Dataset Information

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

ABSTRACT:

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.

SUBMITTER: Mizuguchi Y

PROVIDER: S-EPMC10944685 | biostudies-literature | 2024 Mar

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

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

Mizuguchi Yoshifumi Y Nakao Motoki M Nagai Toshiyuki T Takahashi Yuki Y Abe Takahiro T Kakinoki Shigeo S Imagawa Shogo S Matsutani Kenichi K Saito Takahiko T Takahashi Masashige M Kato Yoshiya Y Komoriyama Hirokazu H Hagiwara Hikaru H Hirata Kenji K Ogawa Takahiro T Shimizu Takuto T Otsu Manabu M Chiyo Kunihiro K Anzai Toshihisa T

European heart journal. Digital health 20231220 2

<h4>Aims</h4>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.<h4>Methods and results</h4>We prospectively examined 417 elderly (≥75 years) with symptomatic chronic HF patients from 7 centres bet ...[more]

PMID: 38505484

Similar Datasets

Project description:AimsThere is currently no gold standard in evaluating frailty in patients with heart failure (HF), and the prognostic value of frailty according to the Canadian Study of Health and Aging Clinical Frailty Scale (CFS) on mortality in patients with HF is still unknown.Methods and resultsAmong consecutive 596 patients after their discharge from HF in Kokura Memorial Hospital (Kitakyushu, Japan) during 2015, their frailty at discharge was assessed according to CFS. Patients were classified into three groups: low (N = 232, 38.9%), intermediate (N = 230, 38.6%), and high (N = 134, 22.5%). The primary endpoint was defined as 2 year all-cause death. The mean age was 76.6 ± 10.1 years, and 55.3% were men in entire cohort. There were significant differences in age, living environment, and dementia among low, intermediate, and high CFS groups. Left ventricular ejection fraction (LVEF) and co-morbidities such as severe renal failure and severe anaemia tended to increase with frailty severity, while body mass index (BMI) and albumin level tended to decrease with frailty severity. Two year cumulative incidences of all-cause death for the three groups were 12.8%, 25.4%, and 52.7% (P < 0.001), respectively. This significant difference in the risk for all-cause death among the CFS groups was driven by the risk for cardiac (8.6%, 14.2%, and 31.0%, respectively, P < 0.001) and non-cardiac death (4.6%, 13.0%, and 31.4%, respectively, P < 0.001). The multivariate analysis showed that high frailty was independently associated with all-cause death (intermediate CFS group: adjusted hazard ratio, 1.43, 95% confidence interval, 0.86-2.36, P = 0.16; high CFS group: adjusted hazard ratio, 3.90, 95% confidence interval, 2.32-6.55, P < 0.001), and this result was consistent, irrespective of stratification based on age, sex, BMI, and LVEF without significant interaction.ConclusionsThe simple CFS tool was successful in predicting the risk for all-cause death in patients with HF, and frailty according to CFS was independently associated with all-cause death irrespective of stratification based on age, sex, BMI, and LVEF without significant interaction. The CFS is a valuable prognostic tool in clinical settings.

