Dataset Information

Comparisons Between Hypothesis- and Data-Driven Approaches for Multimorbidity Frailty Index: A Machine Learning Approach.

ABSTRACT: BACKGROUND:Using big data and the theory of cumulative deficits to develop the multimorbidity frailty index (mFI) has become a widely accepted approach in public health and health care services. However, constructing the mFI using the most critical determinants and stratifying different risk groups with dose-response relationships remain major challenges in clinical practice. OBJECTIVE:This study aimed to develop the mFI by using machine learning methods that select variables based on the optimal fitness of the model. In addition, we aimed to further establish 4 entities of risk using a machine learning approach that would achieve the best distinction between groups and demonstrate the dose-response relationship. METHODS:In this study, we used Taiwan's National Health Insurance Research Database to develop a machine learning multimorbidity frailty index (ML-mFI) using the theory of cumulative diseases/deficits of an individual older person. Compared to the conventional mFI, in which the selection of diseases/deficits is based on expert opinion, we adopted the random forest method to select the most influential diseases/deficits that predict adverse outcomes for older people. To ensure that the survival curves showed a dose-response relationship with overlap during the follow-up, we developed the distance index and coverage index, which can be used at any time point to classify the ML-mFI of all subjects into the categories of fit, mild frailty, moderate frailty, and severe frailty. Survival analysis was conducted to evaluate the ability of the ML-mFI to predict adverse outcomes, such as unplanned hospitalizations, intensive care unit (ICU) admissions, and mortality. RESULTS:The final ML-mFI model contained 38 diseases/deficits. Compared with conventional mFI, both indices had similar distribution patterns by age and sex; however, among people aged 65 to 69 years, the mean mFI and ML-mFI were 0.037 (SD 0.048) and 0.0070 (SD 0.0254), respectively. The difference may result from discrepancies in the diseases/deficits selected in the mFI and the ML-mFI. A total of 86,133 subjects aged 65 to 100 years were included in this study and were categorized into 4 groups according to the ML-mFI. Both the Kaplan-Meier survival curves and Cox models showed that the ML-mFI significantly predicted all outcomes of interest, including all-cause mortality, unplanned hospitalizations, and all-cause ICU admissions at 1, 5, and 8 years of follow-up (P<.01). In particular, a dose-response relationship was revealed between the 4 ML-mFI groups and adverse outcomes. CONCLUSIONS:The ML-mFI consists of 38 diseases/deficits that can successfully stratify risk groups associated with all-cause mortality, unplanned hospitalizations, and all-cause ICU admissions in older people, which indicates that precise, patient-centered medical care can be a reality in an aging society.

SUBMITTER: Peng LN

PROVIDER: S-EPMC7317629 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparisons Between Hypothesis- and Data-Driven Approaches for Multimorbidity Frailty Index: A Machine Learning Approach.

Peng Li-Ning LN Hsiao Fei-Yuan FY Lee Wei-Ju WJ Huang Shih-Tsung ST Chen Liang-Kung LK

Journal of medical Internet research 20200611 6

<h4>Background</h4>Using big data and the theory of cumulative deficits to develop the multimorbidity frailty index (mFI) has become a widely accepted approach in public health and health care services. However, constructing the mFI using the most critical determinants and stratifying different risk groups with dose-response relationships remain major challenges in clinical practice.<h4>Objective</h4>This study aimed to develop the mFI by using machine learning methods that select variables base ...[more]

PMID: 32525481

Similar Datasets

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: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.

Project description:BackgroundFew studies have made longitudinal comparisons between frailty phenotype (FP) and frailty index (FI) changes. We aimed to investigate frailty status changes defined by FP and FI concurrently, and to compare the associated factors and incident disability among different combination of FI and FP trajectory groups.MethodsData on respondents aged over 50 who completed the 1999, 2003 and 2007 Taiwan Longitudinal Study on Aging (TLSA) surveys (n = 2807) were excerpted. Changes of FI, FP and major time-dependent variables were constructed by group-based trajectory modeling. Logistic regression was used to investigate the associated factors and relationships with incident disability among different frailty trajectories.ResultsWe identified four FP trajectories - stably robust, worsened frailty, improved frailty, and stably frail and three FI trajectories - stable FI, moderate increase FI and rapid increase FI. Lower self-rated health, mobility impairment, and depressed mood were associated with unfavorable FP and FI changes (all p < 0.001). Regardless of FP trajectory groups, the moderate and rapid increase FI group had significantly more comorbidities than the stable FI group, and more visual, hearing, oral intake impairment, more difficulty in meeting living expenses, and poorer cognitive function in ≥65-year-olds (all p < 0.05). In addition, the worsened frailty, improved frailty, and stably frail groups had ORs for incident disability of 10.5, 3.0, and 13.4, respectively, compared with the stably robust group (all p < 0.01); the moderate and rapid increase FI groups had 8.4-fold and 77.5-fold higher risk than the stable FI group (both p < 0.001). When combining FI and FP trajectories, risk increased with FI trajectory steepness, independent of FP change (all p < 0.01 in rapid increase FI vs stable FI).ConclusionsFour FP trajectories (stably robust, worsened frailty, improved frailty, and stably frail) and three FI trajectories (stable FI, moderate increase FI and rapid increase FI) were identified. Lower self-rated health, mobility impairment, and depressed mood were associated with both unfavorable FP and FI trajectories. Nevertheless, even for individuals in stably robust or improved frailty FP groups, moderate or rapid increase in FI, either due to comorbidities, sensory impairment, cognitive deficits, or financial challenges, may still increase the risk of incident disability.

Project description:BackgroundExisting operational definitions of frailty are personnel-costly and time-consuming, resulting in estimates with a small sample size that cannot be generalized to the population level. The objectives were to develop a multimorbidity frailty index using Taiwan's claim database, and to understand its ability to predict adverse event.MethodsThis is a retrospective cohort study. Subjects aged 65 to 100 years who have full National Health Insurance coverage in 2005 were included. We constructed the multimorbidity frailty index using cumulative deficit approach and categorized study population according to the multimorbidity frailty index quartiles: fit, mild frailty, moderate frailty and severe frailty. The multimorbidity frailty index included deficits from outpatient and inpatient diagnosis. Associations with all-cause mortality, unplanned hospitalization and intensive care unit admission were assessed using Kaplan-Meier curves and Cox regression analyses.ResultsThe multimorbidity frailty index incorporated 32 deficits, with mean multimorbidity frailty index score of 0.052 (standard deviation = 0.060) among 86,133 subjects included. Compared to subjects in fit category, subjects with severe frailty were associated with a 5.0-fold (adjusted hazard ratio, aHR 4.97; 95% confidence interval, 95% CI 4.49-5.50) increased risk of death at 1 year after adjusting for age and gender. Subjects with moderate frailty or mild frailty was associated with 3.1- (adjusted HR 3.08; 95% CI 2.80-3.39) or 1.9- (adjusted HR 1.86; 95% CI 1.71-2.01) folds increased risk, respectively.4.49-5.50). The risk trend of unplanned hospitalization and intensive care unit admission is similar among the study population. Besides, the association between the frailty categories and all three outcomes was slightly stronger among women.ConclusionThe multimorbidity frailty index was highly associated with all-cause mortality, unplanned hospitalization and ICU admission. It could serve as an efficient tool for stratifying older adults into different risk groups for planning care management programs.

Dataset Information

Comparisons Between Hypothesis- and Data-Driven Approaches for Multimorbidity Frailty Index: A Machine Learning Approach.

Publications

Comparisons Between Hypothesis- and Data-Driven Approaches for Multimorbidity Frailty Index: A Machine Learning Approach.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets