scholarly journals Machine Learning-Based Predictive Models of Behavioral and Psychological Symptoms of Dementia

2021 ◽  
Vol 5 (Supplement_1) ◽  
pp. 648-648
Author(s):  
Eunhee Cho ◽  
Sujin Kim ◽  
Seok-Jae Heo ◽  
Jinhee Shin ◽  
Byoung Seok Ye ◽  
...  
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Test Data ◽  
Predictive Models ◽  
Psychological Symptoms ◽  
Community Dwelling ◽  
Categorical Variables ◽  
Support Vector ◽  
Individualized Care ◽  
Behavioral And Psychological Symptoms

Abstract Models predicting the occurrence of specific types of behavioral and psychological symptoms of dementia (BPSD) can be highly beneficial for its early intervention and individualized care planning. Using a machine learning approach, this study developed and validated predictive models of the occurrence of BPSD, categorized into seven subsyndromes, among community-dwelling older adults with dementia in South Korea. BPSD dairy was used to measure BPSD and the state of unmet needs daily. We measured sleep and activity levels using actigraphy, and stress and fatigue using a portable heart rate variability analyzer. We developed predictive models and conducted cross-validation using training data that consisted of the first two wave dataset, and then validated the models using wave 3 test data. To deal with imbalanced datasets, we used Synthetic Minority Oversampling Technique (SMOTE), an over-sampling method. Categorical variables were pre-processed using target encoding. We then compared the machine-learning models with logistic regression. The area under the receiver operating characteristic curve (AUC) scores of the support vector machine (SVM) models for the wave 3 test data showed a similar or greater value than logistic regression models across all BPSD subsyndromes. The SVM model (AUC = 0.899) had an AUC value greater than that of the logistic regression model (AUC = 0.717), particularly for hyperactivity symptoms. Machine learning algorithms, especially SVM models, can be used to develop BPSD prediction models to help identify at-risk individuals and implement symptom-targeted individualized interventions.

scholarly journals The impact of lockdown during SARS-CoV-2 outbreak on behavioral and psychological symptoms of dementia

2021 ◽  
Vol 42 (3) ◽  
pp. 825-833
Author(s):  
Arianna Manini ◽  
Michela Brambilla ◽  
Laura Maggiore ◽  
Simone Pomati ◽  
Leonardo Pantoni
Keyword(s):  
Logistic Regression ◽  
Psychological Symptoms ◽  
Neuropsychiatric Symptoms ◽  
Community Dwelling ◽  
Caregiver Distress ◽  
Neuropsychiatric Inventory ◽  
Logistic Regression Models ◽  
The Impact ◽  
Behavioral And Psychological Symptoms

Abstract Background During Covid-19 pandemic, the Italian government adopted restrictive limitations and declared a national lockdown on March 9, which lasted until May 4 and produced dramatic consequences on people’s lives. The aim of our study was to assess the impact of prolonged lockdown on behavioral and psychological symptoms of dementia (BPSD). Methods Between April 30 and June 8, 2020, we interviewed with a telephone-based questionnaire the caregivers of the community-dwelling patients with dementia who had their follow-up visit scheduled from March 9 to May 15 and canceled due to lockdown. Among the information collected, patients’ BPSDs were assessed by the Neuropsychiatric Inventory (NPI). Non-parametric tests to compare differences between NPI scores over time and logistic regression models to explore the impact of different factors on BPSD worsening were performed. Results A total of 109 visits were canceled and 94/109 caregivers completed the interview. Apathy, irritability, agitation and aggression, and depression were the most common neuropsychiatric symptoms experienced by patients both at baseline and during Covid-19 pandemic. Changes in total NPI and caregiver distress scores between baseline and during lockdown, although statistically significant, were overall modest. The logistic regression model failed to determine predictors of BPSD worsening during lockdown. Conclusion This is one of the first studies to investigate the presence of BPSD during SARS-CoV-2 outbreak and related nationwide lockdown, showing only slight, likely not clinically relevant, differences in BPSD burden, concerning mostly agitation and aggression, anxiety, apathy and indifference, and irritability.

scholarly journals Structural Health Monitoring Using Machine Learning and Cumulative Absolute Velocity Features

