Frailty Identification Using Heart Rate Dynamics: A Deep Learning Approach

Frailty identification using a sensor-based upper-extremity function test: a deep learning approach

The global increase in the older adult population highlights the need for effective frailty assessment, a condition linked to adverse health outcomes such as hospitalization and mortality. Existing frailty assessment tools, like the Fried phenotype and Rockwood score, have practical limitations, necessitating a more efficient approach. This study aims to enhance frailty prediction accuracy in older adults using a combined biomechanical and deep learning approach. We recruited 312 participants (126 non-frail, 145 pre-frail, 41 frail) and assessed frailty using the Fried index, upper-extremity function (UEF) test, and muscle force calculations. Machine learning (ML) models, including logistic regression and support vector machine (SVM), were employed alongside deep learning with long short-term memory (LSTM) networks. Results showed that incorporating muscle model parameters significantly improved frailty prediction. The LSTM model achieved the highest accuracy (74%), outperforming SVM (67%) and regression (66%), with precision and F1 scores of 81% and 75%, respectively. Notably, muscle co-contraction emerged as a critical predictor, with frail individuals exhibiting substantially higher levels. Our findings demonstrate that integrating UEF tasks with deep learning models provides superior frailty prediction, potentially offering a robust, efficient clinical tool. However, further validation with larger, more diverse populations is needed to confirm the generalizability of our results. This study underscores the potential of advanced computational techniques to improve the identification and monitoring of frailty in older adults.

Digital biomarkers for real-life, home-based monitoring of frailty: a systematic review and meta-analysis

BACKGROUND

Frailty, characterised by decreased physiological function and increased vulnerability to stressors, was associated with an increase in numerous adverse outcomes. Although the number of digital biomarkers for detecting frailty in older adults is increasing, there remains a lack of evidence regarding their effectiveness for early detection and follow-up in real-world, home-based settings.

METHODS

Five databases were searched from inception until 1 August 2024. Standardised forms were utilised for data extraction. The Quality Assessment of Diagnostic Accuracy Studies was used to assess the risk of bias and applicability of included studies. A meta-analysis was conducted to assess the overall sensitivity and specificity for frailty detection.

RESULTS

The systematic review included 16 studies, identifying digital biomarkers relevant for frailty detection, including gait, activity, sleep, heart rate, hand movements and room transition. Meta-analysis further revealed pooled sensitivity of 0.78 [95% confidence interval (CI): 0.70-0.86] and specificity of 0.79 (95% CI: 0.72-0.86) to classify robust and pre-frailty/frailty participants. The overall risk of bias indicated that all the included studies were characterised as having a high or unclear risk of bias.

CONCLUSION

This study offers a thorough characterisation of digital biomarkers for detecting frailty, underscoring their potential for early prediction in home settings. These findings are instrumental in bridging the gap between evidence and practice, enabling more proactive and personalised healthcare monitoring. Further longitudinal studies involving larger sample sizes are necessary to validate the effectiveness of these digital biomarkers as diagnostic tools or prognostic indicators.

Sensor-Based Frailty Assessment Using Fitbit

This study evaluated the reliability of Fitbit in assessing frailty based on motor and heart rate (HR) parameters through a validated upper extremity function (UEF) test, which involves 20 s of rapid elbow flexion. For motor performance, participants completed six trials of full elbow flexion using their right arm, with and without weight. Fitbit and a commercial motion sensor were worn on the right arm. For HR measurements, an ECG system was placed on the left chest alongside the Fitbit on the left wrist. Motor parameters assessing speed, flexibility, weakness, exhaustion, and HR before, during, and after UEF were measured. A total of 42 participants (age = 22 ± 3) were recruited. For motor parameters, excellent agreement was observed between the wearable sensor and Fitbit, except for flexibility (ICC = 0.87 ± 0.09). For HR parameters, ICC values showed weak agreement between ECG and Fitbit for HR increase and recovery (ICC = 0.24 ± 0.11), while moderate to stronger agreement was seen for mean HR during baseline, task, and post-task (ICC = 0.81 ± 0.13). Fitbit is a reliable tool for assessing frailty through motor parameters and provides reasonably accurate HR estimates during baseline, task, and recovery periods. However, Fitbit's ability to track rapid HR changes during activity is limited.

