Predicting the Swallow-Related Quality of Life of the Elderly Living in a Local Community Using Support Vector Machine. Int J Environ Res Public Health. 2019;16. [PMID: 31684165 PMCID: PMC6862249 DOI: 10.3390/ijerph16214269]

Distinguishing between bipolar depression and unipolar depression based on the reward circuit activities and clinical characteristics: A machine learning analysis

BACKGROUND

Differentiating bipolar depression (BD) from unipolar depression (UD) is a major clinical challenge. Identifying the potential classifying biomarkers between these two diseases is vital to optimize personalized management of depressed individuals.

METHODS

Here, we aimed to integrate neuroimaging and clinical data with machine learning method to classify BD and UD at the individual level. Data were collected from 31 healthy controls (HC group) and 80 depressive patients with an average follow-up period of 7.51 years. Of these patients, 32 got diagnosis conversion from major depressive disorder (MDD) to BD (BD group) and 48 remain persistent diagnosis of MDD (MDD group). Using graph theory and functional connectivity (FC) analysis, we investigated the differences in reward circuit properties among three groups. Then we applied a support vector machine and leave-one-out cross-validation methods to classify BD and UD patients based on neuroimaging and clinical data.

RESULTS

Compared with MDD and HC, BD showed decreased degree centrality of right mediodorsal thalamus (MD) and nodal efficiency (NE) of left ventral pallidum. Compared with BD and HC, MDD showed decreased NE of right MD and increased FC between right MD and bilateral dorsolateral prefrontal cortex and left ventromedial prefrontal cortex. Notably, the classifier obtained high classification accuracies (87.50 %) distinguishing BD and UD patients based on reward circuit properties and clinical features.

LIMITATIONS

The classifying model requires out-of-sample replication analysis.

CONCLUSION

The reward circuit dysfunction can not only provide additional information to assist clinical differential diagnosis, but also in turn informed treatment decision of depressive patients.

Sarcopenic Dysphagia, Malnutrition, and Oral Frailty in Elderly: A Comprehensive Review

Frailty is a highly prevalent condition in the elderly that has been increasingly considered as a crucial public health issue, due to the strict correlation with a higher risk of fragility fractures, hospitalization, and mortality. Among the age-related diseases, sarcopenia and dysphagia are two common pathological conditions in frail older people and could coexist leading to dehydration and malnutrition in these subjects. “Sarcopenic dysphagia” is a complex condition characterized by deglutition impairment due to the loss of mass and strength of swallowing muscles and might be also related to poor oral health status. Moreover, the aging process is strictly related to poor oral health status due to direct impairment of the immune system and wound healing and physical and cognitive impairment might indirectly influence older people’s ability to carry out adequate oral hygiene. Therefore, poor oral health might affect nutrient intake, leading to malnutrition and, consequently, to frailty. In this scenario, sarcopenia, dysphagia, and oral health are closely linked sharing common pathophysiological pathways, disabling sequelae, and frailty. Thus, the aim of the present comprehensive review is to describe the correlation among sarcopenic dysphagia, malnutrition, and oral frailty, characterizing their phenotypically overlapping features, to propose a comprehensive and effective management of elderly frail subjects.

Exploring the potential of thyroid hormones to predict clinical improvements in depressive patients: A machine learning analysis of the real-world based study

BACKGROUND

Although undergoing antidepressant treatments, many patients continue to struggle with chronic depression episode. Seeking the potential biomarkers and establishing a predictive model of clinical improvements is vital to optimize personalized management of depression. Mounting evidence showed thyroid hormones changes are central to leading paradigms of depression.

METHODS

Here, we conducted a real-world based retrospective study using clinical and biochemical data of 2086 depressive inpatients during period of 2014-2020. We first performed regression analyses to evaluate the contributing effect of free triiodothyronine (FT3), free thyroxine (FT4) and thyroid stimulating hormone (TSH) in predicting the clinical outcomes of depression. Then we established 7 predictive models using different combination of such hormones by supervised learning methods and tested the actual prediction efficacy on clinical outcomes, in order to select the one with the best predictive power.

RESULTS

The results showed that lower values of FT3 and FT4 can both predict a poor clinical outcome in depression. Further, a model with the best performance was selected (sensitivity=0.91, specificity=0.79, and ROC-AUC=0.86), including the values of FT3 and FT4, and the scores of Hamilton Depression Scale (HAMD) and Hamilton Anxiety Scale (HAMA) as features.