2021 ◽  
Vol 11 (12) ◽  
pp. 5727
Author(s):  
Sifat Muin ◽  
Khalid M. Mosalam
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Structural Health Monitoring ◽  
Health Monitoring ◽  
Degree Of Freedom ◽  
Absolute Velocity ◽  
Support Vector ◽  
Damage State ◽  
Structural Health ◽  
Cumulative Absolute Velocity

Machine learning (ML)-aided structural health monitoring (SHM) can rapidly evaluate the safety and integrity of the aging infrastructure following an earthquake. The conventional damage features used in ML-based SHM methodologies face the curse of dimensionality. This paper introduces low dimensional, namely, cumulative absolute velocity (CAV)-based features, to enable the use of ML for rapid damage assessment. A computer experiment is performed to identify the appropriate features and the ML algorithm using data from a simulated single-degree-of-freedom system. A comparative analysis of five ML models (logistic regression (LR), ordinal logistic regression (OLR), artificial neural networks with 10 and 100 neurons (ANN10 and ANN100), and support vector machines (SVM)) is performed. Two test sets were used where Set-1 originated from the same distribution as the training set and Set-2 came from a different distribution. The results showed that the combination of the CAV and the relative CAV with respect to the linear response, i.e., RCAV, performed the best among the different feature combinations. Among the ML models, OLR showed good generalization capabilities when compared to SVM and ANN models. Subsequently, OLR is successfully applied to assess the damage of two numerical multi-degree of freedom (MDOF) models and an instrumented building with CAV and RCAV as features. For the MDOF models, the damage state was identified with accuracy ranging from 84% to 97% and the damage location was identified with accuracy ranging from 93% to 97.5%. The features and the OLR models successfully captured the damage information for the instrumented structure as well. The proposed methodology is capable of ensuring rapid decision-making and improving community resiliency.

scholarly journals The Holistic Impact of Using Arts-Based Intervention for Elderly With Dementia

2020 ◽  
Vol 4 (Supplement_1) ◽  
pp. 567-567
Author(s):  
Rainbow Tin Hun Ho
Keyword(s):  
Motor Behavior ◽  
Psychological Symptoms ◽  
Controlled Trial ◽  
Negative Mood ◽  
Community Dwelling ◽  
Creative Arts ◽  
Dance Movement ◽  
Moderate Dementia ◽  
Practical Experiences ◽  
Behavioral And Psychological Symptoms

Abstract The use of creative arts on supporting elderly with dementia has been becoming popular due to its safe and engaging process. This non-pharmacological approach can complement with other treatment methods to support elderly with dementia on various aspects, including physical, cognitive and social functioning. In our randomized controlled trial on dance movement therapy (DMT) for 204 community dwelling elders with mild dementia, we found DMT could significantly reduce the level of depression, loneliness and negative mood (β=0.33-0.42, p<.01), and also the diurnal cortisol slope (β =0.30, p<.01); while in another trial on 73 elderly with moderate dementia, we found music and movement could help reduce the behavioral and psychological symptoms such as agitation (β = -0.41, p<.01), aberrant motor behavior (β=-1.02, p<.01), and dysphonia (β=-0.61, p<.05). The present presentation aims to share with the audience our practical experiences, the research procedures as well as the findings of the projects.

scholarly journals Rationale, Design, and Methodology of a Prospective Cohort Study for Coping with Behavioral and Psychological Symptoms of Dementia: The RECage Project

2021 ◽  
Vol 80 (4) ◽  
pp. 1613-1627
Author(s):  
Eleni Poptsi ◽  
Magda Tsolaki ◽  
Sverre Bergh ◽  
Bruno Mario Cesana ◽  
Alfonso Ciccone ◽  
...  
Keyword(s):  
Cohort Study ◽  
Psychotropic Drug ◽  
Psychological Symptoms ◽  
Cost Of Care ◽  
Community Dwelling ◽  
Drug Consumption ◽  
Study Results ◽  
Short And Long Term ◽  
Behavioral And Psychological Symptoms

Background: Behavioral and psychological symptoms of dementia (BPSD) are quite challenging problems during the dementia course. Special Care Units for people with dementia (PwD) and BPSD (SCU-B) are residential medical structures, where BPSD patients are temporarily admitted, in case of unmanageable behavioral disturbances at home. Objective: RECage (REspectful Caring for AGitated Elderly) aspires to assess the short and long-term effectiveness of SCU-Bs toward alleviating BPSD and improving the quality of life (QoL) of PwD and their caregivers. Methods: RECage is a three-year, prospective study enrolling 500 PwD. Particularly, 250 community-dwelling PwDs presenting with severe BPSD will be recruited by five clinical centers across Europe, endowed with a SCU-B, for a short period of time; a second similar group of 250 PwD will be followed by six other no-SCU-B centers solely via outpatient visits. RECage’s endpoints include short and long-term SCU-B clinical efficacy, QoL of patients and caregivers, cost-effectiveness of the SCU-B, psychotropic drug consumption, caregivers’ attitude toward dementia, and time to nursing home placement. Results: PwD admitted in SCU-Bs are expected to have diminished rates of BPSD and better QoL and their caregivers are also expected to have better QoL and improved attitude towards dementia, compared to those followed in no-SCU-Bs. Also, the cost of care and the psychotropic drug consumption are expected to be lower. Finally, PwD followed in no-SCU-Bs are expected to have earlier admission to nursing homes. Conclusion: The cohort study results will refine the SCU-B model, issuing recommendations for implementation of SCU-Bs in the countries where they are scarce or non-existent.

Detecting Face Touching Using Smartwatches to Mitigate the Spread of COVID-19: Pilot Study (Preprint)

2021 ◽  
Author(s):  
Chen Bai ◽  
Yu-Peng Chen ◽  
Adam Wolach ◽  
Lisa Anthony ◽  
Mamoun Mardini
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Respiratory Diseases ◽  
Window Size ◽  
Support Vector ◽  
Accelerometer Data ◽  
Respiratory Illnesses ◽  
Motion Data ◽  
Machine Learning Methods

BACKGROUND Frequent spontaneous facial self-touches, predominantly during outbreaks, have the theoretical potential to be a mechanism of contracting and transmitting diseases. Despite the recent advent of vaccines, behavioral approaches remain an integral part of reducing the spread of COVID-19 and other respiratory illnesses. Real-time biofeedback of face touching can potentially mitigate the spread of respiratory diseases. The gap addressed in this study is the lack of an on-demand platform that utilizes motion data from smartwatches to accurately detect face touching. OBJECTIVE The aim of this study was to utilize the functionality and the spread of smartwatches to develop a smartwatch application to identifying motion signatures that are mapped accurately to face touching. METHODS Participants (n=10, 50% women, aged 20-83) performed 10 physical activities classified into: face touching (FT) and non-face touching (NFT) categories, in a standardized laboratory setting. We developed a smartwatch application on Samsung Galaxy Watch to collect raw accelerometer data from participants. Then, data features were extracted from consecutive non-overlapping windows varying from 2-16 seconds. We examined the performance of state-of-the-art machine learning methods on face touching movements recognition (FT vs NFT) and individual activity recognition (IAR): logistic regression, support vector machine, decision trees and random forest. RESULTS Machine learning models were accurate in recognizing face touching categories; logistic regression achieved the best performance across all metrics (Accuracy: 0.93 +/- 0.08, Recall: 0.89 +/- 0.16, Precision: 0.93 +/- 0.08, F1-score: 0.90 +/- 0.11, AUC: 0.95 +/- 0.07) at the window size of 5 seconds. IAR models resulted in lower performance; the random forest classifier achieved the best performance across all metrics (Accuracy: 0.70 +/- 0.14, Recall: 0.70 +/- 0.14, Precision: 0.70 +/- 0.16, F1-score: 0.67 +/- 0.15) at the window size of 9 seconds. CONCLUSIONS Wearable devices, powered with machine learning, are effective in detecting facial touches. This is highly significant during respiratory infection outbreaks, as it has a great potential to refrain people from touching their faces and potentially mitigate the possibility of transmitting COVID-19 and future respiratory diseases.

