Search

Introduction: The Group Lifestyle Balance™ (GLB) program is an adaptation of the landmark Diabetes Prevention Program (DPP) group lifestyle intervention that is approved by the Centers for Disease Control and Prevention as a model curriculum for diabetes (T2D) prevention. While participation in the program has been associated with clinically significant weight loss and decreases in other risk factors for T2D and cardiovascular disease in community settings, participant retention and sustained engagement throughout the 12-month program have been major challenges. Little is known about participant preference for key customizable structural aspects of program delivery that are known to influence program acceptability. Hypothesis: We hypothesized that there are features of GLB that can be customized by the delivery system to enhance recruitment and retention. Methods: We conducted a discrete choice experiment at Sutter Health, a large integrated healthcare system in northern California. We invited 122,744 patients who met DPP eligibility criteria and had elevated BMI (>25), to complete an online survey. The questions were constructed to address four aspects of the structure of the program: delivery mode (in-person vs online); timing of sessions (day and time of day); facilitator (lifestyle coach vs. lifestyle coach with extra formal training); session format (group vs group plus 1:1). Three cohorts answered four different questions - each with 2 choices to determine optimal design of the program. We also asked participants to rate qualities of the facilitator and the group according to importance. Results: Surveys were completed by 6,923 (5.6%) of those invited. Two-thirds of respondents reported they would rather meet online with live video than in-person (64.2%, 1556 of 2425) and preferred the program be set in the health system (68.6%, 1664 of 2425). Most preferred the addition of private sessions (72.8%, 3273 of 4498), and a lifestyle coach with formal clinical training (80.9%, 1962 of 2425). A plurality of respondents rated facilitator personal experience with weight management as important/very important (45.2%, 3132 of 6923) and the majority also reported importance of teaching experience, and professional training (50.0%, 3456; 71.2%, 4932; both of 6923, respectively). One-quarter reported that it was important/very important for the other participants to be of similar age and sensitive to cultural differences (25.4%, 1759; 23.7%, 1639; both of 6923, respectively). Conclusions: This study identified patient preferences for several modifiable features of GLB (delivery mode, timing, session format) and several group factors. Understanding and optimizing these factors to meet the needs of participant subpopulations may be an important mechanism for improving intervention uptake and retention. Multivariable analysis is forthcoming to determine preferences for subgroups.

The novel coronavirus disease (COVID-19) pandemic is the gravest public-health crisis that the United States has seen in more than a century. Healthcare delivery systems are the focal point for interfacing with COVID-19; however, many were and remain unprepared for this or similar outbreaks. In this paper, we describe the Learning Health System (LHS) as an ideal organizing principle to inform an evidence-based response to public-health emergencies like COVID-19. We further describe barriers and challenges to the realization of the LHS and propose a call to action for a substantial investment in the LHS, with a focus on public health. Specifically, we advocate for a Learning Health Network that promotes collaboration between health systems, community-based organizations, and government agencies, especially during public health emergencies. We have approached this commentary through the unique lens of researchers embedded within a large, integrated healthcare delivery system, with direct experience working with clinical and operational units in response to the COVID-19 pandemic.

Even mild paravalvular leak (PVL) is associated with worse quality of life and increased mortality. The Ultra transcatheter heart valve (THV) is intentionally designed to reduce PVL. However, there...

Introduction The purpose of this study was to develop and validate a predictive model for the early identification of nonresponders to a 12-month lifestyle change program in clinical practice. Methods Investigators identified lifestyle change program participants in the electronic health records of a large healthcare delivery system between 2010 and 2017. Nonresponse was defined as weight gain or no weight loss at 12 months from the program initiation (baseline). Logistic regression with percentage weight change at 2–12 weeks from baseline was used as an independent predictor of nonresponse. Baseline demographics and clinical characteristics were also tested as potential predictors. The authors performed ten-fold cross-validation for model assessment and examined model performance with the area under the receiver operating characteristic curve, sensitivity, specificity, and positive and negative predictive values. The analyses were conducted in 2019. Results Among 947 program participants, 30% were classified as nonresponders at 12 months. The model with the best discrimination of responders from nonresponders included weight change at 12 weeks from baseline as the sole predictor (area under the receiver operating characteristic curve, 0.789). Sensitivity and positive predictive value were maximized at 0.56 (specificity and negative predictive value, 0.81 each). Conclusions In a cohort of lifestyle change program participants from clinical practice, percentage weight change at 12 weeks from baseline can serve as a single indicator of nonresponse at the completion of the 12-month program. Clinicians can easily apply this algorithm to identify and assess participants in potential need of adjunctive or alternative therapy to maximize treatment outcomes.

Introduction: Patients with left ventricular assist device (VAD) are typically treated with aspirin and warfarin. However, some patients are unable to tolerate full anticoagulation (AC). There is limited information available regarding intermediate-term outcomes in patients on reduced or no anticoagulation. Methods: Patients who underwent VAD implantation at California Pacific Medical Center from January 2015 to January 2020 were studied retrospectively. Patients received aspirin 81 mg daily and warfarin with a target INR of 2-3, and anticoagulation was gradually de-intensified or withdrawn in response to recurrent mucosal bleeding. Pre-implantation characteristics, thrombolytic events (hemolysis, pump thrombosis requiring exchange, TIA, or ischemic CVA), and survival post-implant were compared among patients treated with full AC vs. reduced or no AC. We performed nonparametric survival analysis to obtain Kaplan-Meier survival estimates as of 9/15/2020. Cox proportional hazards regression was used to adjust for confounders measured at baseline. Results: 91 patients underwent VAD implant (80 HeartMate 3 and 11 HeartMate II). The median age was 65, and the majority of patients (79%) were treated as destination therapy. Reduced AC was used in 43 patients (47%), including no anticoagulation (12 patients), aspirin monotherapy (2 patients), warfarin monotherapy (16), warfarin monotherapy with a reduced INR target (10), and aspirin plus warfarin with a reduced INR target (3). During a median follow-up of 22 months, 15 thrombotic events were observed (12 in the reduced AC group and 3 in the full AC group, P=0.19). Two patients underwent pump exchange. 67% of thrombotic events and both pump exchanges occurred in HMII recipients. Survival was similar in both groups (Figure). Conclusions: The use of a reduced or no anticoagulation strategy after VAD implant is not uncommon and is associated with acceptable outcomes, particularly among HeartMate 3 recipients.

Exposure to nitrogen dioxide (NO(2)), black carbon (BC), and ultrafine particles (UFP) during pregnancy may increase risk of preeclampsia, but previous studies have not assessed hyper-localized differences in pollutant levels which may cause exposure misclassification. We used data from Google Street View cars with mobile air monitors that repeatedly sampled NO(2), BC, and UFP every 30-meters in Downtown and West Oakland neighborhoods during 2015–2017. Data were linked to electronic health records of pregnant women in the 2014-2016 Sutter Health population who resided within 120-meters of monitoring data (N=1,095) to identify preeclampsia cases. We used G-computation with log-binomial regression to estimate risk differences (RD) associated with hypothetical interventions reducing pollutant levels to 25(th) percentiles observed in our sample on preeclampsia risk, overall and stratified by race/ethnicity. Prevalence of preeclampsia was 6.8%. Median (interquartile range) levels of NO(2), BC, and UFP were 10.8 ppb (9.0, 13.0), 0.34 μg/m(3) (0.27, 0.42), and 29.2 # × 10(3)/cm(3) (26.6, 32.6), respectively. Changes in the risk of preeclampsia achievable by limiting each pollutant to the 25(th) percentile was NO(2) RD =−1.5 per 100 women (95% confidence interval (CI): −2.5, −0.5); BC RD=−1.0 (95% CI: −2.2, 0.02); and UFP RD = −0.5 (95% CI: −1.8, 0.7). Estimated effects were largest for non-Latina Black mothers: NO(2) RD=−2.8 (95% CI: −5.2, −0.3) and BC RD=−3.0 (95% CI: −6.4, 0.4).