LIMITATIONS

The predictive model requires further external validation, and multi-center researches to confirm its clinical applicability.

CONCLUSIONS

Our findings present a crucial role of thyroid measurements in predicting clinical outcomes of depression. Assessment of thyroid hormone should be extended to routine practice settings to determine which patients should be most in need of earlier or intensive interventions for preventing continued dysfunction.

The Contribution of Temporal Flat Lateral Position on the Mortality and Discharge Rates of Older Patients with Severe Dysphagia

Severe dysphagia leads to mortality in older patients and hinders their discharge from hospitals. The temporal flat lateral position (TFLP) enables them to continuously eat, thus resolving the aforementioned issues. We aimed to explore the effect of TFLP on the mortality and discharge rates of older patients with severe dysphagia. This interventional study comprised a historical control of patients admitted to a rural community hospital from January 2019 to December 2020 and diagnosed with severe dysphagia. The primary outcomes included the mortality and the rate of discharge from the hospital. While the intervention group was treated with TFLP, the control group underwent no treatment. We selected 79 participants (intervention group = 26, control group = 53), with an average age of 87.9 years. The discharge rate was significantly higher in the intervention group than in the control group (57.7% vs. 26.4%, p = 0.012). The mortality rate was also significantly lower in the intervention group compared to the control group (34.6% vs. 71.7%, p = 0.003). TFLP can improve the discharge and mortality rates in community hospitals, thereby improving patient outcomes. Clinicians should focus on practical education and the implementation of TFLP in communities in order to promote it.

Exploring Factors for Predicting Anxiety Disorders of the Elderly Living Alone in South Korea Using Interpretable Machine Learning: A Population-Based Study

This epidemiological study aimed to develop an X-AI that could explain groups with a high anxiety disorder risk in old age. To achieve this objective, (1) this study explored the predictors of senile anxiety using base models and meta models. (2) This study presented decision tree visualization that could help psychiatric consultants and primary physicians easily interpret the path of predicting high-risk groups based on major predictors derived from final machine learning models with the best performance. This study analyzed 1558 elderly (695 males and 863 females) who were 60 years or older and completed the Zung’s Self-Rating Anxiety Scale (SAS). We used support vector machine (SVM), random forest, LightGBM, and Adaboost for the base model, a single predictive model, while using XGBoost algorithm for the meta model. The analysis results confirmed that the predictive performance of the “SVM + Random forest + LightGBM + AdaBoost + XGBoost model (stacking ensemble: accuracy 87.4%, precision 85.1%, recall 87.4%, and F1-score 85.5%)” was the best. Also, the results of this study showed that the elderly who often (or mostly) felt subjective loneliness, had a Self Esteem Scale score of 26 or less, and had a subjective communication with their family of 4 or less (on a 10-point scale) were the group with the highest risk anxiety disorder. The results of this study imply that it is necessary to establish a community-based mental health policy that can identify elderly groups with high anxiety risks based on multiple risk factors and manage them constantly.

Eating Alone or Together among Community-Living Older People-A Scoping Review

Research on healthy aging commonly concerns problems related to loneliness and food intake. These are not independent aspects of health since eating, beyond its biological necessity, is a central part of social life. This scoping review aimed to map scientific articles on eating alone or together among community-living older people, and to identify relevant research gaps. Four databases were searched, 989 articles were identified and 98 fulfilled the inclusion criteria. In the first theme, eating alone or together are treated as central topics of interest, isolated from adjoining, broader concepts such as social participation. In the second, eating alone or together are one aspect of the findings, e.g., one of several risk factors for malnutrition. Findings confirm the significance of commensality in older peoples' life. We recommend future research designs allowing identification of causal relationships, using refined ways of measuring meals alone or together, and qualitative methods adding complexity.

