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
收藏
页码:152 / 162
页数:11
相关论文
共 43 条
[1]   Frailty Assessment in the Cardiovascular Care of Older Adults [J].
Afilalo, Jonathan ;
Alexander, Karen P. ;
Mack, Michael J. ;
Maurer, Mathew S. ;
Green, Philip ;
Allen, Larry A. ;
Popma, Jeffrey J. ;
Ferrucci, Luigi ;
Forman, Daniel E. .
JOURNAL OF THE AMERICAN COLLEGE OF CARDIOLOGY, 2014, 63 (08) :747-762
[2]  
McDonagh Theresa A, 2021, Eur Heart J, V42, P3599, DOI [10.1002/ejhf.2333, 10.1016/j.rec.2022.05.005, 10.1093/eurheartj/ehab368]
[3]   Trends in Length of Stay and Short-term Outcomes Among Medicare Patients Hospitalized for Heart Failure, 1993-2006 [J].
Bueno, Hector ;
Ross, Joseph S. ;
Wang, Yun ;
Chen, Jersey ;
Vidan, Maria T. ;
Normand, Sharon-Lise T. ;
Curtis, Jeptha P. ;
Drye, Elizabeth E. ;
Lichtman, Judith H. ;
Keenan, Patricia S. ;
Kosiborod, Mikhail ;
Krumholz, Harlan M. .
JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2010, 303 (21) :2141-2147
[4]   OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields [J].
Cao, Zhe ;
Hidalgo, Gines ;
Simon, Tomas ;
Wei, Shih-En ;
Sheikh, Yaser .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2021, 43 (01) :172-186
[5]   Lower Extremity Performance Measures Predict Long-Term Prognosis in Older Patients Hospitalized for Heart Failure [J].
Chiarantini, Daniela ;
Volpato, Stefano ;
Sioulis, Fotini ;
Bartalucci, Francesca ;
Del Bianco, Laura ;
Mangani, Irene ;
Pepe, Giuseppe ;
Tarantini, Francesca ;
Berni, Andrea ;
Marchionni, Niccolo ;
Di Bari, Mauro .
JOURNAL OF CARDIAC FAILURE, 2010, 16 (05) :390-395
[6]   Association between frailty and the combination of physical activity level and sedentary behavior in older adults [J].
da Silva, Venicius Dantas ;
Tribess, Sheilla ;
Meneguci, Joilson ;
Sasaki, Jeffer Eidi ;
Garcia-Meneguci, Cintia Aparecida ;
Oliveira Carneiro, Jose Ailton ;
Virtuoso, Jair Sindra, Jr. .
BMC PUBLIC HEALTH, 2019, 19 (1)
[7]   Clinical frailty scale: Inter-rater reliability of retrospective scoring in emergency abdominal surgery [J].
Fornaess, Katarina M. ;
Nome, Pia L. ;
Aakre, Elin Kismul ;
Hegvik, Tor-Arne ;
Jammer, Ib .
ACTA ANAESTHESIOLOGICA SCANDINAVICA, 2022, 66 (01) :25-29
[8]   Frailty in older adults: Evidence for a phenotype [J].
Fried, LP ;
Tangen, CM ;
Walston, J ;
Newman, AB ;
Hirsch, C ;
Gottdiener, J ;
Seeman, T ;
Tracy, R ;
Kop, WJ ;
Burke, G ;
McBurnie, MA .
JOURNALS OF GERONTOLOGY SERIES A-BIOLOGICAL SCIENCES AND MEDICAL SCIENCES, 2001, 56 (03) :M146-M156
[9]   Extremely randomized trees [J].
Geurts, P ;
Ernst, D ;
Wehenkel, L .
MACHINE LEARNING, 2006, 63 (01) :3-42
[10]   THE DELPHI TECHNIQUE - A CRITIQUE [J].
GOODMAN, CM .
JOURNAL OF ADVANCED NURSING, 1987, 12 (06) :729-734