Using machine learning algorithms based on patient admission laboratory parameters to predict adverse outcomes in COVID-19 patients
Yuchen Fu,
Xuejing Xu,
Juan Du,
Taihong Huang,
Jiping Shi,
Guanghao Song,
Qing Gu,
Han Shen,
Sen Wang
Affiliations
Yuchen Fu
Department of Clinical Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, 210008, China; State Key Laboratory for Novel Software Technology, National Institute of Healthcare Data Science at Nanjing University, Nanjing, 210008, China
Xuejing Xu
Department of Clinical Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, 210008, China
Juan Du
Comprehensive Cancer Center of Drum Tower Hospital, Medical School of Nanjing University, Clinical Cancer Institute of Nanjing University, Nanjing, 210008, China
Taihong Huang
Department of Clinical Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, 210008, China
Jiping Shi
Department of Clinical Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, 210008, China
Guanghao Song
Department of Clinical Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, 210008, China
Qing Gu
State Key Laboratory for Novel Software Technology, National Institute of Healthcare Data Science at Nanjing University, Nanjing, 210008, China; Corresponding author.
Han Shen
Department of Clinical Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, 210008, China; Corresponding author.
Sen Wang
Department of Clinical Laboratory Medicine, Nanjing Drum Tower Hospital, Affiliated Hospital of Medical School, Nanjing University, Nanjing, 210008, China; Corresponding author.
Amidst the global COVID-19 pandemic, the urgent need for timely and precise patient prognosis assessment underscores the significance of leveraging machine learning techniques. In this study, we present a novel predictive model centered on routine clinical laboratory test data to swiftly forecast patient survival outcomes upon admission. Our model integrates feature selection algorithms and binary classification algorithms, optimizing algorithmic selection through meticulous parameter control. Notably, we developed an algorithm coupling Lasso and SVM methodologies, achieving a remarkable area under the ROC curve of 0.9277 with the use of merely 8 clinical laboratory parameters collected upon admission. Our primary contribution lies in the utilization of straightforward laboratory parameters for prognostication, circumventing data processing intricacies, and furnishing clinicians with an expeditious and precise prognostic assessment tool.