Prevalence of swallowing difficulties in older people without neurological disorders: Swallowing profile of older people in the city of Santos, Brazil

Several studies report that 40% to 60% of older people have some difficulty chewing and/or swallowing, which can lead to malnutrition, dehydration, weight loss, a lack of eating desire, etc. Identify older adults with swallowing difficulties in the city of Santos, Brazil, among users of the public healthcare system. A cross-sectional study was conducted with 100 individuals aged 60 to 90 years with no neurological disorders. Patient histories were taken, and stomatognathic evaluations were performed. The Mini Mental Health Examination (MMHE) and swallowing-related quality-of-life questionnaire (SWAL-QOL) were administered. The clinical swallowing assessment was performed with liquid, pasty and solid foods using two assessment protocols (Dysphagia Risk Evaluation Protocol and the Protocol for the Introduction and Transition of Foods)'. We found complaints of poorly adapted dentures among 49.3% of denture wearers and a high prevalence of hypofunction of oro-facial muscles. Sixty-five per cent of the respondents had facial muscle hypofunction, 51% exhibited lip hypofunction, and 49% exhibited tongue hypofunction. Moreover, 54% reported difficulty swallowing. On the SWAL-QOL questionnaire, 37% reported choking when eating food, 44% reported choking when drinking liquids, 29% reported coughing during meals, and 77% reported difficulty chewing. The present study revealed an important prevalence of complaints related to swallowing difficulties among older people in the city of Santos with structural and physiological changes characteristic of presbyphagia. The most prevalent conditions were poorly adapted dentures and hypofunction of oro-facial muscles, underscoring the importance of stomatognathic interventions in primary care.

Analysis of Quality of Life and Nutritional Status in Elderly Patients with Dysphagia in Order to Prevent Hospital Admissions in a COVID-19 Pandemic

(1) Background: Oropharyngeal dysphagia (OD) is currently recognized as one of the geriatric syndromes due to its high frequency in older people and its associated complications, which have a direct impact on quality of life. The main objective is to determine the effectiveness of telehealth consultation for the re-evaluation of nutritional status and quality of life assessment in older people diagnosed with OD associated with active use of thickeners to prevent hospital admissions in a COVID-19 pandemic. (2) Methods: an observational, descriptive, and longitudinal study that included a sample of 33 subjects with age equal or superior to 65 years diagnosed with OD with conserved cognitive capacity. The nutritional status was evaluated through the Mini-Nutritional Assessment (MNA) questionnaire and biochemical parameters and, the quality of life was determined through the Swallowing Quality of Life (SWAL-QOL) questionnaire. (3) Results: Thirty-three older patients with OD were recruited (54.5% women), with a mean age of 83.5 ± 7.6 years. The main cause of OD in the study population was neurodegenerative disease (51.5%), followed by cerebrovascular disease (33.3%), and other causes (15.2%). Sixty point six percent of patients were found to be at risk of malnutrition. The MNA score was significantly correlated to albumin (r: 0.600, p < 0.001) and total proteins (r: 0.435, p = 0.015), but not to total cholesterol (r: -0.116, p = 0.534) or lymphocytes (r: -0.056, p = 0.758). The mean total score of the SWAL-QOL was 75.1 ± 16.4 points. (4) Conclusions: the quality of life of the subjects related to the use of a thickener is good. Although the body mass index (BMI) and average biochemical, nutritional parameters of the subjects are within the range of normality, the MNA has detected a high percentage of subjects with the risk of malnutrition, which suggests the need for continuous re-evaluation in these patients, demonstrating the viability of the telematic route in this research.

Development of a depression in Parkinson's disease prediction model using machine learning

BACKGROUND

It is important to diagnose depression in Parkinson’s disease (DPD) as soon as possible and identify the predictors of depression to improve quality of life in Parkinson’s disease (PD) patients.

AIM

To develop a model for predicting DPD based on the support vector machine, while considering sociodemographic factors, health habits, Parkinson's symptoms, sleep behavior disorders, and neuropsychiatric indicators as predictors and provide baseline data for identifying DPD.

METHODS

This study analyzed 223 of 335 patients who were 60 years or older with PD. Depression was measured using the 30 items of the Geriatric Depression Scale, and the explanatory variables included PD-related motor signs, rapid eye movement sleep behavior disorders, and neuropsychological tests. The support vector machine was used to develop a DPD prediction model.

RESULTS

When the effects of PD motor symptoms were compared using “functional weight”, late motor complications (occurrence of levodopa-induced dyskinesia) were the most influential risk factors for Parkinson's symptoms.

CONCLUSION

It is necessary to develop customized screening tests that can detect DPD in the early stage and continuously monitor high-risk groups based on the factors related to DPD derived from this predictive model in order to maintain the emotional health of PD patients.

