Introduction: Dementia is a condition (a collection of related signs and symptoms) that causes a continuing deterioration in cognitive function, and millions of people are impacted by dementia every year as the world population continues to rise. Conventional approaches for determining dementia rely primarily on clinical examinations, analyzing medical records, and administering cognitive and neuropsychological testing. However, these methods are time-consuming and costly in terms of treatment. Therefore, this study aims to present a noninvasive method for the early prediction of dementia so that preventive steps should be taken to avoid dementia.

Methods: We developed a hybrid diagnostic system based on statistical and machine learning (ML) methods that used patient electronic health records to predict dementia. The dataset used for this study was obtained from the Swedish National Study on Aging and Care (SNAC), with a sample size of 43040 and 75 features. The newly constructed diagnostic extracts a subset of useful features from the dataset through a statistical method (F-score). For the classification, we developed an ensemble voting classifier based on five different ML models: decision tree (DT), naive Bayes (NB), logistic regression (LR), support vector machines (SVM), and random forest (RF). To address the problem of ML model overfitting, we used a cross-validation approach to evaluate the performance of the proposed diagnostic system. Various assessment measures, such as accuracy, sensitivity, specificity, receiver operating characteristic (ROC) curve, and Matthew’s correlation coefficient (MCC), were used to thoroughly validate the devised diagnostic system’s efficiency.

Results: According to the experimental results, the proposed diagnostic method achieved the best accuracy of 98.25%, as well as sensitivity of 97.44%, specificity of 95.744%, and MCC of 0.7535.

Discussion: The effectiveness of the proposed diagnostic approach is compared to various cutting-edge feature selection techniques and baseline ML models. From experimental results, it is evident that the proposed diagnostic system outperformed the prior feature selection strategies and baseline ML models regarding accuracy.

Background

Chronic obstructive pulmonary disease (COPD) is a severe condition affecting millions worldwide, leading to numerous annual deaths. The absence of significant symptoms in its early stages promotes high underdiagnosis rates for the affected people. Besides pulmonary function failure, another harmful problem of COPD is the systematical effects, e.g., heart failure or voice distortion. However, the systematic effects of COPD might provide valuable information for early detection. In other words, symptoms caused by systematic effects could be helpful to detect the condition in its early stages.

Objective

The proposed study aims to explore whether the voice features extracted from the vowel “a” utterance carry any information that can be predictive of COPD by employing Machine Learning (ML) on a newly collected voice dataset.

Methods

Forty-eight participants were recruited from the pool of research clinic visitors at Blekinge Institute of Technology (BTH) in Sweden between January 2022 and May 2023. A dataset consisting of 1246 recordings from 48 participants was gathered. The collection of voice recordings containing the vowel “a” utterance commenced following an information and consent meeting with each participant using the VoiceDiagnostic application. The collected voice data was subjected to silence segment removal, feature extraction of baseline acoustic features, and Mel Frequency Cepstrum Coefficients (MFCC). Sociodemographic data was also collected from the participants. Three ML models were investigated for the binary classification of COPD and healthy controls: Random Forest (RF), Support Vector Machine (SVM), and CatBoost (CB). A nested k-fold cross-validation approach was employed. Additionally, the hyperparameters were optimized using grid-search on each ML model. For best performance assessment, accuracy, F1-score, precision, and recall metrics were computed. Afterward, we further examined the best classifier by utilizing the Area Under the Curve (AUC), Average Precision (AP), and SHapley Additive exPlanations (SHAP) feature-importance measures.

Results

The classifiers RF, SVM, and CB achieved a maximum accuracy of 77 %, 69 %, and 78 % on the test set and 93 %, 78 % and 97 % on the validation set, respectively. The CB classifier outperformed RF and SVM. After further investigation of the best-performing classifier, CB demonstrated the highest performance, producing an AUC of 82 % and AP of 76 %. In addition to age and gender, the mean values of baseline acoustic and MFCC features demonstrate high importance and deterministic characteristics for classification performance in both test and validation sets, though in varied order.

Conclusion

This study concludes that the utterance of vowel “a” recordings contain information that can be captured by the CatBoost classifier with high accuracy for the classification of COPD. Additionally, baseline acoustic and MFCC features, in conjunction with age and gender information, can be employed for classification purposes and benefit healthcare for decision support in COPD diagnosis.

