Predicting mortality and incident immobility in older Belgian men by characteristics related to sarcopenia and frailty.

There is an increasing awareness of sarcopenia in older people. We applied machine learning principles to predict mortality and incident immobility in older Belgian men through sarcopenia and frailty characteristics. Mortality could be predicted with good accuracy. Serum 25-hydroxyvitamin D and bone mineral density scores were the most important predictors. INTRODUCTION: Machine learning principles were used to predict 5-year mortality and 3-year incident severe immobility in a population of older men by frailty and sarcopenia characteristics. METHODS: Using prospective data from 1997 on 264 older Belgian men (n = 152 predictors), 29 statistical models were developed and tuned on 75% of data points then validated on the remaining 25%. The model with the highest test area under the curve (AUC) was chosen as the best. From these, ranked predictor importance was extracted. RESULTS: Five-year mortality could be predicted with good accuracy (test AUC of .85 [.73; .97], sensitivity 78%, specificity 89% at a probability cut-off of 22.3%) using a Bayesian generalized linear model. Three-year incident severe immobility could be predicted with fair accuracy (test AUC .74 [.57; .91], sensitivity 67%, specificity 78% at a probability cut-off of 14.2%) using a multivariate adaptive regression splines model. Serum 25-hydroxyvitamin D levels and hip bone mineral density scores were the most important predictors of mortality, while biochemical androgen markers and Short-Form 36 Physical Domain questions were the most important predictors of immobility. Sarcopenia assessed by lean mass estimates was relevant to mortality prediction but not immobility prediction. CONCLUSIONS: Using advanced statistical models and a machine learning approach 5-year mortality can be predicted with good accuracy using a Bayesian generalized linear model and 3-year incident severe immobility with fair accuracy using a multivariate adaptive regression splines model.

Hand grip strength as a screening tool for frailty in older patients with haematological malignancies.

OBJECTIVES: Frailty is a geriatric syndrome characterized by decreased physiological reserves and an age-related vulnerability to stressors with higher risk of adverse health outcomes. Comprehensive geriatric assessment (CGA) might detect frailty but is time-consuming, implying the need for initial frailty screening. Most frailty screening tools do not include functional measures. Hand grip strength (HGS) is a reliable surrogate for overall muscle strength and predicts functional decline, morbidity and mortality. No studies are available in cancer patients on HGS as screening tool for frailty. We aimed to assess whether HGS can be used as a screening tool to predict an abnormal CGA and therefore frailty. METHODS: Single centre cohort study in 59 patients aged 70 years or more with a haematological malignancy. HGS was measured using a vigorimeter. A patient was considered frail if any of the CGA elements were impaired. RESULTS: Mean HGS before start of therapy in women was 37.0 ± 14.3 kPa and in men 66.1 ± 13.1 kPa. An abnormal CGA was present in 52 subjects (88%). HGS was associated with concurrent abnormal CGA (p = 0.058 in women, p = 0.009 in men). AUC was 0.800 (SE = 0.130) in women and 0.847 (SE = 0.118) in men. Optimal HGS cut-off points for likelihood of abnormal CGA were ≤52 kPa in women and ≤80 kPa in men. DISCUSSION: In older patients with haematological malignancies, impairment in muscle function is present at diagnosis. HGS seems a promising screening tool to identify patients with abnormal CGA.