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