Effect of Neuromuscular Electrical Stimulation on Masseter Muscle Thickness and Maximal Bite Force Among Healthy Community-Dwelling Persons Aged 65 Years and Older: A Randomized, Double Blind, Placebo-Controlled Study

Aim: This study investigated the effect of neuromuscular electrical stimulation (NMES) on masseter muscle thickness and maximal bite force among healthy community-dwelling elderly persons older than 65 years. Materials and methods: A total of 40 participants were randomly assigned to the experimental and placebo groups. In the experimental group, NMES was applied to both masseter muscles, and electrical signals were gradually increased until the participants felt a grabbing sensation (range 6.0–7.5 mA) in the masseter muscle. The placebo group, in contrast, underwent NMES in the same manner and procedure as the experimental group with less electrical intensity (0.5 mA). All interventions were administered five times a week for six weeks, 20 min per day. The outcomes were masseter muscle thickness assessed using ultrasound and maximal bite force using a bite force meter. The level of significance was set as p < 0.05. Results: The experimental group showed a significant increase in both masseter muscle thickness and maximal bite force as compared with the placebo group (p = 0.002 and 0.019, respectively). Moreover, the degree of change in the masseter muscle thickness and maximal bite force significantly increased in the experimental and placebo groups (p < 0.001, both). Conclusions: This study demonstrated that NMES could be an effective modality for increasing masseter muscle thickness and maximal bite force in healthy older adults.

Application of Machine Learning Technique to Distinguish Parkinson's Disease Dementia and Alzheimer's Dementia: Predictive Power of Parkinson's Disease-Related Non-Motor Symptoms and Neuropsychological Profile

In order to develop a predictive model that can distinguish Parkinson’s disease dementia (PDD) from other dementia types, such as Alzheimer’s dementia (AD), it is necessary to evaluate and identify the predictive accuracy of the cognitive profile while considering the non-motor symptoms, such as depression and rapid eye movement (REM) sleep behavior disorders. This study compared Parkinson’s disease (PD)’s non-motor symptoms and the diagnostic predictive power of cognitive profiles that distinguish AD and PD using machine learning. This study analyzed 118 patients with AD and 110 patients with PDD, and all subjects were 60 years or older. In order to develop the PDD prediction model, the dataset was divided into training data (70%) and test data (30%). The prediction accuracy of the model was calculated by the recognition rate. The results of this study show that Parkinson-related non-motor symptoms, such as REM sleep behavior disorders, and cognitive screening tests, such as Korean version of Montreal Cognitive Assessment, were highly accurate factors for predicting PDD. It is required to develop customized screening tests that can detect PDD in the early stage based on these results. Furthermore, it is believed that including biomarkers such as brain images or cerebrospinal fluid as input variables will be more useful for developing PDD prediction models in the future.

Is the Random Forest Algorithm Suitable for Predicting Parkinson's Disease with Mild Cognitive Impairment out of Parkinson's Disease with Normal Cognition?

Because it is possible to delay the progression of dementia if it is detected and treated in an early stage, identifying mild cognitive impairment (MCI) is an important primary goal of dementia treatment. The objectives of this study were to develop a random forest-based Parkinson's disease with mild cognitive impairment (PD-MCI) prediction model considering health behaviors, environmental factors, medical history, physical functions, depression, and cognitive functions using the Parkinson's Dementia Clinical Epidemiology Data (a national survey conducted by the Korea Centers for Disease Control and Prevention) and to compare the prediction accuracy of our model with those of decision tree and multiple logistic regression models. We analyzed 96 subjects (PD-MCI = 45; Parkinson's disease with normal cognition (PD-NC) = 51 subjects). The prediction accuracy of the model was calculated using the overall accuracy, sensitivity, and specificity. Based on the random forest analysis, the major risk factors of PD-MCI were, in descending order of magnitude, Clinical Dementia Rating (CDR) sum of boxes, Untitled Parkinson's Disease Rating (UPDRS) motor score, the Korean Mini Mental State Examination (K-MMSE) total score, and the K- Korean Montreal Cognitive Assessment (K-MoCA) total score. The random forest method achieved a higher sensitivity than the decision tree model. Thus, it is advisable to develop a protocol to easily identify early stage PDD based on the PD-MCI prediction model developed in this study, in order to establish individualized monitoring to track high-risk groups.