Project description:AimsFrailty is associated with prognosis of cardiovascular diseases. However, the significance of frailty in patients with heart failure with preserved ejection fraction (HFpEF) remains to be elucidated. The purpose of this study was to examine the prognostic significance of the Clinical Frailty Scale (CFS) in real-world patients with HFpEF using data from a prospective multicentre observational study of patients with HFpEF (PURSUIT-HFpEF study).Method and resultsWe classified 842 patients with HFpEF enrolled in the PURSUIT-HFpEF study into two groups using CFS. The registry enrolled patients hospitalized with a diagnosis of decompensated heart failure. Median age was 82 [interquartile range: 77, 87], and 45% of the patients were male. Of 842 patients, 406 were classified as high CFS (CFS ≥ 4, 48%) and 436 as low CFS (CFS ≤ 3, 52%). The primary endpoint was the composite of all-cause mortality and heart failure admission. Secondary endpoints were all-cause mortality and heart failure admission. Patients with high CFS were older (85 vs. 79 years, P < 0.001), predominantly female (65% vs. 46%, P < 0.001) and more likely to have New York Heart Association (NYHA) ≥ 2 (75% vs. 53%, P < 0.001) and a higher level of NT-proBNP (1360 vs 838 pg/mL, P < 0.001) than those with low CFS. Patients with high CFS had a significantly greater risk of composite endpoint (Kaplan-Meier estimated 1-year event rate 39% vs. 23%, log-rank P < 0.001), all-cause mortality (Kaplan-Meier estimated 1-year event rate 17% vs. 7%, log-rank P < 0.001) and heart failure admission (Kaplan-Meier estimated 1-year event rate 28% vs. 19%, log-rank P = 0.002) than those with low CFS. Multivariable Cox regression analysis revealed that high CFS was significantly associated with composite endpoint (adjusted HR 1.92, 95% CI 1.35-2.73, P < 0.001), all-cause mortality (adjusted HR 2.54, 95% CI 1.39-4.66, P = 0.003) and heart failure admission (adjusted HR 1.55, 95% CI 1.03-2.32, P = 0.035) even after adjustment for covariates. Moreover, change in CFS grade was also significantly associated with composite endpoint (adjusted HR 1.23, 95% CI 1.11-1.36, P < 0.001), all-cause mortality (adjusted HR 1.32, 95% CI 1.13-1.55, P = 0.001) and heart failure admission (adjusted HR 1.15, 95% CI 1.02-1.30, P = 0.021).ConclusionsFrailty assessed by the CFS was associated with poor prognosis in patients with HFpEF.

Project description:BACKGROUND:Frailty is one of the most critical age-related conditions in older adults. It is often recognized as a syndrome of physiological decline in late life, characterized by a marked vulnerability to adverse health outcomes. A clear operational definition of frailty, however, has not been agreed so far. There is a wide range of studies on the detection of frailty and their association with mortality. Several of these studies have focused on the possible risk factors associated with frailty in the elderly population while predicting who will be at increased risk of frailty is still overlooked in clinical settings. OBJECTIVE:The objective of our study was to develop predictive models for frailty conditions in older people using different machine learning methods based on a database of clinical characteristics and socioeconomic factors. METHODS:An administrative health database containing 1,095,612 elderly people aged 65 or older with 58 input variables and 6 output variables was used. We first identify and define six problems/outputs as surrogates of frailty. We then resolve the imbalanced nature of the data through resampling process and a comparative study between the different machine learning (ML) algorithms - Artificial neural network (ANN), Genetic programming (GP), Support vector machines (SVM), Random Forest (RF), Logistic regression (LR) and Decision tree (DT) - was carried out. The performance of each model was evaluated using a separate unseen dataset. RESULTS:Predicting mortality outcome has shown higher performance with ANN (TPR 0.81, TNR 0.76, accuracy 0.78, F1-score 0.79) and SVM (TPR 0.77, TNR 0.80, accuracy 0.79, F1-score 0.78) than predicting the other outcomes. On average, over the six problems, the DT classifier has shown the lowest accuracy, while other models (GP, LR, RF, ANN, and SVM) performed better. All models have shown lower accuracy in predicting an event of an emergency admission with red code than predicting fracture and disability. In predicting urgent hospitalization, only SVM achieved better performance (TPR 0.75, TNR 0.77, accuracy 0.73, F1-score 0.76) with the 10-fold cross validation compared with other models in all evaluation metrics. CONCLUSIONS:We developed machine learning models for predicting frailty conditions (mortality, urgent hospitalization, disability, fracture, and emergency admission). The results show that the prediction performance of machine learning models significantly varies from problem to problem in terms of different evaluation metrics. Through further improvement, the model that performs better can be used as a base for developing decision-support tools to improve early identification and prediction of frail older adults.