Ability of Heart Rate Recovery and Gait Kinetics in a Single Wearable to Predict Frailty: Quasiexperimental Pilot Study

BACKGROUND

Aging is a risk factor for falls, frailty, and disability. The utility of wearables to screen for physical performance and frailty at the population level is an emerging research area. To date, there is a limited number of devices that can measure frailty and physical performance simultaneously.

OBJECTIVE

The aim of this study is to evaluate the accuracy and validity of a continuous digital monitoring wearable device incorporating gait mechanics and heart rate recovery measurements for detecting frailty, poor physical performance, and falls risk in older adults at risk of falls.

METHODS

This is a substudy of 156 community-dwelling older adults ≥60 years old with falls or near falls in the past 12 months who were recruited for a fall prevention intervention study. Of the original participants, 22 participants agreed to wear wearables on their ankles. An interview questionnaire involving demographics, cognition, frailty (FRAIL), and physical function questions as well as the Falls Risk for Older People in the Community (FROP-Com) was administered. Physical performance comprised gait speed, timed up and go (TUG), and the Short Physical Performance Battery (SPPB) test. A gait analyzer was used to measure gait mechanics and steps (FRAIL-functional: fatigue, resistance, and aerobic), and a heart rate analyzer was used to measure heart rate recovery (FRAIL-nonfunctional: weight loss and chronic illness).

RESULTS

The participants' mean age was 74.6 years. Of the 22 participants, 9 (41%) were robust, 10 (46%) were prefrail, and 3 (14%) were frail. In addition, 8 of 22 (36%) had at least one fall in the past year. Participants had a mean gait speed of 0.8 m/s, a mean SPPB score of 8.9, and mean TUG time of 13.8 seconds. The sensitivity, specificity, and area under the curve (AUC) for the gait analyzer against the functional domains were 1.00, 0.84, and 0.92, respectively, for SPPB (balance and gait); 0.38, 0.89, and 0.64, respectively, for FRAIL-functional; 0.45, 0.91, and 0.68, respectively, for FROP-Com; 0.60, 1.00, and 0.80, respectively, for gait speed; and 1.00, 0.94, and 0.97, respectively, for TUG. The heart rate analyzer demonstrated superior validity for the nonfunctional components of frailty, with a sensitivity of 1.00, specificity of 0.73, and AUC of 0.83.

CONCLUSIONS

Agreement between the gait and heart rate analyzers and the functional components of the FRAIL scale, gait speed, and FROP-Com was significant. In addition, there was significant agreement between the heart rate analyzer and the nonfunctional components of the FRAIL scale. The gait and heart rate analyzers could be used in a screening test for frailty and falls in community-dwelling older adults but require further improvement and validation at the population level.

The application of machine learning for identifying frailty in older patients during hospital admission

BACKGROUND

Early identification of frail patients and early interventional treatment can minimize the frailty-related medical burden. This study investigated the use of machine learning (ML) to detect frailty in hospitalized older adults with acute illnesses.

METHODS

We enrolled inpatients of the geriatric medicine ward at Taichung veterans general hospital between 2012 and 2022. We compared four ML models including logistic regression, random forest (RF), extreme gradient boosting, and support vector machine (SVM) for the prediction of frailty. The feature window as well as the prediction window was set as half a year before admission. Furthermore, Shapley additive explanation plots and partial dependence plots were used to identify Fried's frailty phenotype for interpreting the model across various levels including domain, feature, and individual aspects.

RESULTS

We enrolled 3367 patients. Of these, 2843 were frail. We used 21 features to train the prediction model. Of the 4 tested algorithms, SVM yielded the highest AUROC, precision and F1-score (78.05%, 94.53% and 82.10%). Of the 21 features, age, gender, multimorbidity frailty index, triage, hemoglobin, neutrophil ratio, estimated glomerular filtration rate, blood urea nitrogen, and potassium were identified as more impactful due to their absolute values.

CONCLUSIONS

Our results demonstrated that some easily accessed parameters from the hospital clinical data system can be used to predict frailty in older hospitalized patients using supervised ML methods.

Short-term heart rate variability: A potential approach to frailty assessment in older adults

Objectives

This study aimed to evaluate cardiac autonomic modulation using short-term heart rate variability (HRV) and compare it among frailty statuses in older Indian adults.

