Importance analysis of psychosociological variables in frailty syndrome in heart failure patients using machine learning approach.

The prevention and diagnosis of frailty syndrome (FS) in cardiac patients requires innovative systems to support medical personnel, patient adherence, and self-care behavior. To do so, modern medicine uses a supervised machine learning approach (ML) to study the psychosocial domains of frailty in cardiac patients with heart failure (HF). This study aimed to determine the absolute and relative diagnostic importance of the individual components of the Tilburg Frailty Indicator (TFI) questionnaire in patients with HF. An exploratory analysis was performed using machine learning algorithms and the permutation method to determine the absolute importance of frailty components in HF. Based on the TFI data, which contain physical and psychosocial components, machine learning models were built based on three algorithms: a decision tree, a random decision forest, and the AdaBoost Models classifier. The absolute weights were used to make pairwise comparisons between the variables and obtain relative diagnostic importance. The analysis of HF patients' responses showed that the psychological variable TFI20 diagnosing low mood was more diagnostically important than the variables from the physical domain: lack of strength in the hands and physical fatigue. The psychological variable TFI21 linked with agitation and irritability was diagnostically more important than all three physical variables considered: walking difficulties, lack of hand strength, and physical fatigue. In the case of the two remaining variables from the psychological domain (TFI19, TFI22), and for all variables from the social domain, the results do not allow for the rejection of the null hypothesis. From a long-term perspective, the ML based frailty approach can support healthcare professionals, including psychologists and social workers, in drawing their attention to the non-physical origins of HF.

Physical, Psychological and Social Frailty Are Predictive of Heart Failure: A Cross-Sectional Study.

BACKGROUND: Little is known about frailty among patients hospitalized with heart failure (HF). To date, the limited information on frailty in HF is based on a unidimensional view of frailty, in which only physical aspects are considered when determining frailty. The aims of this study were to study different dimensions of frailty (physical, psychological and social) in patients with HF and the effect of different dimensions of frailty on the incidence of heart failure. METHODS: The study used a cross-sectional design and included 965 patients hospitalized for heart failure and 164 healthy controls. HF was defined according to the ESC guidelines. The Tilburg Frailty Indicator (TFI) was used to assess frailty. Probit regression analyses and chi-square statistics were used to examine associations between the occurrence of heart failure and TFI domains of frailty. RESULTS: Patients diagnosed with frailty were 15.3% more likely to develop HF compared to those not diagnosed with frailty (p < 0.001). An increase in physical, psychological and social frailty corresponded to an increased risk of HF of 2.9% (p < 0.001), 4.4% (p < 0.001) and 6.6% (p < 0.001), respectively. CONCLUSIONS: We found evidence of the association between different dimensions of frailty and incidence of HF.

Evaluation of Frailty Syndrome and Adherence to Recommendations in Elderly Patients with Hypertension.

Frailty syndrome (FS) often coexists with many diseases of the elderly, including arterial hypertension, and may affect the disease course and adherence to therapeutic recommendations. This study aimed to evaluate the relationship between frailty and adherence to therapeutic recommendations in elderly hypertensive patients. The study included 259 patients hospitalized between January 2019 and November 2020 due to exacerbation of hypertension symptoms. Medical records were used to obtain basic sociodemographic and clinical data. The study was based on the Tilburg Frailty Indicator (TFI) and the Hill-Bone Scale (HBCS). The obtained data were analyzed within a cross-sectional design. The mean frailty score indicated by the TFI questionnaire was 7.09 ± 3.73. The most prominent FS component was associated with the physical domain (4.24 ± 2.54). The mean overall adherence measured with the HBCS was 20.51 ± 3.72. The linear regression model testing the Hill-Bone "reduced sodium intake" score against the TFI domains showed no relationships between the variables. Another regression model for the Hill-Bone "appointment-keeping" subscale indicated significant predictors for physical and social TFI domains (p = 0.002 and p < 0.0001, respectively). For the Hill-Bone "taking antihypertensive drugs" variable, the regression model found significant relationships with all TFI domains: physical (p < 0.0001), psychological (p = 0.003) and social (p < 0.0001). Our study suggests that frailty in patients with arterial hypertension can negatively impact their adherence to therapeutic recommendations.

Monetary Incentives Increase Metacognitive Confidence in Source Memory Performance in Patients With Schizophrenia.

BACKGROUND: Contemporary psychiatric research focuses its attention on the patient's dysfunction of metacognition in relation to the basic cognitive processes of mental activity. The current study investigated dysfunctional metacognition in relation to self-monitoring of memory in patients diagnosed with schizophrenia. Dysfunctions in metacognition were examined by focusing on two types of metacognitive measures: post-decision wagering (PDW) scale and confidence ratings (CR) scale (CR). OBJECTIVES: The research employed an action-memory task that required patients with schizophrenia (N = 39) and healthy controls (N = 50) to evaluate their metacognition by categorizing self-monitoring actions (imagined vs. performed actions) either with PDW or CR. It was hypothesized that metacognition in self-monitoring activity in patients diagnosed with schizophrenia is improved by imaginary monetary incentives. MATERIAL AND METHODS: To test this hypothesis, participants were asked to memorize actions either performed or imagined during the first phase of the experiment. The second phase was to identify previous actions as performed, imagined or new, and then to express confidence using two measures of metacognition (CR or PDW scales) that were randomly allocated to participants. RESULTS: Our study showed reduced performance in the action memory task for patients with schizophrenia, although there were no group differences in confidence measures when assessing self-monitoring actions. In particular, irrespective of the diagnosis, no differences in confidence measures for correct responses were found in the case of the PDW and CR scales. We also observed that metacognitive judgements were more accurate for incorrect responses when both groups used monetary incentives to reveal their metacognition. CONCLUSIONS: Our findings suggest that monetary incentives improve accuracy of metacognition among both patients and healthy controls. This accuracy-enhancing effect of monetary incentives on metacognition was possibly a result of motivational processes, including aversion to loss. The paper discusses the potential application of PDW in therapeutic metacognitive training for patients with schizophrenia.