Introduction: The CDC established the National Diabetes Prevention Program (NDPP) initiative in 2010, leading to implementation of numerous group-based lifestyle interventions, such as the 12-month Group Lifestyle Balance (GLB) program, in community and clinical settings. Heterogeneity in weight outcomes is common. While evidence suggests that session attendance is associated with greater weight loss, some participants do not achieve weight loss even with high session attendance. Conversely, some may achieve clinically significant weight loss (≥5%) with lower attendance. In this study, we sought to identify and characterize such paradoxical interventional outcomes. (i.e., high session attendance and Hypothesis: No a priori hypotheses. Methods: We conducted a longitudinal descriptive analysis of overweight/obese GLB participants using electronic health record data from an integrated healthcare delivery system in Northern California (2010-2017). We focused on the 12-week intensive core phase of the curriculum because prior studies show that weight loss outcomes achieved during this period are highly correlated with long-term weight loss. We categorized patients into 4 mutually exclusive groups by session attendance ( Results: Among 1,818 evaluable participants, we identified 870 (47.9%) with paradoxical outcomes. Of these, 104 (12.0%) achieved ≥5% weight loss with Conclusions: Nearly half of all GLB participants in this integrated health system had paradoxical outcomes, with more than 40% classified as paradoxical non-responders. These results suggest that session attendance may not be as sensitive a predictor of weight outcomes as previously thought, and other approaches are needed to understand the complex factors influencing goal attainment in behavioral lifestyle programs.

Background Migraine is one of the most common neurological disorders in clinical practice and is a substantial cause of disability worldwide. Current approaches to therapy are primarily based on medication but are often limited by inadequate effectiveness and common side effects. Newer, more effective medications are expensive. Mindfulness-based stress reduction (MBSR), an 8-week classroom-based meditation intervention, is inexpensive, has no known side effects, and has demonstrated clinically meaningful effectiveness for several chronic-pain syndromes. In addition, MBSR has shown promising results for migraine therapy in a few small case studies and pilot studies. We present here the protocol for a two-arm randomized controlled pilot trial of MBSR for moderate-to-severe episodic migraine, which, if successful, will form the basis for a fully powered clinical trial. Methods/design This study, set in Northern California, is a two-arm parallel-comparison single-blinded randomized controlled pilot trial with the goal of recruiting approximately 60 participants with moderate-to-severe episodic migraine. The feasibility outcomes include ability and time required to recruit, adherence to the MBSR treatment, and ability to measure outcomes using 31-day headache diaries and patient-reported questionnaire data. The active treatment arm consists of an 8-week community-based MBSR class plus usual care, and the wait-list control group is usual care. Recruitment is underway and expected to be complete by the end of 2018. Discussion To our knowledge, this is the first pragmatic trial in the U.S. of MBSR for migraine using community-based classes, and if it proves viable, we plan to conduct a fully powered trial to determine the effectiveness of the intervention for reducing headache days for moderate-to-severe episodic migraineurs. Trial registration Clinicaltrials.gov, NCT02824250. Registered on 6 July 2016. Electronic supplementary material The online version of this article (10.1186/s13063-019-3355-y) contains supplementary material, which is available to authorized users.

Introduction: Several current guidelines assess sonographic features to guide management of thyroid nodules. The ACR uses an additive point system to assign the level of risk to various sonographic features, whereas the ATA groups sonographic features together to determine the level of risk. The purpose of this study is to compare the performance of the ATA guidelines and ACR TI-RADS at an urban endocrinology clinic in risk stratifying thyroid nodules by their specific sonographic features. Methods: This retrospective, chart-review study includes adult patients who met sonographic criteria for fine needle aspiration (FNA) biopsy based on ATA or ACR TI-RADS at an outpatient endocrinology practice in San Francisco, CA between December 2011 and August 2019. Patients with a prior history of thyroid malignancy (anaplastic and medullary thyroid carcinoma or thyroid lymphoma) were excluded. The reference standard for the diagnosis of malignancy was surgical pathology or FNA cytology Bethesda category V or VI when surgical pathology was unavailable. Analysis of guideline performances and specific sonographic features included: sensitivities (Sn), specificities (Sp), positive predictive values (PPV), negative predictive values (NPV), and area-under-the-curve (AUC) using Fisher’s exact test. Results: Two hundred seventy-five nodules among 195 adults (86.2% were women) were included in the analysis. Twelve nodules were malignant, with an associated malignancy rate of 4.4%. TI-RADS had higher accuracy based on AUC of 0.710 compared to 0.623 using ATA guidelines. TI-RADS also had a higher PPV of 21.4% among nodules with 9 points, versus 5.8% among nodules in the ATA “high suspicion” category. Ultrasound characteristics with the highest Sp, relative PPV and NPV were: microcalcifications (84.5%, 4.3%, 96.0%, respectively), taller-than-wide (81.7%, 7.1%, 96.7%), irregular margins (77.7%, 6.0%, 96.5%); the characteristic with the highest Sn was hypoechogenicity (83.3%), however this had relatively low Sp (25.4%) and PPV (4.5%). Conclusions: TI-RADS performed better with higher overall accuracy and PPV when applied to nodules classified as having the highest malignancy risk. Taller-than-wide shape, irregular margins, and microcalcifications were the characteristics most useful for malignancy risk stratification. Limitations of this study include: interobserver bias, small sample size, referred patient population (which may differ from other institutions), and inability in some cases to confirm malignant FNA cytology with surgical pathology.

Introduction Translational lifestyle change programs for community and clinical settings have been available for a decade, yet there are limited data on their comparative effectiveness. This study examines the effectiveness of a Centers for Disease Control and Prevention–aligned lifestyle change program relative to usual care in clinical practice. Methods This was an electronic health record–based retrospective cohort study conducted in a community-based healthcare system. Investigators identified adult program participants and usual-care patients in the electronic health record between 2010 and 2018 and defined their index date (baseline) as the first lifestyle change program encounter or a random encounter date, respectively. Participants were matched 1:2 to usual-care patients on baseline demographics and clinical characteristics using propensity-score methods. Changes in body weight and blood pressure were examined from baseline through 24 months. Results The authors identified 2,833 program participants and 438,432 usual-care patients meeting study eligibility criteria. A total of 2,833 program participants were matched to 4,776 usual-care patients; the average age was 54 years, and 80% of the participants were female. Program participation was associated with a 1.9- and 1.6-fold higher prevalence of clinically meaningful (≥5%) weight loss at 12- and 24-month follow-up than usual care and a higher prevalence of blood pressure control at 12 months but not at 24 months. Patients without type 2 diabetes at baseline had more pronounced outcomes than those with type 2 diabetes. Conclusions This study demonstrates the effectiveness of an evidence-based, Centers for Disease Control and Prevention–aligned lifestyle change program in reducing cardiometabolic risk factors compared with usual care in clinical practice, with long-term reductions in weight and transient reductions in blood pressure.

Purpose The purpose of this electronic health record (EHR)–based retrospective cohort study was to characterize a population of patients participating in a 12-month, lifestyle change program in a community-based health system and to examine longitudinal weight outcomes. Methods Program participants were identified in the EHRs of a health care delivery system across 18 sites between 2010 and 2017. Outcomes were mean weight change and proportion of patients with ≥5% weight loss through 24 months from program initiation. Results Among 4463 program participants, 3156 met study eligibility criteria, with a mean ± SD age of 53.5 ± 13.1 years; 77.7% were women. Mean baseline weight ± SD was 101.3 ± 23.8 kg. Three main cardiometabolic risk groups were identified: prediabetes/high risk for diabetes (47.3%), overweight/obese in the absence of elevated diabetes risk (27.2%), and existing diabetes (23.9%). Maximal mean weight loss was 3.9% at 6 months from baseline. At 12 and 24 months from baseline, mean weight loss was 3.2% and 2.3%, respectively, with 31% and 29% of participants attaining ≥5% weight loss. Long-term weight outcomes were similar across risk groups. Conclusions A lifestyle change program in a clinical practice setting is associated with modest weight loss, sustained through 24 months, among participants with a range of cardiometabolic risk factors. More than one-quarter of participants achieve ≥5% weight loss, regardless of cardiometabolic risk.

Background: Translational diabetes prevention lifestyle change programs can promote weight loss and reduce cardiometabolic risk factors in those at high risk for diabetes. Few studies have examined completion of such programs in the real world or the relationship between program completion and cardiometabolic outcomes. Methods: In this retrospective study, we identified program participants, ≥18 years of age, in the electronic health records (2010-2017) of a large, community-based healthcare system. We examined the number of classes completed during the 12-week intensive core phase of the program (12 sessions max) and the total number of sessions completed during the full 12-month curriculum (26 session max). We further examined the relationship between total session completion and changes in weight, systolic/diastolic blood pressure (SBP/DBP), and total cholesterol (TC) at 12 months (±3 months) follow-up, using linear regression with adjustment for baseline characteristics. Results: We identified 1,116 program participants meeting eligibility criteria. At baseline, mean weight = 99 kg, SBP/DBP = 126/76 mmHg, and TC = 192 mg/dL. Participants attended a mean of 9 of 12 sessions (median=11) during the intensive core phase, and 60% completed ≥10 sessions. Participants attended a mean of 14 sessions (median=15) over the full 12-month program. Each session completed was statistically significantly associated with, on average, a -0.39 kg change in weight (P Conclusion: In real-world clinical practice, lifestyle change program completion is suboptimal, yet evidence suggests that greater class attendance is associated with better outcomes. Strategies to promote program retention can have an important impact on cardiometabolic risk reduction. Disclosure H. Huang: None. K.M. Azar: None. S. Sudat: None. A. Pressman: None. R. Romanelli: None. Funding National Institute of Diabetes and Digestive and Kidney Diseases