Methods

A total of 210 subjects aged 60 years and above were recruited into three groups: frail (n = 70), pre-frail (n = 70), and non-frail (n = 70) from the outpatient department of Geriatric Medicine at a tertiary care hospital in India. Frailty status was assessed using the Rockwood frailty index (FI) criteria. HRV was derived from a 5-min ECG recording of standard limb leads and assessed using time domain, frequency domain, and nonlinear analysis of cardiac interval variability.

Results

The HRV parameters indicative of parasympathetic modulation such as SDNN, SDSD, rMSSD, NN50, pNN50, absolute HF power, and SD1 were significantly lower in frail subjects compared with both pre-frail and non-frail subjects (P < 0.05). Absolute LF power and SD2 were also lower in frail subjects compared with pre-frail and non-frail subjects (P < 0.05). Measures of sympatho-vagal balance (LF/HF and SD1/SD2 ratios) did not show statistical significance. The FI demonstrated negative correlations with all HRV parameters.

Conclusions

Frail individuals exhibit decreased sympathetic and parasympathetic modulation compared with pre-frail and non-frail individuals, although maintaining a balanced sympatho-vagal state. Furthermore, autonomic modulation declines progressively with increasing frailty.

Associating frailty and dynamic dysregulation between motor and cardiac autonomic systems

Frailty is a geriatric syndrome associated with the lack of physiological reserve and consequent adverse outcomes (therapy complications and death) in older adults. Recent research has shown associations between heart rate (HR) dynamics (HR changes during physical activity) with frailty. The goal of the present study was to determine the effect of frailty on the interconnection between motor and cardiac systems during a localized upper-extremity function (UEF) test. Fifty-six individuals aged 65 or above were recruited and performed the previously developed UEF test consisting of 20-s rapid elbow flexion with the right arm. Frailty was assessed using the Fried phenotype. Wearable gyroscopes and electrocardiography were used to measure motor function and HR dynamics. In this study, the interconnection between motor (angular displacement) and cardiac (HR) performance was assessed, using convergent cross-mapping (CCM). A significantly weaker interconnection was observed among pre-frail and frail participants compared to non-frail individuals (p < 0.01, effect size = 0.81 ± 0.08). Using logistic models, pre-frailty and frailty were identified with sensitivity and specificity of 82%-89%, using motor, HR dynamics, and interconnection parameters. Findings suggested a strong association between cardiac-motor interconnection and frailty. Adding CCM parameters in a multimodal model may provide a promising measure of frailty.

Use of Artificial Intelligence in the Identification and Diagnosis of Frailty Syndrome in Older Adults: Scoping Review

BACKGROUND

Frailty syndrome (FS) is one of the most common noncommunicable diseases, which is associated with lower physical and mental capacities in older adults. FS diagnosis is mostly focused on biological variables; however, it is likely that this diagnosis could fail owing to the high biological variability in this syndrome. Therefore, artificial intelligence (AI) could be a potential strategy to identify and diagnose this complex and multifactorial geriatric syndrome.

OBJECTIVE

The objective of this scoping review was to analyze the existing scientific evidence on the use of AI for the identification and diagnosis of FS in older adults, as well as to identify which model provides enhanced accuracy, sensitivity, specificity, and area under the curve (AUC).

METHODS

A search was conducted using PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guidelines on various databases: PubMed, Web of Science, Scopus, and Google Scholar. The search strategy followed Population/Problem, Intervention, Comparison, and Outcome (PICO) criteria with the population being older adults; intervention being AI; comparison being compared or not to other diagnostic methods; and outcome being FS with reported sensitivity, specificity, accuracy, or AUC values. The results were synthesized through information extraction and are presented in tables.

RESULTS

We identified 26 studies that met the inclusion criteria, 6 of which had a data set over 2000 and 3 with data sets below 100. Machine learning was the most widely used type of AI, employed in 18 studies. Moreover, of the 26 included studies, 9 used clinical data, with clinical histories being the most frequently used data type in this category. The remaining 17 studies used nonclinical data, most frequently involving activity monitoring using an inertial sensor in clinical and nonclinical contexts. Regarding the performance of each AI model, 10 studies achieved a value of precision, sensitivity, specificity, or AUC ≥90.

