Yingjie Qi1, Jian-An Jia2, Huiming Li3, Nagen Wan3, Shuqin Zhang4, Xiaoling Ma5. 1. The First Affiliated Hospital of University of Science and Technology of China (Anhui Provincial Hospital Infection Hospital), Susong Road 218#, Hefei, 230022, Anhui Province, China. 2. Department of Laboratory Medicine, The 901Th Hospital of Joint Logistics Support Force of Chinese People's Liberation Army, Hefei, 230031, Anhui, China. 3. Department of Laboratory Medicine, The First Affiliated Hospital of Nanchang University, Nanchang, 330006, Jiangxi, China. 4. Centre for Computational Systems Biology, School of Mathematical Sciences, Fudan University, Shanghai, 200433, China. 5. The First Affiliated Hospital of University of Science and Technology of China (Anhui Provincial Hospital Infection Hospital), Susong Road 218#, Hefei, 230022, Anhui Province, China. maxiaoling@ustc.edu.cn.
Abstract
BACKGROUND: It is important to recognize the coronavirus disease 2019 (COVID-19) patients in severe conditions from moderate ones, thus more effective predictors should be developed. METHODS: Clinical indicators of COVID-19 patients from two independent cohorts (Training data: Hefei Cohort, 82 patients; Validation data: Nanchang Cohort, 169 patients) were retrospected. Sparse principal component analysis (SPCA) using Hefei Cohort was performed and prediction models were deduced. Prediction results were evaluated by receiver operator characteristic curve and decision curve analysis (DCA) in above two cohorts. RESULTS: SPCA using Hefei Cohort revealed that the first 13 principal components (PCs) account for 80.8% of the total variance of original data. The PC1 and PC12 were significantly associated with disease severity with odds ratio of 4.049 and 3.318, respectively. They were used to construct prediction model, named Model-A. In disease severity prediction, Model-A gave the best prediction efficiency with area under curve (AUC) of 0.867 and 0.835 in Hefei and Nanchang Cohort, respectively. Model-A's simplified version, named as LMN index, gave comparable prediction efficiency as classical clinical markers with AUC of 0.837 and 0.800 in training and validation cohort, respectively. According to DCA, Model-A gave slightly better performance than others and LMN index showed similar performance as albumin or neutrophil-to-lymphocyte ratio. CONCLUSIONS: Prediction models produced by SPCA showed robust disease severity prediction efficiency for COVID-19 patients and have the potential for clinical application.
BACKGROUND: It is important to recognize the coronavirus disease 2019 (COVID-19) patients in severe conditions from moderate ones, thus more effective predictors should be developed. METHODS: Clinical indicators of COVID-19patients from two independent cohorts (Training data: Hefei Cohort, 82 patients; Validation data: Nanchang Cohort, 169 patients) were retrospected. Sparse principal component analysis (SPCA) using Hefei Cohort was performed and prediction models were deduced. Prediction results were evaluated by receiver operator characteristic curve and decision curve analysis (DCA) in above two cohorts. RESULTS: SPCA using Hefei Cohort revealed that the first 13 principal components (PCs) account for 80.8% of the total variance of original data. The PC1 and PC12 were significantly associated with disease severity with odds ratio of 4.049 and 3.318, respectively. They were used to construct prediction model, named Model-A. In disease severity prediction, Model-A gave the best prediction efficiency with area under curve (AUC) of 0.867 and 0.835 in Hefei and Nanchang Cohort, respectively. Model-A's simplified version, named as LMN index, gave comparable prediction efficiency as classical clinical markers with AUC of 0.837 and 0.800 in training and validation cohort, respectively. According to DCA, Model-A gave slightly better performance than others and LMN index showed similar performance as albumin or neutrophil-to-lymphocyte ratio. CONCLUSIONS:Prediction models produced by SPCA showed robust disease severity prediction efficiency for COVID-19patients and have the potential for clinical application.
Entities:
Keywords:
COVID-19; Prediction; Principal component analysis; SARS-CoV-2; Severity
Authors: Jetan H Badhiwala; Christopher D Witiw; Farshad Nassiri; Blessing N R Jaja; Muhammad A Akbar; Alireza Mansouri; Zamir Merali; George M Ibrahim; Jefferson R Wilson; Michael G Fehlings Journal: Spine J Date: 2018-05-07 Impact factor: 4.166
Authors: Christine M Leeper; Matthew D Neal; Christine McKenna; Timothy Billiar; Barbara A Gaines Journal: Surgery Date: 2017-12-13 Impact factor: 3.982
Authors: Sridhar V Basavaraju; Monica E Patton; Kacie Grimm; Mohammed Ata Ur Rasheed; Sandra Lester; Lisa Mills; Megan Stumpf; Brandi Freeman; Azaibi Tamin; Jennifer Harcourt; Jarad Schiffer; Vera Semenova; Han Li; Bailey Alston; Muyiwa Ategbole; Shanna Bolcen; Darbi Boulay; Peter Browning; Li Cronin; Ebenezer David; Rita Desai; Monica Epperson; Yamini Gorantla; Tao Jia; Panagiotis Maniatis; Kimberly Moss; Kristina Ortiz; So Hee Park; Palak Patel; Yunlong Qin; Evelene Steward-Clark; Heather Tatum; Andrew Vogan; Briana Zellner; Jan Drobeniuc; Matthew R P Sapiano; Fiona Havers; Carrie Reed; Susan Gerber; Natalie J Thornburg; Susan L Stramer Journal: Clin Infect Dis Date: 2021-06-15 Impact factor: 9.079
Authors: Trine Kåsine; Anne Ma Dyrhol-Riise; Andreas Barratt-Due; Anders Benjamin Kildal; Inge Christoffer Olsen; Katerina Nezvalova-Henriksen; Fridtjof Lund-Johansen; Hedda Hoel; Aleksander Rygh Holten; Anders Tveita; Alexander Mathiessen; Mette Haugli; Ragnhild Eiken; Åse Berg; Asgeir Johannessen; Lars Heggelund; Tuva Børresdatter Dahl; Bente Halvorsen; Pawel Mielnik; Lan Ai Kieu Le; Lars Thoresen; Gernot Ernst; Dag Arne Lihaug Hoff; Hilde Skudal; Bård Reiakvam Kittang; Roy Bjørkholt Olsen; Birgitte Tholin; Carl Magnus Ystrøm; Nina Vibeche Skei; Raisa Hannula; Olav Dalgard; Ane-Kristine Finbråten; Kristian Tonby; Saad Aballi; Fredrik Müller; Kristin Greve-Isdahl Mohn; Marius Trøseid; Pål Aukrust; Thor Ueland Journal: J Intern Med Date: 2021-10-03 Impact factor: 13.068