Accuracy of EHR data and diversity in patients' conditions and practice patterns are critical challenges in learning insightful practice-based clinical pathways. Learning and visualizing clinical pathways from actual practice data captured in the EHR may facilitate efficient practice review by healthcare providers and support patient engagement in shared decision making.

The post-acute sequelae of SARS-CoV-2 infection (PASC) refers to a broad spectrum of symptoms and signs that are persistent, exacerbated or newly incident in the period after acute SARS-CoV-2 infection. Most studies have examined these conditions individually without providing evidence on co-occurring conditions. In this study, we leveraged the electronic health record data of two large cohorts, INSIGHT and OneFlorida+, from the national Patient-Centered Clinical Research Network. We created a development cohort from INSIGHT and a validation cohort from OneFlorida+ including 20,881 and 13,724 patients, respectively, who were SARS-CoV-2 infected, and we investigated their newly incident diagnoses 30–180 days after a documented SARS-CoV-2 infection. Through machine learning analysis of over 137 symptoms and conditions, we identified four reproducible PASC subphenotypes, dominated by cardiac and renal (including 33.75% and 25.43% of the patients in the development and validation cohorts); respiratory, sleep and anxiety (32.75% and 38.48%); musculoskeletal and nervous system (23.37% and 23.35%); and digestive and respiratory system (10.14% and 12.74%) sequelae. These subphenotypes were associated with distinct patient demographics, underlying conditions before SARS-CoV-2 infection and acute infection phase severity. Our study provides insights into the heterogeneity of PASC and may inform stratified decision-making in the management of PASC conditions.

Background The ability to accurately predict the occurrence of in‐hospital death after percutaneous coronary intervention is important for clinical decision‐making. We sought to utilize the New York Percutaneous Coronary Intervention Reporting System in order to elucidate the determinants of in‐hospital mortality in patients undergoing percutaneous coronary intervention across New York State. Methods and Results We examined 479 804 patients undergoing percutaneous coronary intervention between 2004 and 2012, utilizing traditional and advanced machine learning algorithms to determine the most significant predictors of in‐hospital mortality. The entire data were randomly split into a training (80%) and a testing set (20%). Tuned hyperparameters were used to generate a trained model while the performance of the model was independently evaluated on the testing set after plotting a receiver‐operator characteristic curve and using the output measure of the area under the curve ( AUC ) and the associated 95% CIs. Mean age was 65.2±11.9 years and 68.5% were women. There were 2549 in‐hospital deaths within the patient population. A boosted ensemble algorithm (AdaBoost) had optimal discrimination with AUC of 0.927 (95% CI 0.923–0.929) compared with AUC of 0.913 for XGB oost (95% CI 0.906–0.919, P =0.02), AUC of 0.892 for Random Forest (95% CI 0.889–0.896, P <0.01), and AUC of 0.908 for logistic regression (95% CI 0.907–0.910, P <0.01). The 2 most significant predictors were age and ejection fraction. Conclusions A big data approach that utilizes advanced machine learning algorithms identifies new associations among risk factors and provides high accuracy for the prediction of in‐hospital mortality in patients undergoing percutaneous coronary intervention.

AKI is a recognized complication of coronavirus disease 2019 (COVID-19) (1). In this study, we characterized the AKI incidence and outcomes in patients with COVID-19 and AKI. We conducted a retrospective cohort study of 1002 patients admitted from March 1 to April 19, 2020 through the Emergency Department at NewYork-Presbyterian/ Weill Cornell Medical Center. Patient follow-up was until at least June 20, 2020, at which time 22 patients were still hospitalized and nine were transferred to another hospital facility. Baseline creatinine was defined as the closest creatinine prior to March 1, 2020 or, if none was available, the creatinine at time of hospital presentation. The Weill Cornell Institutional Review Board approved this study. AKI, defined by the Kidney Disease Improving Global Outcomes criteria (2), occurred in 294 (29%) of the 1002 patients: stage 1 AKI (n5182, 18%); stage 2 AKI (n529, 3%); and stage 3 AKI (n583, 8%). KRT was performed in 59 patients (6%); 53 received hemodialysis and/or continuous venovenous hemodialysis, five received a combination of acute peritoneal dialysis and hemodialysis/continuous venovenous hemodialysis, and one received acute peritoneal dialysis. The time from hospitalization to AKI was a median of 2.2 days in stage 1 AKI, 2.4 days in stage 2 AKI, and 1.6 days in stage 3 AKI. We evaluated the urine electrolytes and microscopy associated with the AKI event within 3 days. Among those available, the fractional excretion of sodium (FENa) was ,1% in 76%, and urine microscopy had granular casts in 21%. The presumed etiology of stage 3 AKI on the basis of manual chart review was acute tubular necrosis (ATN) in 28%, prerenal in 13%, prerenal/ATN in 11%, other causes in 4%, and unknown in 45% of patients. Granular casts were observed more frequently in stage 3 AKI than stage 1 AKI and stage 2 AKI (33% versus 16%, P50.006). We compared clinical characteristics of the patients with AKI with those without AKI (Table 1). Patients who developed AKI were older and more frequently had a history of hypertension, diabetes mellitus, congestive heart failure, CKD, and kidney transplantation than patients without AKI (P,0.001). Proteinuria and hematuria were

