Machine learning models for identifying pre-frailty in community dwelling older adults

Background

There is increasing evidence that pre-frailty manifests as early as middle age. Understanding the factors contributing to an early trajectory from good health to pre-frailty in middle aged and older adults is needed to inform timely preventive primary care interventions to mitigate early decline and future frailty.

Methods

A cohort of 656 independent community dwelling adults, aged 40–75 years, living in South Australia, undertook a comprehensive health assessment as part of the Inspiring Health cross-sectional observational study. Secondary analysis was completed using machine learning models to identify factors common amongst participants identified as not frail or pre-frail using the Clinical Frailty Scale (CFS) and Fried Frailty Phenotype (FFP). A correlation-based feature selection was used to identify factors associated with pre-frailty classification. Four machine learning models were used to derive the prediction models for classification of not frail and pre-frail. The class discrimination capability of the machine learning algorithms was evaluated using area under the receiver operating characteristic curve (AUC), sensitivity, specificity, precision, F1-score and accuracy.

Results

Two stages of feature selection were performed. The first stage included 78 physiologic, anthropometric, environmental, social and lifestyle variables. A follow-up analysis with a narrower set of 63 variables was then conducted with physiologic factors associated with the FFP associated features removed, to uncover indirect indicators connected with pre-frailty. In addition to the expected physiologic measures, a range of anthropometric, environmental, social and lifestyle variables were found to be associated with pre-frailty outcomes for the cohort. With FFP variables removed, machine learning (ML) models found higher BMI and lower muscle mass, poorer grip strength and balance, higher levels of distress, poor quality sleep, shortness of breath and incontinence were associated with being classified as pre-frail. The machine learning models achieved an AUC score up to 0.817 and 0.722 for FFP and CFS respectively for predicting pre-frailty. With feature selection, the performance of ML models improved by up to + 7.4% for FFP and up to + 7.9% for CFS.

Conclusions

The results of this study indicate that machine learning methods are well suited for predicting pre-frailty and indicate a range of factors that may be useful to include in targeted health assessments to identify pre-frailty in middle aged and older adults.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12877-022-03475-9.

Physical Frailty: ICFSR International Clinical Practice Guidelines for Identification and Management

OBJECTIVE

The task force of the International Conference of Frailty and Sarcopenia Research (ICFSR) developed these clinical practice guidelines to overview the current evidence-base and to provide recommendations for the identification and management of frailty in older adults.

METHODS

These recommendations were formed using the GRADE approach, which ranked the strength and certainty (quality) of the supporting evidence behind each recommendation. Where the evidence-base was limited or of low quality, Consensus Based Recommendations (CBRs) were formulated. The recommendations focus on the clinical and practical aspects of care for older people with frailty, and promote person-centred care. Recommendations for Screening and Assessment: The task force recommends that health practitioners case identify/screen all older adults for frailty using a validated instrument suitable for the specific setting or context (strong recommendation). Ideally, the screening instrument should exclude disability as part of the screening process. For individuals screened as positive for frailty, a more comprehensive clinical assessment should be performed to identify signs and underlying mechanisms of frailty (strong recommendation). Recommendations for Management: A comprehensive care plan for frailty should address polypharmacy (whether rational or nonrational), the management of sarcopenia, the treatable causes of weight loss, and the causes of exhaustion (depression, anaemia, hypotension, hypothyroidism, and B12 deficiency) (strong recommendation). All persons with frailty should receive social support as needed to address unmet needs and encourage adherence to a comprehensive care plan (strong recommendation). First-line therapy for the management of frailty should include a multi-component physical activity programme with a resistance-based training component (strong recommendation). Protein/caloric supplementation is recommended when weight loss or undernutrition are present (conditional recommendation). No recommendation was given for systematic additional therapies such as cognitive therapy, problem-solving therapy, vitamin D supplementation, and hormone-based treatment. Pharmacological treatment as presently available is not recommended therapy for the treatment of frailty.