Timely outreach to individuals in an advanced stage of illness offers opportunities to exercise decision control over health care. Predictive models built using Electronic health record (EHR) data are being explored as a way to anticipate such need with enough lead time for patient engagement. Prior studies have focused on hospitalized patients, who typically have more data available for predicting care needs. It is unclear if prediction driven outreach is feasible in the primary care setting. In this study, we apply predictive modeling to the primary care population of a large, regional health system and systematically examine the impact of technical choices, such as requiring a minimum number of health care encounters (data density requirements) and aggregating diagnosis codes using Clinical Classifications Software (CCS) groupings to reduce dimensionality, on model performance in terms of discrimination and positive predictive value. We assembled a cohort of 349,667 primary care patients between 65 and 90 years of age who sought care from Sutter Health between July 1, 2011 and June 30, 2014, of whom 2.1% died during the study period. EHR data comprising demographics, encounters, orders, and diagnoses for each patient from a 12 month observation window prior to the point when a prediction is made were extracted. L1 regularized logistic regression and gradient boosted tree models were fit to training data and tuned by cross validation. Model performance in predicting one year mortality was assessed using held-out test patients. Our experiments systematically varied three factors: model type, diagnosis coding, and data density requirements. We found substantial, consistent benefit from using gradient boosting vs logistic regression (mean AUROC over all other technical choices of 84.8% vs 80.7% respectively). There was no benefit from aggregation of ICD codes into CCS code groups (mean AUROC over all other technical choices of 82.9% vs 82.6% respectively). Likewise increasing data density requirements did not affect discrimination (mean AUROC over other technical choices ranged from 82.5% to 83%). We also examine model performance as a function of lead time, which is the interval between death and when a prediction was made. In subgroup analysis by lead time, mean AUROC over all other choices ranged from 87.9% for patients who died within 0 to 3 months to 83.6% for those who died 9 to 12 months after prediction time.

Graphical abstract, Data quality is essential to the success of the most simple and the most complex analysis. In the context of the COVID-19 pandemic, large-scale data sharing across the US and around the world has played an important role in public health responses to the pandemic and has been crucial to understanding and predicting its likely course. In California, hospitals have been required to report a large volume of daily data related to COVID-19. In order to meet this need, electronic health records (EHRs) have played an important role, but the challenges of reporting high-quality data in real-time from EHR data sources have not been explored. We describe some of the challenges of utilizing EHR data for this purpose from the perspective of a large, integrated, mixed-payer health system in northern California, US. We emphasize some of the inadequacies inherent to EHR data using several specific examples, and explore the clinical-analytic gap that forms the basis for some of these inadequacies. We highlight the need for data and analytics to be incorporated into the early stages of clinical crisis planning in order to utilize EHR data to full advantage. We further propose that lessons learned from the COVID-19 pandemic can result in the formation of collaborative teams joining clinical operations, informatics, data analytics, and research, ultimately resulting in improved data quality to support effective crisis response.

Objectives Increasing evidence demonstrates effectiveness of Mindfulness-Based Stress Reduction (MBSR) for pain-related and functional disorders. In order to conduct successful and efficient trials of MBSR, evidence regarding the relative performance of strategies to improve recruitment, retention, and adherence is required, but few studies have examined these issues specifically. Design In preparation for a fully powered trial, we conducted a 2-arm, parallel comparison randomized controlled feasibility trial of MBSR vs. usual-care for 60 patients with migraine headache. Setting Two large U.S. health systems in Northern California. Intervention MBSR is an 8-week classroom-based intervention that combines mindfulness meditation and yoga, with didactic presentations about stress psychology and group process/experiential education. Participants received the intervention at their choice of one of several existing, vetted community-based classes. Main outcome measures Successful recruitment was defined a priori as 18 participants within any 9-week period or 60 participants enrolled within a 36-week period. We considered participants adherent to the intervention if they attended at least 5 of the 8 weekly classes and the day-long retreat. Results We successfully enrolled 18 participants within a 7-week period, however, we did not attain our second goal of recruiting 60 participants within a 36-week period. Sixty-eight percent of our participants were adherent to the intervention. Conclusions We found that close monitoring of recruitment activities, flexibility in protocol modifications, and integration within the delivery system were crucial factors for successful participant recruitment, retention, and adherence in mindfulness research.

