The objective was to identify the chronic impact of SARS-CoV-2 virus infection in new diagnostics, pharmacological prescriptions, and use of healthcare resources in patients after acute infection in a case-control study. Methods: Case-control study with observation of new diagnostics codified in the Electronic Health Recordings, with a total population of 604,000 subjects. Cases included patients diagnosed with acute infection. Matched controls in the absence of infection using a Propensity Score were also included. Observational period was 6 months. New diagnostic (CIE10), prescriptions and visits to Health Care Resources were identified. Results: 38,167 patients with a previous COVID infection and the same number of controls were analyzed. Population included < 18 years old, 7586 (mean age 10.2 years, girls 49%), and 30,581 adults (mean age 46.6 years, females 53%). In adults, 25% presented new diagnoses, while the prevalence was 16% in youth. A total of 40 new diagnostics were identified. The most frequent were diagnostics in the neuropsychiatric sphere, with older age, female, and previous admission in the Critical Care Unit being the factors related in adults, while in youth higher age was also a factor. Prescription of psychoanaleptic, psycholeptic and muscle relaxants had increased. An increment of around 20% in visits to Primary Care Physicians, Specialists and Emergency Departments was registered. Conclusion: Compared with a control group, an increment in the number of new diagnostics, new prescriptions and higher use of Health Care resources were observed. Many of the new diagnoses also occur in non-infected subjects, supporting the complex origin of so-called Long-COVID.
Artificial Intelligence is creating a paradigm shift in health care, with phenotyping patients through clustering techniques being one of the areas of interest. Objective: To develop a predictive model to classify heart failure (HF) patients according to their left ventricular ejection fraction (LVEF), by using available data from Electronic Health Records (EHR). Subjects and methods: 2854 subjects over 25 years old with a diagnosis of HF and LVEF, measured by echocardiography, were selected to develop an algorithm to predict patients with reduced EF using supervised analysis. The performance of the developed algorithm was tested in heart failure patients from Primary Care. To select the most influentual variables, the LASSO algorithm setting was used, and to tackle the issue of one class exceeding the other one by a large amount, we used the Synthetic Minority Oversampling Technique (SMOTE). Finally, Random Forest (RF) and XGBoost models were constructed. Results: The full XGBoost model obtained the maximum accuracy, a high negative predictive value, and the highest positive predictive value. Gender, age, unstable angina, atrial fibrillation and acute myocardial infarct are the variables that most influence EF value. Applied in the EHR dataset, with a total of 25,594 patients with an ICD-code of HF and no regular follow-up in cardiology clinics, 6170 (21.1%) were identified as pertaining to the reduced EF group. Conclusion: The obtained algorithm was able to identify a number of HF patients with reduced ejection fraction, who could benefit from a protocol with a strong possibility of success. Furthermore, the methodology can be used for studies using data extracted from the Electronic Health Records.