CONCLUSIONS

The findings of this scoping review clarify the overall status of recent studies using AI to identify and diagnose FS. Moreover, the findings show that the combined use of AI using clinical data along with nonclinical information such as the kinematics of inertial sensors that monitor activities in a nonclinical context could be an appropriate tool for the identification and diagnosis of FS. Nevertheless, some possible limitations of the evidence included in the review could be small sample sizes, heterogeneity of study designs, and lack of standardization in the AI models and diagnostic criteria used across studies. Future research is needed to validate AI systems with diverse data sources for diagnosing FS. AI should be used as a decision support tool for identifying FS, with data quality and privacy addressed, and the tool should be regularly monitored for performance after being integrated in clinical practice.

Machine learning approaches for frailty detection, prediction and classification in elderly people: A systematic review

BACKGROUND

Frailty in older people is a syndrome related to aging that is becoming increasingly common and problematic as the average age of the world population increases. Detecting frailty in its early stages or, even better, predicting its appearance can greatly benefit health in later years of life and save the healthcare system from high costs. Machine Learning models fit the need to develop a tool for supporting medical decision-making in detecting or predicting frailty.

METHODS

In this review, we followed the PRISMA methodology to conduct a systematic search of the most relevant Machine Learning models that have been developed so far in the context of frailty. We selected 41 publications and compared them according to their purpose, the type of dataset used, the target variables, and the results they obtained, highlighting their shortcomings and strengths.

RESULTS

The variety of frailty definitions allows many problems to fall into this field, and it is often challenging to compare results due to the differences in target variables. The data types can be divided into gait data, usually collected with sensors, and medical records, often in the context of aging studies. The most common algorithms are well-known models available from every Machine Learning library. Only one study developed a new framework for frailty classification, and only two considered Explainability.

CONCLUSIONS

This review highlights some gaps in the field of Machine Learning applied to the assessment and prediction of frailty, such as the need for a universal quantitative definition. It emphasizes the need for close collaboration between medical professionals and data scientists to unlock the potential of data collected in hospital and clinical settings. As a suggestion for future work, the area of Explainability, which is crucial for models in medicine and health care, was considered in very few studies.

Digital health technology combining wearable gait sensors and machine learning improve the accuracy in prediction of frailty

Background

Frailty is a dynamic and complex geriatric condition characterized by multi-domain declines in physiological, gait and cognitive function. This study examined whether digital health technology can facilitate frailty identification and improve the efficiency of diagnosis by optimizing analytical and machine learning approaches using select factors from comprehensive geriatric assessment and gait characteristics.

Methods

As part of an ongoing study on observational study of Aging, we prospectively recruited 214 individuals living independently in the community of Southern China. Clinical information and fragility were assessed using comprehensive geriatric assessment (CGA). Digital tool box consisted of wearable sensor-enabled 6-min walk test (6MWT) and five machine learning algorithms allowing feature selections and frailty classifications.

Results

It was found that a model combining CGA and gait parameters was successful in predicting frailty. The combination of these features in a machine learning model performed better than using either CGA or gait parameters alone, with an area under the curve of 0.93. The performance of the machine learning models improved by 4.3-11.4% after further feature selection using a smaller subset of 16 variables. SHapley Additive exPlanation (SHAP) dependence plot analysis revealed that the most important features for predicting frailty were large-step walking speed, average step size, age, total step walking distance, and Mini Mental State Examination score.

Conclusion

This study provides evidence that digital health technology can be used for predicting frailty and identifying the key gait parameters in targeted health assessments.

A Systematic Survey of Data Augmentation of ECG Signals for AI Applications

AI techniques have recently been put under the spotlight for analyzing electrocardiograms (ECGs). However, the performance of AI-based models relies on the accumulation of large-scale labeled datasets, which is challenging. To increase the performance of AI-based models, data augmentation (DA) strategies have been developed recently. The study presented a comprehensive systematic literature review of DA for ECG signals. We conducted a systematic search and categorized the selected documents by AI application, number of leads involved, DA method, classifier, performance improvements after DA, and datasets employed. With such information, this study provided a better understanding of the potential of ECG augmentation in enhancing the performance of AI-based ECG applications. This study adhered to the rigorous PRISMA guidelines for systematic reviews. To ensure comprehensive coverage, publications between 2013 and 2023 were searched across multiple databases, including IEEE Explore, PubMed, and Web of Science. The records were meticulously reviewed to determine their relevance to the study's objective, and those that met the inclusion criteria were selected for further analysis. Consequently, 119 papers were deemed relevant for further review. Overall, this study shed light on the potential of DA to advance the field of ECG diagnosis and monitoring.