Avoidable hospital readmissions not only contribute to the high costs of healthcare in the US, but also have an impact on the quality of care for patients. Large scale adoption of Electronic Health Records (EHR) has created the opportunity to proactively identify patients with high risk of hospital readmission, and apply effective interventions to mitigate that risk. To that end, in the past, numerous machine-learning models have been employed to predict the risk of 30-day hospital readmission. However, the need for an accurate and real-time predictive model, suitable for hospital setting applications still exists. Here, using data from more than 300,000 hospital stays in California from Sutter Health's EHR system, we built and tested an artificial neural network (NN) model based on Google's TensorFlow library. Through comparison with other traditional and non-traditional models, we demonstrated that neural networks are great candidates to capture the complexity and interdependency of various data fields in EHRs. LACE, the current industry standard, showed a precision (PPV) of 0.20 in identifying high-risk patients in our database. In contrast, our NN model yielded a PPV of 0.24, which is a 20% improvement over LACE. Additionally, we discussed the predictive power of Social Determinants of Health (SDoH) data, and presented a simple cost analysis to assist hospitalists in implementing helpful and cost-effective post-discharge interventions.

Background: Home-based care coordination and support programs for people with advanced illness work alongside usual care to promote personal care goals, which usually include a preference for home-based end-of-life care. More research is needed to confirm the efficacy of these programs, especially when disseminated on a large scale. Advanced Illness Management is one such program, implemented within a large open health system in northern California, USA. Aim: To evaluate the impact of Advanced Illness Management on end-of-life resource utilization, cost of care, and care quality, as indicators of program success in supporting patient care goals. Design: A retrospective-matched observational study analyzing medical claims in the final 3 months of life. Setting/participants: Medicare fee-for-service 2010–2014 decedents in northern California, USA. Results: Final month total expenditures for Advanced Illness Management enrollees ( N = 1352) were reduced by US$4824 (US$3379, US$6268) and inpatient payments by US$6127 (US$4874, US$7682). Enrollees also experienced 150 fewer hospitalizations/1000 (101, 198) and 1361 fewer hospital days/1000 (998, 1725). The percentage of hospice enrollees increased by 17.9 percentage points (14.7, 21.0), hospital deaths decreased by 8.2 percentage points (5.5, 10.8), and intensive care unit deaths decreased by 7.1 percentage points (5.2, 8.9). End-of-life chemotherapy use and non-inpatient expenditures in months 2 and 3 prior to death did not differ significantly from the control group. Conclusion: Advanced Illness Management has a positive impact on inpatient utilization, cost of care, hospice enrollment, and site of death. This suggests that home-based support programs for people with advanced illness can be successful on a large scale in supporting personal end-of-life care choices.

Avoidable hospital readmissions not only contribute to the high costs of healthcare in the US, but also have an impact on the quality of care for patients. Large scale adoption of Electronic Health Records (EHR) has created the opportunity to proactively identify patients with high risk of hospital readmission, and apply effective interventions to mitigate that risk. To that end, in the past, numerous machine-learning models have been employed to predict the risk of 30-day hospital readmission. However, the need for an accurate and real-time predictive model, suitable for hospital setting applications still exists. Here, using data from more than 300,000 hospital stays in California from Sutter Health's EHR system, we built and tested an artificial neural network (NN) model based on Google's TensorFlow library. Through comparison with other traditional and non-traditional models, we demonstrated that neural networks are great candidates to capture the complexity and interdependency of various data fields in EHRs. LACE, the current industry standard, showed a precision (PPV) of 0.20 in identifying high-risk patients in our database. In contrast, our NN model yielded a PPV of 0.24, which is a 20% improvement over LACE. Additionally, we discussed the predictive power of Social Determinants of Health (SDoH) data, and presented a simple cost analysis to assist hospitalists in implementing helpful and cost-effective post-discharge interventions.