Performance Evaluation of Machine Learning Algorithms for Sarcopenia Diagnosis in Older Adults.

BACKGROUND: Sarcopenia is a progressive and generalized skeletal muscle disorder. Early diagnosis is necessary to reduce the adverse effects and consequences of sarcopenia, which can help prevent and manage it in a timely manner. The aim of this study was to identify the important risk factors for sarcopenia diagnosis and compare the performance of machine learning (ML) algorithms in the early detection of potential sarcopenia. METHODS: A cross-sectional design was employed for this study, involving 160 participants aged 65 years and over who resided in a community. ML algorithms were applied by selecting 11 features-sex, age, BMI, presence of hypertension, presence of diabetes mellitus, SARC-F score, MNA score, calf circumference (CC), gait speed, handgrip strength (HS), and mid-upper arm circumference (MUAC)-from a pool of 107 clinical variables. The results of the three best-performing algorithms were presented. RESULTS: The highest accuracy values were achieved by the ALL (male + female) model using LightGBM (0.931), random forest (RF; 0.927), and XGBoost (0.922) algorithms. In the female model, the support vector machine (SVM; 0.939), RF (0.923), and k-nearest neighbors (KNN; 0.917) algorithms performed the best. Regarding variable importance in the ALL model, the last HS, sex, BMI, and MUAC variables had the highest values. In the female model, these variables were HS, age, MUAC, and BMI, respectively. CONCLUSIONS: Machine learning algorithms have the ability to extract valuable insights from data structures, enabling accurate predictions for the early detection of sarcopenia. These predictions can assist clinicians in the context of predictive, preventive, and personalized medicine (PPPM).

Evaluation of the quality of life in the university of third age students: a cross-sectional study.

PURPOSE: The purpose of this paper was to determine the quality of life (QoL) and related factors in university of third age (U3A) students, as well as to compare the QoL between those who participated in education and those who did not. METHODS: Two hundred seventy-one people aged 60 and over who are students at Ege U3A, were included in this cross-sectional study. Demographic data of participants were collected through a pre-prepared form. Data on the QoL of individuals were collected through the short form of the WHO QoL Scale (WHOQOL-BREF). RESULTS: A total of 271 participants were included in this study. 82.2% (n = 221) of the research group were women. In U3A, 65.3% (n = 177) of the individuals were former students. The highest value was found in the psychological and general health sub-parameter with 75.0%, and the lowest value in the social relations sub-parameters with 66.7%. The scores of sub-parameters of social environment were significantly higher in men than in women (p < 0.001, respectively). The physical health scores of the former students were higher than those of the new students (p < 0.001). CONCLUSIONS: It was determined that the QoL of U3A students was higher among males, those with higher education levels, and those who were married, as well as that the QoL of the individuals participating in the U3A training was positive in the physical health sub-dimension. There is a need for future studies in which pre- and post-training evaluations will be conducted to determine the impact of the U3A training program.

Frequency and Risk Factors of Re-hospitalization in Geriatric Inpatient Wards: A Multicenter Retrospective Analysis.

PURPOSE: We aimed to evaluate frequency and risk factors of re-hospitalization which are not stated in comorbidity indexes in geriatric wards. METHODS: A total of 585 patients who were admitted to tertiary care geriatric inpatient clinics at least once between 1 September 2017 and 1 September 2018 and who survived to discharge during initial hospitalization were included in this cross-sectional retrospective multicenter study. RESULTS: Overall, 507(86.7%) patients were hospitalized once for treatment during the study period, while re-hospitalization occurred in 78(13.3%) patients. Rates of previous surgery (10.3 vs. 3.0%, p = .006), urinary incontinence (UI) (50.0 vs. 36.3%, p = .021), controlled hypertension (64.1 vs. 46.4%, p = .024), malnutrition (55.1 vs. 29.6%, p = .014) were significantly higher in re-hospitalized patients. Re-hospitalized patients were younger (mean ± SD 76.4 ± 8.3 vs. 79.6 ± 7.9 years, p = .002) than once-hospitalized patients. Multivariate logistic regression analysis revealed the younger patient age (OR, 0.942, 95% CI 0.910 to 0.976, p = .001), higher Modified Charlson Comorbidity Index (MCCI) score (OR, 1.368, 95% CI 1.170 to 1.600, p < .001) to significantly predict the increased risk of re-hospitalization. CONCLUSIONS: Our findings showed that previous history of surgery and geriatric syndromes such as UI, malnutrition were determined to significantly predict the increased risk of re-hospitalization. We suggest that these risk factors be added to prognostic tools designed for elderly patients.

The impact of the COVID-19 pandemic on well-being of seniors attending online programs at University of the Third Age: a follow-up study.

BACKGROUND: Reports on psychological effects of quarantine during past outbreaks and pandemics showed that quarantined people were more likely to experience psychological problems than those who were not. It was also shown that there was an increase in anxiety, depression, and stress in all age groups during the COVID-19 pandemic. So, we investigated emotional states and quality of life as components of general well-being in older participants of University of the Third Age (U3A) attending online programs during the second year of the pandemic, and compared them with the pre-pandemic COVID-19 period. METHODS: This study was conducted among 27 participants of a U3A program. Data on sociodemographics, Charlson comorbidity index, the Geriatric Depression Scale Short Form (GDS-SF), The Geriatric Anxiety Scale (GAS), and Turkish version of World Health Organization Quality of Life Instrument Older Adults Module (WHOQOL-OLD) were taken in September 2019 and September 2021. RESULTS: The median age of the participants was 68 (60-75) years (81.5% female). In the COVID-19 pandemic period; 'Death and dying' (except for 'Fear of pain before death' score), 'Intimacy' domain, and 'Social participation' domain scores of WHOQOL-OLD decreased compared to the pre-pandemic period (P < 0.001, P = 0.011, and P < 0.001, respectively) whereas the scores for GAS and GDS-SF were higher (P < 0.001 and P = 0.011). The reason for the decrease in 'Social participation' domain scores was the decrease in 'Satisfaction with opportunity to participate in community'. There was no significant difference in 'Autonomy' domain of WHOQOL-OLD (P = 0.598). CONCLUSION: Although there was no change in 'Autonomy' domain among the participants of U3A before and during the pandemic period, anxiety and depression scores were higher in the second year of the COVID pandemic. Only a decrease in satisfaction with opportunity to participate in community might have significant impact on social participation.

The Relationship of Balance Disorders with Falling, the Effect of Health Problems, and Social Life on Postural Balance in the Elderly Living in a District in Turkey.

The aim of this study was to determine the prevalence of balance disorders; the effects of sociodemographic, medical, and social conditions on postural balance; and the relationship between balance and falls in elderly individuals. The study design was cross-sectional. A total of 607 community-dwelling elderly individuals with a mean age of 73.99 ± 6.6 years were enrolled after being selected by stratified random sampling. The study was performed as a face-to-face survey in the homes of elderly individuals. Sociodemographic and medical data were obtained from elderly individuals using the Elderly Identification Form. Balance disorders were determined using the Berg Balance Scale (BBS). In this study, the prevalence of balance disorders was found to be 34.3% in the community-dwelling elderly. Older age, physical disability, having four or more chronic illnesses, the presence of incontinence, having a history of falls, not walking regularly, absence of free time activity, and obesity were found to be associated with an increased prevalence of balance disorders. Balance disorders are commonly seen in the elderly and may be triggered by a variety of biological and social factors. It is crucial to develop and implement national health and social policies to eliminate the causes of this problem, as well as to prioritize preventive health services in the ever-increasing elderly population.