Project description:AimsThis study aims to develop explainable machine learning models and clinical tools for predicting mortality in patients in the intensive care unit (ICU) with heart failure (HF).MethodsPatients diagnosed with HF who experienced their first ICU stay lasting between 24 h and 28 days were selected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database. The primary outcome was all-cause mortality within 28 days. Data analysis was performed using Python and R, with feature selection conducted via least absolute shrinkage and selection operator (LASSO) regression. Fifteen models were evaluated, and the most effective model was rendered explainable through the Shapley additive explanations (SHAP) approach. A nomogram was developed based on logistic regression to facilitate interpretation. For external validation, the eICU database was utilized.ResultsAfter selection, the study included 2343 records, with 1808 surviving and 535 deceased patients. The median age of the study population was 70.00, with ~3/5 males (60.31%). The median length of stay in the ICU was 6.00 days. The median age of the survival group was younger than the non-survival group (69.00 vs. 73.00), and non-survival patients spent longer time in the ICU. Seventy-five features were initially selected, including basic information, vital signs, laboratory tests, haemodynamics and oxygen status. LASSO regression determined the shrinkage parameter α = 0.020, and 44 features were chosen for model construction. The linear discriminant analysis (LDA) model showed the best performance, and the accuracy reached 0.8354 in the training cohort and 0.8563 in the testing cohort. It showed satisfying area under the curve (AUC), recall, precision, F1 score, Cohen's kappa score and Matthew's correlation coefficient. The concordance index (c-index) reached 0.7972 in the training cohort and 0.8125 in the testing cohort. In external validation, the LDA model achieved approximately 0.9 in accuracy, precision, recall and F1 score, with an AUC of 0.79. Univariable analysis was performed in the training cohort. Features that differed significantly between the survival and non-survival groups were subjected to multiple logistic regression. The nomogram built on multiple logistic regression included 14 features and demonstrated excellent performance. The AUC of the nomogram is 0.852 in the training cohort, 0.855 in the internal validation cohort and 0.770 in the external validation cohort. The calibration curve showed good consistency.ConclusionsThe study developed an LDA and a nomogram model for predicting mortality in HF patients in the ICU. The SHAP approach was employed to elucidate the LDA model, enhancing its utility for clinicians. These models were made accessible online for clinical application.

Project description:AimsFrailty may be found in heart failure patients especially in the elderly and is associated with a poor prognosis. However, assessment of frailty status is time-consuming, and the electronic frailty indices developed using health records have served as useful surrogates. We hypothesized that an electronic frailty index developed using machine learning can improve short-term mortality prediction in patients with heart failure.Methods and resultsThis was a retrospective observational study that included patients admitted to nine public hospitals for heart failure from Hong Kong between 2013 and 2017. Age, sex, variables in the modified frailty index, Deyo's Charlson co-morbidity index (≥2), neutrophil-to-lymphocyte ratio (NLR), and prognostic nutritional index at baseline were analysed. Gradient boosting, which is a supervised sequential ensemble learning algorithm with weak prediction submodels (typically decision trees), was applied to predict mortality. Variables were ranked in the order of importance with a total score of 100 and used to build the frailty models. Comparisons were made with decision tree and multivariable logistic regression. A total of 8893 patients (median: age 81, Q1-Q3: 71-87 years old) were included, in whom 9% had 30 day mortality and 17% had 90 day mortality. Prognostic nutritional index, age, and NLR were the most important variables predicting 30 day mortality (importance score: 37.4, 32.1, and 20.5, respectively) and 90 day mortality (importance score: 35.3, 36.3, and 14.6, respectively). Gradient boosting significantly outperformed decision tree and multivariable logistic regression. The area under the curve from a five-fold cross validation was 0.90 for gradient boosting and 0.87 and 0.86 for decision tree and logistic regression in predicting 30 day mortality. For the prediction of 90 day mortality, the area under the curve was 0.92, 0.89, and 0.86 for gradient boosting, decision tree, and logistic regression, respectively.ConclusionsThe electronic frailty index based on co-morbidities, inflammation, and nutrition information can readily predict mortality outcomes. Their predictive performances were significantly improved by gradient boosting techniques.

Dataset Information

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

Aims

Methods and results

Conclusion

Publications

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

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets