Machine learning and LACE index for predicting 30-day readmissions after heart failure hospitalization in elderly patients.

Machine learning (ML) techniques may improve readmission prediction performance in heart failure (HF) patients. This study aimed to assess the ability of ML algorithms to predict unplanned all-cause 30-day readmissions in HF elderly patients, and to compare them with conventional LACE (Length of hospitalization, Acuity, Comorbidities, Emergency department visits) index. All patients aged ≥ 65 years discharged alive between 2010 and 2019 after a hospitalization for acute HF were included in this retrospective cohort study. We applied MICE (Multivariate Imputation via Chained Equations) method to obtain a balanced, fully valued dataset and LASSO (Least Absolute Shrinkage and Selection Operator) algorithm to get the most significant features. Training (80% of records) and test (20%) cohorts were randomly selected. Study population: 3079 patients, 394 (12.8%) presented at least one readmission within 30 days, and 2685 (87.2%) did not. In the test cohort AUCs (IC95%) of XGBoost, Ada Boost Classifier, Random forest, and Gradient Boosting, and LACE Index were: 0.803 (0.734-0.872), 0.782 (0.711-0.854), 0.776 (0.703-0.848), 0.786 (0.715-0.857), and 0.504 (0.414-0.594), respectively, for predicting readmissions. A SHAP analysis was performed to offer a breakdown of the ML variables associated with readmission. Positive and negative predicting values estimates of the different ML models and LACE index were also provided, for several values of readmission rate prevalence. Among elderly patients, the rate of all-cause unplanned 30-day readmissions after hospitalization due to an acute HF was high. ML models performed better than the conventional LACE index for predicting readmissions. ML models can be proposed as promising tools for the identification of subjects at high risk of hospitalization in this clinical setting, enabling care teams to target interventions for improving overall clinical outcomes.

Supervised machine learning for the assessment of Chronic Kidney Disease advancement.

BACKGROUND AND OBJECTIVE: Chronic Kidney Disease (CKD) is a condition characterized by a progressive loss of kidney function over time caused by many diseases. The most effective weapons against CKD are early diagnosis and treatment, which in most of the cases can only postpone the onset of complete kidney failure. The CKD grading system is classified based on the estimated Glomerular Filtration Rate (eGFR), and it helps to stratify patients for risk, follow up and management planning. This study aims to effectively predict how soon a CKD patient will need to be dialyzed, thus allowing personalized care and strategic planning of treatment. METHODS: To accurately predict the time frame within which a CKD patient will necessarily have to be dialyzed, a computational model based on a supervised machine learning approach is developed. Many techniques, regarding both information extraction and model training phases, are compared in order to understand which approaches are most effective. The different models compared are trained on the data extracted from the Electronic Medical Records of the Vimercate Hospital. RESULTS: As final model, we propose a set of Extremely Randomized Trees classifiers considering 27 features, including creatinine level, urea, red blood cells count, eGFR trend (which is not even the most important), age and associated comorbidities. In predicting the occurrence of complete renal failure within the next year rather than later, it obtains a test accuracy of 94%, specificity of 91% and sensitivity of 96%. More and shorter time-frame intervals, up to 6 months of granularity, can be specified without relevantly worsening the model performance. CONCLUSIONS: The developed computational model provides nephrologists with a great support in predicting the patient's clinical pathway. The model promising results, coupled with the knowledge and experience of the clinicians, can effectively lead to better personalized care and strategic planning of both patient's needs and hospital resources.

Effectiveness of a Hospital-Based Computerized Decision Support System on Clinician Recommendations and Patient Outcomes: A Randomized Clinical Trial.