Abstract TP458: High Accuracy of Predictive Models for SAH Using Different Machine Learning Approaches

Stroke ◽  
2020 ◽  
Vol 51 (Suppl_1) ◽  
Author(s):  
Paul Litvak ◽  
Jeevan Medikonda ◽  
Girish Menon ◽  
Pitchaiah Mandava
Keyword(s):  
Machine Learning ◽  
Predictive Models ◽  
Prediction Accuracy ◽  
Support Vector ◽  
World Federation ◽  
Learning Approaches ◽  
Flow Models ◽  
Multi Stage ◽  
Stage 1 ◽  
Categorical Scale

Background: Patients suffering from subarachnoid hemorrhage (SAH) have poor long-term outcomes. There are predictive models for ischemic and hemorrhagic stroke. However, there is paucity of models for SAH. Machine learning concepts were applied to build multi-stage Neural Networks (NN), Support Vector Machines (SVM) and Keras/Tensor Flow models to predict SAH outcomes. Methods: A database of ~800 aneurysmal SAH patients from Kasturba Medical College was utilized. Baseline variables of World Federation of Neurosurgeons 5-point scale (WFNS 1-5), age, gender, and presence/absence of hypertension and diabetes were considered in Stage 1. Stage 2 included all Stage 1 variables along with presence/absence of radiologic signs vasospasm and ischemia. Stage 3 includes earlier 2 stages and discharge Glasgow Outcome Scale (GOS 1-5). GOS at 3 months was predicted using 2-layer NN/SVM/Keras-TensorFlow models on the five point categorical scale as well as dichotomized to dead/alive and favorable (GOS 4-5) or unfavorable (GOS 1-3). Prediction accuracy of models was compared to the recorded GOS. Results: Prediction accuracy shown as percentages (See Table) for all three stages was similar for SVM, NN and Keras/TensorFlow models. Accuracy was remarkably higher with dichotomization compared to the complete five point GOS categorical scale. Conclusions: SVM, NN, and Keras-TensorFlow based machine learning models can be used to predict SAH outcomes to a high degree of accuracy. These powerful predictive models can be used to prognosticate and select patients into trials.

scholarly journals A Framework for Effective Application of Machine Learning to Microbiome-Based Classification Problems

mBio ◽  
2020 ◽  
Vol 11 (3) ◽  
Author(s):  
Begüm D. Topçuoğlu ◽  
Nicholas A. Lesniak ◽  
Mack T. Ruffin ◽  
Jenna Wiens ◽  
Patrick D. Schloss
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Random Forest ◽  
Sequence Data ◽  
Characteristic Curve ◽  
Predictive Performance ◽  
Model Complexity ◽  
Support Vector ◽  
Classification Problems ◽  
Microbial Biomarkers

ABSTRACT Machine learning (ML) modeling of the human microbiome has the potential to identify microbial biomarkers and aid in the diagnosis of many diseases such as inflammatory bowel disease, diabetes, and colorectal cancer. Progress has been made toward developing ML models that predict health outcomes using bacterial abundances, but inconsistent adoption of training and evaluation methods call the validity of these models into question. Furthermore, there appears to be a preference by many researchers to favor increased model complexity over interpretability. To overcome these challenges, we trained seven models that used fecal 16S rRNA sequence data to predict the presence of colonic screen relevant neoplasias (SRNs) (n = 490 patients, 261 controls and 229 cases). We developed a reusable open-source pipeline to train, validate, and interpret ML models. To show the effect of model selection, we assessed the predictive performance, interpretability, and training time of L2-regularized logistic regression, L1- and L2-regularized support vector machines (SVM) with linear and radial basis function kernels, a decision tree, random forest, and gradient boosted trees (XGBoost). The random forest model performed best at detecting SRNs with an area under the receiver operating characteristic curve (AUROC) of 0.695 (interquartile range [IQR], 0.651 to 0.739) but was slow to train (83.2 h) and not inherently interpretable. Despite its simplicity, L2-regularized logistic regression followed random forest in predictive performance with an AUROC of 0.680 (IQR, 0.625 to 0.735), trained faster (12 min), and was inherently interpretable. Our analysis highlights the importance of choosing an ML approach based on the goal of the study, as the choice will inform expectations of performance and interpretability. IMPORTANCE Diagnosing diseases using machine learning (ML) is rapidly being adopted in microbiome studies. However, the estimated performance associated with these models is likely overoptimistic. Moreover, there is a trend toward using black box models without a discussion of the difficulty of interpreting such models when trying to identify microbial biomarkers of disease. This work represents a step toward developing more-reproducible ML practices in applying ML to microbiome research. We implement a rigorous pipeline and emphasize the importance of selecting ML models that reflect the goal of the study. These concepts are not particular to the study of human health but can also be applied to environmental microbiology studies.

