Machine Learning Successfully Detects Patients with COVID-19 Prior to PCR Results and Predicts Their Survival Based on Standard Laboratory Parameters in an Observational Study

• Published in: Infectious diseases and therapy Vol. 12; no. 1; pp. 111 - 129
• Main Authors: Styrzynski, Filip, Zhakparov, Damir, Schmid, Marco, Roqueiro, Damian, Lukasik, Zuzanna, Solek, Julia, Nowicki, Jakub, Dobrogowski, Milosz, Makowska, Joanna, Sokolowska, Milena, Baerenfaller, Katja
• Format: Journal Article
• Language: English
• Published: Cheshire Springer Healthcare 01.01.2023; Springer; Springer Nature B.V
• Subjects: C-reactive protein; Comparative analysis; Comparative studies; COVID-19; Hemoglobin; Infectious Diseases; Internal Medicine; Leukocytes; Lymphocytes; Machine learning; Medical diagnosis; Medical prognosis; Medicine; Medicine & Public Health; Neutrophils; Observational studies; Original Research; Pandemics; Proteins; Severe acute respiratory syndrome coronavirus 2; Poland; China; SARS-CoV-2 diagnosis; Laboratory parameters; Predictive features; COVID-19 prognosis; Machine learning
• ISSN: 2193-8229; 2193-6382
• DOI: 10.1007/s40121-022-00707-8

Introduction In the current COVID-19 pandemic, clinicians require a manageable set of decisive parameters that can be used to (i) rapidly identify SARS-CoV-2 positive patients, (ii) identify patients with a high risk of a fatal outcome on hospital admission, and (iii) recognize longitudinal warning signs of a possible fatal outcome. Methods This comparative study was performed in 515 patients in the Maria Skłodowska-Curie Specialty Voivodeship Hospital in Zgierz, Poland. The study groups comprised 314 patients with COVID-like symptoms who tested negative and 201 patients who tested positive for SARS-CoV-2 infection; of the latter, 72 patients with COVID-19 died and 129 were released from hospital. Data on which we trained several machine learning (ML) models included clinical findings on admission and during hospitalization, symptoms, epidemiological risk, and reported comorbidities and medications. Results We identified a set of eight on-admission parameters: white blood cells, antibody-synthesizing lymphocytes, ratios of basophils/lymphocytes, platelets/neutrophils, and monocytes/lymphocytes, procalcitonin, creatinine, and C-reactive protein. The medical decision tree built using these parameters differentiated between SARS-CoV-2 positive and negative patients with up to 90–100% accuracy. Patients with COVID-19 who on hospital admission were older, had higher procalcitonin, C-reactive protein, and troponin I levels together with lower hemoglobin and platelets/neutrophils ratio were found to be at highest risk of death from COVID-19. Furthermore, we identified longitudinal patterns in C-reactive protein, white blood cells, and D dimer that predicted the disease outcome. Conclusions Our study provides sets of easily obtainable parameters that allow one to assess the status of a patient with SARS-CoV-2 infection, and the risk of a fatal disease outcome on hospital admission and during the course of the disease.