration. We conducted individual interviews with people just released from carceral facilities (n=~20) and providers (n=~10) from the local community and carceral facilities involved with the transition for returning community members. We used rigorous rapid qualitative analysis to generate thematic output characterizing the unique circumstances impacting the development and use of personal health information technology for individuals returning from incarceration and to identify content and features for the mobile app based on the preferences and needs of our participants. RESULTS As of February 2023, we have completed 27 qualitative interviews with individuals recently released from carceral systems (n=20) and stakeholders (n=7) who support justice-involved individuals from various organizations in the community. CONCLUSIONS We anticipate that the study will characterize the experiences of people transitioning from prison and jails to community settings; describe the information, technology resources, and needs upon reentry to the community; and create potential pathways for fostering engagement with personal health information technology. INTERNATIONAL REGISTERED REPORT DERR1-10.2196/44748