Machine Learning Approaches for the Frailty Screening: A Narrative Review

Frailty characterizes a state of impairments that increases the risk of adverse health outcomes such as physical limitation, lower quality of life, and premature death. Frailty prevention, early screening, and management of potential existing conditions are essential and impact the elderly population positively and on society. Advanced machine learning (ML) processing methods are one of healthcare’s fastest developing scientific and technical areas. Although research studies are being conducted in a controlled environment, their translation into the real world (clinical setting, which is often dynamic) is challenging. This paper presents a narrative review of the procedures for the frailty screening applied to the innovative tools, focusing on indicators and ML approaches. It results in six selected studies. Support vector machine was the most often used ML method. These methods apparently can identify several risk factors to predict pre-frail or frailty. Even so, there are some limitations (e.g., quality data), but they have enormous potential to detect frailty early.

Chronotropic Response and Heart Rate Variability before and after a 160 m Walking Test in Young, Middle-Aged, Frail, and Non-Frail Older Adults

The frailty syndrome is characterized by a decreased capacity to adequately respond to stressors. One of the most impaired physiological systems is the autonomous nervous system, which can be assessed through heart rate (HR) variability (HRV) analysis. In this article, we studied the chronotropic response (HR and HRV) to a walking test. We also analyzed HRV indices in rest as potential biomarkers of frailty. For this, a 160 m-walking test and two standing rest tests (before and after the walking) were performed by young (19−29 years old, n = 21, 57% women), middle-aged (30−59 years old, n = 16, 62% women), and frail older adults (>60 years old, n = 28, 40% women) and non-frail older adults (>60 years old, n = 15, 71% women), classified with the FRAIL scale and the Clinical Frailty Scale (CFS). Frequency domain parameters better allowed to distinguish between frail and non-frail older adults (low-frequency power LF, high-frequency power HF (nu), LF/HF ratio, and ECG-derived respiration rate EDR). Frail older adults showed an increased HF (nu) and EDR and a reduced LF (nu) and LF/HF compared to non-frail older adults. The increase in HF (nu) could be due to a higher breathing effort. Our results showed that a walk of 160 m is a sufficient cardiovascular stressor to exhibit an attenuated autonomic response in frail older adults. Several HRV indices showed to be potential biomarkers of frailty, being LF (nu) and the time required to reach the maximum HR the best candidates.

Predictive Accuracy of Digital Biomarker Technologies for Detection of Mild Cognitive Impairment and Pre-Frailty Amongst Older Adults: A Systematic Review and Meta-Analysis

Digital biomarker technologies coupled with predictive models are increasingly applied for early detection of age-related potentially reversible conditions including mild cognitive impairment (MCI) and pre-frailty (PF). We aimed to determine the predictive accuracy of digital biomarker technologies to detect MCI and PF with systematic review and meta-analysis. A computer-assisted search on major academic research databases including IEEE-Xplore was conducted. Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines were adopted reporting in this study. Summary receiver operating characteristic curve based on random-effect bivariate model was used to evaluate overall sensitivity and specificity for detection of the respective age-related conditions. A total of 43 studies were selected for final systematic review and meta-analysis. 26 studies reported on detection of MCI with sensitivity and specificity of 0.48-1.00 and 0.55-1.00, respectively. On the other hand, there were 17 studies that reported on the detection of PF with reported sensitivity of 0.53-1.00 and specificity of 0.61-1.00. Meta-analysis further revealed pooled sensitivities of 0.84 (95% CI: 0.79-0.88) and 0.82 (95% CI: 0.74-0.88) for in-home detection of MCI and PF, respectively, while pooled specificities were 0.85 (95% CI: 0.80-0.89) and 0.82 (95% CI: 0.75-0.88), respectively. Besides MCI, and PF, in this work during systematic review, we also found one study which reported a sensitivity of 0.93 and a specificity of 0.57 for detection of cognitive frailty (CF). The meta-analytic result, for the first time, quantifies the predictive efficacy of digital biomarker technologies for detection of MCI and PF. Additionally, we found the number of studies for detection of CF to be notably lower, indicating possible research gaps to explore predictive models on digital biomarker technology for detection of CF.