Correlating drug prescriptions with prognosis in severe COVID-19: first step towards resource management.

BACKGROUND: Optimal COVID-19 management is still undefined. In this complicated scenario, the construction of a computational model capable of extracting information from electronic medical records, correlating signs, symptoms and medical prescriptions, could improve patient management/prognosis. METHODS: The aim of this study is to investigate the correlation between drug prescriptions and outcome in patients with COVID-19. We extracted data from 3674 medical records of hospitalized patients: drug prescriptions, outcome, and demographics. The outcome evaluated was hospital outcome. We applied correlation analysis using a Logistic Regression algorithm for machine learning with Lasso and Matthews correlation coefficient. RESULTS: We found correlations between drugs and patient outcomes (death/discharged alive). Anticoagulants, used very frequently during all phases of the disease, were associated with good prognosis only after the first week of symptoms. Antibiotics very frequently prescribed, especially early, were not correlated with outcome, suggesting that bacterial infections may not be important in determining prognosis. There were no differences between age groups. CONCLUSIONS: In conclusion, we achieved an important result in the area of Artificial Intelligence, as we were able to establish a correlation between concrete variables in a real and extremely complex environment of clinical data from COVID-19. Our results are an initial and promising contribution in decision-making and real-time environments to support resource management and forecasting prognosis of patients with COVID-19.

Predicting the outcome for COVID-19 patients by applying time series classification to electronic health records.

BACKGROUND: COVID-19 caused more than 622 thousand deaths in Brazil. The infection can be asymptomatic and cause mild symptoms, but it also can evolve into a severe disease and lead to death. It is difficult to predict which patients will develop severe disease. There are, in the literature, machine learning models capable of assisting diagnose and predicting outcomes for several diseases, but usually these models require laboratory tests and/or imaging. METHODS: We conducted a observational cohort study that evaluated vital signs and measurements from patients who were admitted to Hospital das Clínicas (São Paulo, Brazil) between March 2020 and October 2021 due to COVID-19. The data was then represented as univariate and multivariate time series, that were used to train and test machine learning models capable of predicting a patient's outcome. RESULTS: Time series-based machine learning models are capable of predicting a COVID-19 patient's outcome with up to 96% general accuracy and 81% accuracy considering only the first hospitalization day. The models can reach up to 99% sensitivity (discharge prediction) and up to 91% specificity (death prediction). CONCLUSIONS: Results indicate that time series-based machine learning models combined with easily obtainable data can predict COVID-19 outcomes and support clinical decisions. With further research, these models can potentially help doctors diagnose other diseases.

Use and misuse of biomarkers and the role of D-dimer and C-reactive protein in the management of COVID-19: A post-hoc analysis of a prospective cohort study.

OBJECTIVE: Coronavirus disease 2019 (COVID-19) is associated with high mortality among hospitalized patients and incurs high costs. Severe acute respiratory syndrome coronavirus 2 infection can trigger both inflammatory and thrombotic processes, and these complications can lead to a poorer prognosis. This study aimed to evaluate the association and temporal trends of D-dimer and C-reactive protein (CRP) levels with the incidence of venous thromboembolism (VTE), hospital mortality, and costs among inpatients with COVID-19. METHODS: Data were extracted from electronic patient records and laboratory databases. Crude and adjusted associations for age, sex, number of comorbidities, Sequential Organ Failure Assessment score at admission, and D-dimer or CRP logistic regression models were used to evaluate associations. RESULTS: Between March and June 2020, COVID-19 was documented in 3,254 inpatients. The D-dimer level ≥4,000 ng/mL fibrinogen equivalent unit (FEU) mortality odds ratio (OR) was 4.48 (adjusted OR: 1.97). The CRP level ≥220 mg/dL OR for death was 7.73 (adjusted OR: 3.93). The D-dimer level ≥4,000 ng/mL FEU VTE OR was 3.96 (adjusted OR: 3.26). The CRP level ≥220 mg/dL OR for VTE was 2.71 (adjusted OR: 1.92). All these analyses were statistically significant (p<0.001). Stratified hospital costs demonstrated a dose-response pattern. Adjusted D-dimer and CRP levels were associated with higher mortality and doubled hospital costs. In the first week, elevated D-dimer levels predicted VTE occurrence and systemic inflammatory harm, while CRP was a hospital mortality predictor. CONCLUSION: D-dimer and CRP levels were associated with higher hospital mortality and a higher incidence of VTE. D-dimer was more strongly associated with VTE, although its discriminative ability was poor, while CRP was a stronger predictor of hospital mortality. Their use outside the usual indications should not be modified and should be discouraged.

Setting up hospital care provision to patients with COVID-19: lessons learnt at a 2400-bed academic tertiary center in São Paulo, Brazil.

As of August 30, 2020, Brazil ranked second among countries with the highest number of COVID-19 cases, with the city of São Paulo as the national epidemic epicenter. Local public healthcare institutions were challenged to respond to a fast-growing hospital demand, reengineering care provision to optimize clinical outcomes and minimize intra-hospital coronavirus infection. In this paper we describe how the largest public hospital complex in Latin America faced this unprecedented burden, managing severe COVID-19 cases while sustaining specialized care to patients with other conditions. In our strategic plan a 900-bed hospital was exclusively designated for COVID-19 care and continuity of care to those not infected with coronavirus ensured in other inpatient facilities. After 152 days, 4241 patients with severe COVID-19 were hospitalized, 70% of whom have already been discharged, whereas the remaining Institutes of the complex successfully maintained high complexity inpatient and urgent/emergency care to non-COVID-19 patients.