scholarly journals Evaluation of Prognosis in Nasopharyngeal Cancer Using Machine Learning

2020 ◽  
Vol 19 ◽  
pp. 153303382090982
Author(s):  
Melek Akcay ◽  
Durmus Etiz ◽  
Ozer Celik ◽  
Alaattin Ozen
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Naive Bayes ◽  
Nasopharyngeal Cancer ◽  
Naïve Bayes ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Tumor Diameter ◽  
Survival Prognosis ◽  
Data Set

Background and Aim: Although the prognosis of nasopharyngeal cancer largely depends on a classification based on the tumor-lymph node metastasis staging system, patients at the same stage may have different clinical outcomes. This study aimed to evaluate the survival prognosis of nasopharyngeal cancer using machine learning. Settings and Design: Original, retrospective. Materials and Methods: A total of 72 patients with a diagnosis of nasopharyngeal cancer who received radiotherapy ± chemotherapy were included in the study. The contribution of patient, tumor, and treatment characteristics to the survival prognosis was evaluated by machine learning using the following techniques: logistic regression, artificial neural network, XGBoost, support-vector clustering, random forest, and Gaussian Naive Bayes. Results: In the analysis of the data set, correlation analysis, and binary logistic regression analyses were applied. Of the 18 independent variables, 10 were found to be effective in predicting nasopharyngeal cancer-related mortality: age, weight loss, initial neutrophil/lymphocyte ratio, initial lactate dehydrogenase, initial hemoglobin, radiotherapy duration, tumor diameter, number of concurrent chemotherapy cycles, and T and N stages. Gaussian Naive Bayes was determined as the best algorithm to evaluate the prognosis of machine learning techniques (accuracy rate: 88%, area under the curve score: 0.91, confidence interval: 0.68-1, sensitivity: 75%, specificity: 100%). Conclusion: Many factors affect prognosis in cancer, and machine learning algorithms can be used to determine which factors have a greater effect on survival prognosis, which then allows further research into these factors. In the current study, Gaussian Naive Bayes was identified as the best algorithm for the evaluation of prognosis of nasopharyngeal cancer.

scholarly journals Association between Daily Activities and Behavioral and Psychological Symptoms of Dementia in Community-Dwelling Older Adults with Memory Complaints by Their Families

2020 ◽  
Vol 17 (18) ◽  
pp. 6831 ◽  
Author(s):  
Yuriko Ikeda ◽  
Gwanghee Han ◽  
Michio Maruta ◽  
Maki Hotta ◽  
Eri Ueno ◽  
...  
Keyword(s):  
Psychological Symptoms ◽  
Process Analysis ◽  
Family Members ◽  
Community Dwelling ◽  
Stepwise Multiple Regression ◽  
Short Version ◽  
Memory Complaints ◽  
Behavior Disturbance ◽  
With Memory ◽  
Behavioral And Psychological Symptoms

It is important and useful to consider information provided by family members about individuals with memory complaints’ instrumental activities of daily living (IADL). The purpose of this study was to clarify the characteristics and relevance of individuals with memory complaints’ IADL and behavioral and psychological symptoms of dementia (BPSD) assessed from the perspective of the family members using the Process Analysis of Daily Activity for Dementia and short version Dementia Behavior Disturbance scale. A self-administered questionnaire was sent to 2000 randomly selected members of Consumer’s Co-operative Kagoshima, and 621 responded. Of the returned responses, there were 159 participants who answered about individuals with memory complaints. The stepwise multiple regression analysis was used to examine the association between IADL and BPSD. The result showed that many IADL of the individuals with memory complaints were associated with BPSD of apathy, nocturnal wakefulness, and unwarranted accusations, adjusted for age, gender, and the observation list for early signs of dementia. In addition, each IADL was associated with BPSD of apathy, nocturnal wakefulness, and dresses inappropriately. Modifying lifestyle early on when families recognize these changes may help maintain and improve the long-term quality of life of the individuals with memory complaints and their family.

Sign in / Sign up

Export Citation Format

Share Document