Development and validation of machine learning prediction model for post-rehabilitation functional outcome after intracerebral hemorrhage

被引：4

作者：

Sonobe, Shinya ^{[1
,2
,3
,4
,5
]}

Ishikawa, Tetsuo ^{[6
,7
,9
]}

Niizuma, Kuniyasu ^{[1
,2
,3
,4
,5
]}

Kawakami, Eiryo ^{[6
,7
,8
]}

Ueda, Takuya ^{[5
,6
]}

Takaya, Eichi ^{[5
]}

Miyauchi, Carlos Makoto ^{[5
]}

Iwazaki, Junya ^{[5
,10
]}

Kochi, Ryuzaburo ^{[1
,4
]}

Endo, Toshiki ^{[1
,2
,3
]}

Shastry, Arun ^{[11
]}

Jagannatha, Vijayananda ^{[11
]}

Seth, Ajay ^{[11
]}

Nakagawa, Atsuhiro ^{[1
,12
]}

Yoshida, Masahiro ^{[2
,13
]}

Tominaga, Teiji ^{[1
]}

机构：

[1] Tohoku Univ, Dept Neurosurg, Grad Sch Med, Sendai, Miyagi, Japan

[2] Tohoku Univ, Grad Sch Biomed Engn, Dept Neurosurg Engn & Translat Neurosci, Sendai, Miyagi, Japan

[3] Tohoku Univ, Dept Neurosurg Engn & Translat Neurosci, Grad Sch Med, Sendai, Miyagi, Japan

[4] Osaki Citizen Hosp, Dept Neurosurg, Osaki, Miyagi, Japan

[5] Tohoku Univ Hosp, AI Lab, Sendai, Miyagi, Japan

[6] Tohoku Univ, Dept Clin Imaging, Grad Sch Med, Sendai, Miyagi, Japan

[7] RIKEN, Adv Data Sci Project, RIKEN Informat R&D& Strategy Headquarters, Yokohama, Kanagawa, Japan

[8] Chiba Univ, Grad Sch Med, Artificial Intelligence Med, Chiba, Chiba, Japan

[9] Keio Univ, Dept Extended Intelligence Med, Ishii Ishibashi Lab, Sch Med, Shinju Ku, Tokyo, Tokyo, Japan

[10] Tohoku Univ, Off Med Educ, Grad Sch Med, Sendai, Miyagi, Japan

[11] Philips Innovat Campus, Bengaluru, Karnataka, India

[12] Tohoku Univ Hosp, Clin Res Innovat & Educ Ctr, Dept Biodesign, Sendai, Miyagi, Japan

[13] Tohoku Univ, Osaki Citizen Hosp, Dept Preempt Med Community North Miyagi, Grad Sch Med, Sendai, Miyagi, Japan

来源：

INTERDISCIPLINARY NEUROSURGERY-ADVANCED TECHNIQUES AND CASE MANAGEMENT | 2022年 / 29卷

关键词：

Intracerebral hemorrhage; Machine learning prediction; Post-rehabilitation functional outcome; Design thinking; GRADING SCALE; STROKE; MORTALITY; SCORE; RISK;

D O I：

10.1016/j.inat.2022.101560

中图分类号：

R74 [神经病学与精神病学];

学科分类号：

摘要：

Objective: Predicting outcomes after intracerebral hemorrhage (ICH) may help improve patient outcomes. We developed and validated a machine learning prediction model for post-rehabilitation functional outcomes after ICH. Patient selection and explanatory variable settings were based on clinical significance. Functional outcomes were predicted using ternary classification.Methods: The subjects were patients aged > 18 years without pre-onset severe disability who developed primary putaminal and/or thalamic hemorrhage and underwent an inpatient rehabilitation program. As explanatory variables, 43 values related to patient background, imaging-related findings, systemic conditions, neurological findings, and blood tests were acquired within 10 days of onset. As an objective variable, the functional outcome at discharge to home or nursing home was acquired using a ternary classification. The dataset consisting of the collected information was split into a training dataset and a test dataset with a ratio of 2:1. A predictive model using a balanced random forest algorithm was created using supervised learning from the training dataset. The predictive performance was validated using a test dataset.Results: Between January 2018 and June 2019, 100 consecutive patients were included in the study. The areas under the receiver operating characteristic curves for predictions of good, moderate, and poor outcomes were 0.952, 0.790, and 0.921, respectively.

引用

页数：5

共 48 条

[1] Design Thinking in Health Care [J].