Machine learning-based gait analysis to predict clinical frailty scale in elderly patients with heart failure

被引：5

作者：

Mizuguchi, Yoshifumi ^{[1
,2
]}

Nakao, Motoki ^{[1
,2
]}

Nagai, Toshiyuki ^{[1
,2
]}

Takahashi, Yuki ^{[1
,2
]}

Abe, Takahiro ^{[1
,2
]}

Kakinoki, Shigeo ^{[3
]}

Imagawa, Shogo ^{[4
]}

Matsutani, Kenichi ^{[5
]}

Saito, Takahiko ^{[6
]}

Takahashi, Masashige ^{[7
]}

Kato, Yoshiya ^{[8
]}

Komoriyama, Hirokazu ^{[8
]}

Hagiwara, Hikaru ^{[8
]}

Hirata, Kenji ^{[2
,9
]}

Ogawa, Takahiro ^{[10
]}

Shimizu, Takuto ^{[11
]}

Otsu, Manabu ^{[11
]}

Chiyo, Kunihiro ^{[11
]}

Anzai, Toshihisa ^{[1
,2
]}

机构：

[1] Hokkaido Univ, Fac Med, Dept Cardiovasc Med, Kita 15 Nishi 7,Kita Ku, Sapporo 0608638, Japan

[2] Hokkaido Univ, Grad Sch Med, Kita 15 Nishi 7,Kita Ku, Sapporo 0608638, Japan

[3] Otaru Kyokai Hosp, Dept Cardiol, Otaru, Hokkaido, Japan

[4] Natl Hosp Org Hakodate Natl Hosp, Dept Cardiol, Hakodate, Hokkaido, Japan

[5] Sunagawa City Med Ctr, Dept Cardiol, Sunagawa, Hokkaido, Japan

[6] Sunagawa City Med Ctr, Dept Cardiol, Sunagawa, Hokkaido, Japan

[7] Japan Community Healthcare Org Hokkaido Hosp, Dept Cardiol, Sapporo, Japan

[8] Kushiro City Gen Hosp, Dept Cardiol, Kushiro, Hokkaido, Japan

[9] Hokkaido Univ, Fac Med, Dept Diagnost Imaging, Sapporo, Japan

[10] Hokkaido Univ, Fac Informat Sci & Technol, Sapporo, Japan

[11] INFOCOM Corp, Tech Planning Off, Tokyo, Japan

来源：

EUROPEAN HEART JOURNAL - DIGITAL HEALTH | 2024年 / 5卷 / 02期

关键词：

Artificial intelligence; Machine learning; Gait analysis; Frailty; Heart failure; INTERRATER RELIABILITY; MORTALITY; PREVALENCE; PROGNOSIS; STROKE; CARE;

D O I：

10.1093/ehjdh/ztad082

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Aims Although frailty assessment is recommended for guiding treatment strategies and outcome prediction in elderly patients with heart failure (HF), most frailty scales are subjective, and the scores vary among raters. We sought to develop a machine learning-based automatic rating method/system/model of the clinical frailty scale (CFS) for patients with HF.Methods and results We prospectively examined 417 elderly (>= 75 years) with symptomatic chronic HF patients from 7 centres between January 2019 and October 2023. The patients were divided into derivation (n = 194) and validation (n = 223) cohorts. We obtained body-tracking motion data using a deep learning-based pose estimation library, on a smartphone camera. Predicted CFS was calculated from 128 key features, including gait parameters, using the light gradient boosting machine (LightGBM) model. To evaluate the performance of this model, we calculated Cohen's weighted kappa (CWK) and intraclass correlation coefficient (ICC) between the predicted and actual CFSs. In the derivation and validation datasets, the LightGBM models showed excellent agreements between the actual and predicted CFSs [CWK 0.866, 95% confidence interval (CI) 0.807-0.911; ICC 0.866, 95% CI 0.827-0.898; CWK 0.812, 95% CI 0.752-0.868; ICC 0.813, 95% CI 0.761-0.854, respectively]. During a median follow-up period of 391 (inter-quartile range 273-617) days, the higher predicted CFS was independently associated with a higher risk of all-cause death (hazard ratio 1.60, 95% CI 1.02-2.50) after adjusting for significant prognostic covariates.Conclusion Machine learning-based algorithms of automatically CFS rating are feasible, and the predicted CFS is associated with the risk of all-cause death in elderly patients with HF. Graphical Abstract

引用

页码：152 / 162

页数：11

共 43 条

[21] Frailty assessment instruments in heart failure: A systematic review [J].