The application of artificial intelligence (AI) techniques to identify frailty within a residential aged care administrative data set.

INTRODUCTION: Research has shown that frailty, a geriatric syndrome associated with an increased risk of negative outcomes for older people, is highly prevalent among residents of residential aged care facilities (also called long term care facilities or nursing homes). However, progress on effective identification of frailty within residential care remains at an early stage, necessitating the development of new methods for accurate and efficient screening. OBJECTIVES: We aimed to determine the effectiveness of artificial intelligence (AI) algorithms in accurately identifying frailty among residents aged 75 years and over in comparison with a calculated electronic Frailty Index (eFI) based on a routinely-collected residential aged care administrative data set drawn from 10 residential care facilities located in Queensland, Australia. A secondary objective included the identification of best-performing candidate algorithms. METHODS: We designed a frailty prediction system based on the eFI identification of frailty, allocating 84.5 % and 15.5 % of the data to training and test data sets respectively. We compared the performance of 18 specific scenarios to predict frailty against eFI based on unique combinations of three ML algorithms (support vector machines [SVM], decision trees [DT] and K-nearest neighbours [KNN]) and six cases (6, 10, 11, 14, 39 and 70 input variables). We calculated accuracy, percentage positive and negative agreement, sensitivity, specificity, Cohen's kappa and Prevalence- and Bias- Adjusted Kappa (PABAK), table frequencies and positive and negative predictive values. RESULTS: Of 592 eligible resident records, 500 were allocated to the training set and 92 to the test set. Three scenarios (10, 11 and 70 input variables), all based on SVM algorithm, returned overall accuracy above 75 %. CONCLUSIONS: There is some potential for AI techniques to contribute towards better frailty identification within residential care. However, potential benefits will need to be weighed against administrative burden, data quality concerns and presence of potential bias.

Prevalence and associations of frailty in residents of Australian aged care facilities: findings from a retrospective cohort study.

OBJECTIVES: Studies conducted among older people have shown that frailty is a common condition associated with an array of adverse outcomes. The aims of this study were to identify the prevalence and associations of frailty in older people residing in several aged care facilities located in Queensland, Australia. METHODS: The database used for this study was drawn from the Aged Care Funding Instrument (ACFI) database of an Australian aged care provider, and contained data from ten aged care facilities in Queensland, Australia. A modification of an eFI originally developed by Clegg and colleagues and based on Rockwood's Frailty Index (FI) of cumulative deficits was used to identify frailty. RESULTS: In total, 592 participants aged 75 years and over were included in the study (66.6% female). Median (IQR) age was 88.0 (9.0) years. Frailty prevalence among the sample was 43.6%, with 46.3% pre-frail and 10.1% not frail. In a multivariate logistic regression analysis incorporating three different models, frailty was significantly associated with three ACFI domains (Nutrition, Depression and Complex Health Care), along with facility size, consistently across two models. In the third model, frailty was also significantly associated with arthritis, diabetes, hypertension, osteoporosis and vision problems, along with male gender. CONCLUSION: There is a need to develop frailty identification and management programs as part of standard care pathways for older adults residing in aged care facilities. Aged care facilities should consider regular frailty screening in residential aged care residents, along with interventions addressing specific issues such as dysphagia and depression.

Older People Who Are Frequent Users of Acute Care: A Symptom of Fragmented Care? A Case Series Report on Patients' Pathways of Care.

Older frequent users of acute care can experience fragmented care. There is a need to understand the issues in a local context before attempting to address fragmented care. 0.5% (n=61) of the population in a defined local government area were identified as having ≥4 unplanned emergency department (ED) presentations/ admissions to an acute-care hospital over 13 months. A retrospective case-series study was conducted to examine detailed pathways of care for 17 patients within the identified population. The two dominant presentation reasons were clinical symptoms associated with a declining/significant loss of capacity in fundamental self-care activities and chronic cardiac/respiratory conditions. Of patients discharged home, 21% of discharge letters were delayed >7 days and only 19% received a written discharge plan. Half of community dwelling patients received home nursing and/or assistance. Frequent users of acute care can experience untimely hospital communication and may require more coordinated care provided in the community to assist self-care and manage chronic conditions.

An evaluation of a network for professional development in child and adolescent mental health in rural and remote communities.

In 1998 a telemedicine network was established in South Australia and the Northern Territory to deliver educational material to professionals working in child and adolescent mental health in remote areas. The network involved a wide range of health professions, from psychiatrists to psychologists and social workers. The first 12 months of network activity were evaluated by quantitative and qualitative techniques. Four sources of data were used: an activity log, questionnaires, interviews and action research. A total of 36 telemedicine sessions were held, ranging in duration from 45 to 90 min (average 56 min) and involving a total of 45 different professionals, who participated an average of four times each (range 1-15). The most common types of session were case discussions (47%), followed by specialist seminars (36%) and administrative and introductory sessions (17%). The benefits of the network included: networking and peer support; improved efficiency and reduced travel costs; and improved efficiency of health services. The problems included: costs; lack of access to technical support; and the need for staff induction and training.