We demonstrate that data-driven methods offer a promising approach for designing order sets that are generalizable, data-driven, condition-based, and up to date with current best practices.

In order to protect cultivated land and balance farmers’ needs and shortage of land, the Chinese government introduced policies to rearrange land use in rural areas. However, many problems, such as unused rural construction land and illegally occupied land, have occurred through implementing land use policies. Rural construction land transformation has been promoted to solve these problems. This transformation was designed to let farmers voluntarily transforming their idle rural construction land. Then, local government could rearrange village layout for developing cultivation, industry and green space. Therefore, in order to analyze the factors that influenced farmers’ decision-making behavior in rural construction land transformation, household surveys were conducted in four typical villages in Jizhou District. After using the Probit model to analyze the data, the results indicated that the willingness to settle in the city, the mode of housing resettlement, the mode of compensation, the rationality of the measurement standards, and the annual total household income positively affected the willingness of farmers to transform their rural construction land. The strong willingness to settle in the city dominated the other factors. Moreover, the age and amount of construction land, the method of construction land acquisition, and the amount of cultivated land negatively affected the decision-making behavior during the transformation of rural construction land. Based on the influencing factors, policy suggestions are proposed from the perspectives of establishing an orderly transformation mechanism, implementing priority transformation, and providing compensation for transforming rural construction land.

Introduction: We sought to assess longitudinal electronic health records (EHRs) using machine learning (ML) methods to computationally derive probable Alzheimer's Disease (AD) and related dementia subphenotypes. Methods: A retrospective analysis of EHR data from a cohort of 7587 patients seen at a large, multi-specialty urban academic medical center in New York was conducted. Subphenotypes were derived using hierarchical clustering from 792 probable AD patients (cases) who had received at least one diagnosis of AD using their clinical data. The other 6795 patients, labeled as controls, were matched on age and gender with the cases and randomly selected in the ratio of 9:1. Prediction models with multiple ML algorithms were trained on this cohort using 5-fold cross-validation. XGBoost was used to rank the variable importance. Results: Four subphenotypes were computationally derived. Subphenotype A (n = 273; 28.2%) had more patients with cardiovascular diseases; subphenotype B (n = 221; 27.9%) had more patients with mental health illnesses, such as depression and anxiety; patients in subphenotype C (n = 183; 23.1%) were overall older (mean (SD) age, 79.5 (5.4) years) and had the most comorbidities including diabetes, cardiovascular diseases, and mental health disorders; and subphenotype D (n = 115; 14.5%) included patients who took antidementia drugs and had sensory problems, such as deafness and hearing impairment. The 0-year prediction model for AD risk achieved an area under the receiver operating curve (AUC) of 0.764

Objectives Early hospital readmissions or deaths are key healthcare quality measures in pay-for-performance programs. Predictive models could identify patients at higher risk of readmission or death and target interventions. However, existing models usually do not incorporate social determinants of health (SDH) information, although this information is of great importance to address health disparities related to social risk factors. The objective of this study is to examine the impact of social determinants of health on predictive models for potentially avoidable 30-day readmission. Methods We extracted electronic health record data for 19,941 hospital admissions between January 2015 and November 2017 at an academic medical center in New York City. We applied the Simplified HOSPITAL score model to predict potentially avoidable 30-day readmission or death and examined if incorporating individual-and community-level SDH could improve the prediction using cross-validation. We calculated the C-statistic for discrimination, Brier score for accuracy, and Hosmer-Lemeshow test for calibration for each model using logistic regression. Analysis was conducted for all patients and three subgroups that may be disproportionately affected by social risk factors, namely Medicaid patients, patients who are 65 or older, and obese patients. Results The Simplified HOSPITAL score model achieved similar performance in our sample compared to previous studies. Adding SDH did not improve the prediction among all patients. However, adding individual-and community-level SDH at the US census tract level significantly improved the prediction for all three subgroups. Specifically, C-statistics improved from 0.70 to 0.73 for Medicaid patients, from 0.66 to 0.68 for patients 65 or older, and from 0.70 to 0.73 for obese patients.