Importance: Sophisticated evidence-based information resources can filter medical evidence from the literature, integrate it into electronic health records, and generate recommendations tailored to individual patients. Objective: To assess the effectiveness of a computerized clinical decision support system (CDSS) that preappraises evidence and provides health professionals with actionable, patient-specific recommendations at the point of care. Design, Setting, and Participants: Open-label, parallel-group, randomized clinical trial among internal medicine wards of a large Italian general hospital. All analyses in this randomized clinical trial followed the intent-to-treat principle. Between November 1, 2015, and December 31, 2016, patients were randomly assigned to the intervention group, in which CDSS-generated reminders were displayed to physicians, or to the control group, in which reminders were generated but not shown. Data were analyzed between February 1 and July 31, 2018. Interventions: Evidence-Based Medicine Electronic Decision Support (EBMEDS), a commercial CDSS covering a wide array of health conditions across specialties, was integrated into the hospital electronic health records to generate patient-specific recommendations. Main Outcomes and Measures: The primary outcome was the resolution rate, the rate at which medical problems identified and alerted by the CDSS were addressed by a change in practice. Secondary outcomes included the length of hospital stay and in-hospital all-cause mortality. Results: In this randomized clinical trial, 20 563 patients were admitted to the hospital. Of these, 6480 (31.5%) were admitted to the internal medicine wards (study population) and randomized (3242 to CDSS and 3238 to control). The mean (SD) age of patients was 70.5 (17.3) years, and 54.5% were men. In total, 28 394 reminders were generated throughout the course of the trial (median, 3 reminders per patient per hospital stay; interquartile range [IQR], 1-6). These messages led to a change in practice in approximately 4 of 100 patients. The resolution rate was 38.0% (95% CI, 37.2%-38.8%) in the intervention group and 33.7% (95% CI, 32.9%-34.4%) in the control group, corresponding to an odds ratio of 1.21 (95% CI, 1.11-1.32; P < .001). The length of hospital stay did not differ between the groups, with a median time of 8 days (IQR, 5-13 days) for the intervention group and a median time of 8 days (IQR, 5-14 days) for the control group (P = .36). In-hospital all-cause mortality also did not differ between groups (odds ratio, 0.95; 95% CI, 0.77-1.17; P = .59). Alert fatigue did not differ between early and late study periods. Conclusions and Relevance: An international commercial CDSS intervention marginally influenced routine practice in a general hospital, although the change did not statistically significantly affect patient outcomes. Trial Registration: ClinicalTrials.gov identifier: NCT02577198.

A higher d-dimer threshold safely rules-out pulmonary embolism in very elderly emergency department patients.

INTRODUCTION: D-dimer is commonly used in the workup of suspected Pulmonary Embolism (PE), but its specificity decreases with age. We evaluated whether using a higher cutoff value for D-dimer could increase the test specificity without reducing its sensitivity for ruling-out PE in elderly and very elderly patients presenting to the Emergency Department (ED). MATERIAL AND METHODS: All patients with D-dimer and pulmonary Computed Tomography Angiography (CTA) performed in the ED of Vimercate Hospital, from 2010 through 2012 for clinical suspicion of PE were included in this retrospective cohort study. RESULTS: Study population 481 patients (63.4% women, mean age 73.0 ± 16.1 years, confirmed PE 22.5%). In very elderly patients (aged 80 or more years, n=191), compared with standard 490 ng/mL D-dimer threshold, both higher fixed (1000 ng/mL) and age-adjusted cutoffs increase the specificity of D-dimer for the exclusion of PE maintaining a Negative Predictive Value of 100%. Potentially avoided CTAs were 12(6.3%) using 1000 ng/mL cutoff and 10(5.2%) age-adjusted. In very elderly patients the Number Needed to Test was incalculable for the standard cutoff (0 cases), 16 for 1000 ng/mL and 19 for age-adjusted. In patients with PE, index episode mortality was 6.5%, and death occurred only in subjects with D-dimer values above 1000ng/mL and age-adjusted thresholds. CONCLUSION: For very elderly patients with suspected PE in ED, both higher fixed D-dimer (1000 ng/mL) and age-adjusted thresholds increase test specificity for excluding PE without reducing its sensitivity, leading to a safe reduction in the number of CTAs.