A one-year relapse prediction model for acute ischemic stroke (AIS) based on clinical big data
Wenle Li,
Zhendong Ding,
Liangqun Rong,
Xiu'e Wei,
Chenyu Sun,
Scott Lowe,
Muzi Meng,
Chan Xu,
Chengliang Yin,
Haiyan Liu,
Wencai Liu,
Qian Zhou,
Kai Wang
Affiliations
Wenle Li
The State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics & Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, China; .Key Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China
Zhendong Ding
Department of Anesthesiology, The Third Affiliated Hospital of Sun Yat-sen University, No. 600 Tianhe Road, Guangzhou, 510630, China
Liangqun Rong
.Key Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China; Department of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China
Xiu'e Wei
.Key Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China; Department of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China
Chenyu Sun
Department of Thyroid and Breast Surgery, the Second Affiliated Hospital of Anhui Medical University, Hefei, Anhui, China
Scott Lowe
College of Osteopathic Medicine, Kansas City University, 1750 Independence Ave, Kansas City, MO 64106, USA
Muzi Meng
UK Program Site, American University of the Caribbean School of Medicine, Vernon Building Room 64, Sizer St, Preston PR1 1JQ, United Kingdom; Bronxcare Health System, 1650 Grand Concourse, The Bronx, NY 10457, USA
Chan Xu
The State Key Laboratory of Molecular Vaccinology and Molecular Diagnostics & Center for Molecular Imaging and Translational Medicine, School of Public Health, Xiamen University, Xiamen, China
Chengliang Yin
Faculty of Medicine, Macau University of Science and Technology, Macau, China
Haiyan Liu
.Key Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China; Department of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China
Wencai Liu
Department of Orthopaedics, Shanghai Jiao Tong University Affiliated Sixth People's Hospital, 600 Yishan Road, Shanghai 200233, China; Corresponding author.
Qian Zhou
Department of Respiratory and Critical Care Medicine, People's Hospital of Chongqing Liang Jiang New Area, Chongqing, China; Corresponding author.
Kai Wang
.Key Laboratory of Neurological Diseases, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China; Department of Neurology, The Second Affiliated Hospital of Xuzhou Medical University, Xuzhou, Jiangsu, China; Corresponding author.
Objective: To develop and evaluate a nomogram prediction model for recurrence of acute ischemic stroke (AIS) within one year. Method: Patients with AIS treated at the second affiliated hospital of Xuzhou Medical University from August 2017 to July 2019 were enrolled. Clinical data such as demographic data, risk factors, laboratory tests, TOAST etiological types, MRI features, and treatment methods were collected. Cox regression analysis was done to determine the parameters for entering the nomogram model. The performance of the model was estimated by receiver operating characteristic curves, decision curve analysis, calibration curves, and C-index. Result: A total of 645 patients were enrolled in this study. Side of hemisphere (SOH, Bilateral, HR = 0.35, 95 % CI = 0.15–0.84, p = 0.018), homocysteine (HCY, HR = 1.38, 95 % CI = 1.29–1.47, p < 0.001), c-reactive protein (CRP, HR = 1.04, 95 % CI = 1.01–1.07, p = 0.013) and stroke severity (SS, HR = 3.66, 95 % CI = 2.04–6.57, p < 0.001) were independent risk factors. The C-index of the nomogram model was 0.872 (se = 0.016). The area under the receiver operating characteristic (ROC)curve at one-year recurrence was 0.900. Calibration curve, decision curve analysis showed good performance of the nomogram. The cutoff value for low or high risk of recurrence score was 1.73. Conclusion: The nomogram model for stroke recurrence within one year developed in this study performed well. This useful tool can be used in clinical practice to provide important guidance to healthcare professionals.