This contribution corrects cost data from our previously published version in which the 6-month cost data was not censored at baseline and 6-month survey dates. Consequently, the average costs for persons with mild cognitive impairment (PwMCI) and their informal caregivers include costs that occurred outside the initial 6-month period for both intervention and control groups. In this erratum, we have repeated the analysis after appropriately censoring the costs. The results led to numerical differences. However, as both the intervention and control groups have been treated exactly the same, the differences between groups remain insignificant and the general interpretation of the results stand as presented in the original publication. The interpretation of the results in terms of cost-effectiveness has changed for informal caregivers, shifting from "dominant" to "not cost-effective", and for dyads, shifting from "less costly and less effective" to "more costly and less effective". Consequently, ICER and CEAC curves have also changed (see Corrected Fig. 1). However, these changes did not affect the conclusion of the article. 

Background: The growing presence of digital technologies in health care requires the health workforce to have proficiency in subjects such as informatics. This has implications in the education of nursing students, as their preparedness to use these technologies in clinical situations is something that course administrators need to consider. Thus, students’ attitudes toward technology could be investigated to assess their needs regarding this proficiency.

Objective: This study aims to investigate attitudes (enthusiasm and anxiety) toward technology among nursing students and to identify factors associated with those attitudes. Methods: Nursing students at 2 universities in Sweden and 1 university in Poland were invited to answer a questionnaire. Data about attitudes (anxiety and enthusiasm) toward technology, eHealth literacy, electronic device skills, and frequency of using electronic devices and sociodemographic data were collected. Descriptive statistics were used to characterize the data. The Spearman rank correlation coefficient and Mann-Whitney U test were used for statistical inferences.

Results: In total, 646 students answered the questionnaire—342 (52.9%) from the Swedish sites and 304 (47.1%) from the Polish site. It was observed that the students’ technology enthusiasm (techEnthusiasm) was on the higher end of the Technophilia instrument (score range 1-5): 3.83 (SD 0.90), 3.62 (SD 0.94), and 4.04 (SD 0.78) for the whole sample, Swedish students, and Polish students, respectively. Technology anxiety (techAnxiety) was on the midrange of the Technophilia instrument: 2.48 (SD 0.96), 2.37 (SD 1), and 2.60 (SD 0.89) for the whole sample, Swedish students, and Polish students, respectively. Regarding techEnthusiasm among the nursing students, a negative correlation with age was found for the Swedish sample (P<.001; ρSwedish=−0.201) who were generally older than the Polish sample, and positive correlations with the eHealth Literacy Scale score (P<.001; ρall=0.265; ρSwedish=0.190; ρPolish=0.352) and with the perceived skill in using computer devices (P<.001; ρall=0.360; ρSwedish=0.341; ρPolish=0.309) were found for the Swedish, Polish, and total samples. Regarding techAnxiety among the nursing students, a positive correlation with age was found in the Swedish sample (P<.001; ρSwedish=0.184), and negative correlations with eHealth Literacy Scale score (P<.001; ρall=−0.196; ρSwedish=−0.262; ρPolish=−0.133) and with the perceived skill in using computer devices (P<.001; ρall=−0.209; ρSwedish=−0.347; ρPolish=−0.134) were found for the Swedish, Polish, and total samples and with the semester only for the Swedish sample (P<.001; ρSwedish=−0.124). Gender differences were found regarding techAnxiety in the Swedish sample, with women exhibiting a higher mean score than men (2.451, SD 1.014 and 1.987, SD 0.854, respectively).

Conclusions: This study highlights nursing students’ techEnthusiasm and techAnxiety, emphasizing correlations with various factors. With health care’s increasing reliance on technology, integrating health technology–related topics into education is crucial for future professionals to address health care challenges effectively.

©Ana Luiza Dallora, Ewa Kazimiera Andersson, Bruna Gregory Palm, Doris Bohman, Gunilla Björling, Ludmiła Marcinowicz, Louise Stjernberg, Peter Anderberg.

Inadequate sleep in older adults is linked to health issues such as frailty, cognitive impairment, and cardiovascular disorders. Maintaining regular sleep patterns is important for healthy aging, making effective sleep monitoring essential. While polysomnography (PSG) is the gold standard for diagnosing sleep disorders, its regular use in home settings is limited. Alternative objective monitoring methods in the home can offer insights into natural sleep patterns and factors affecting them without the limitations of PSG.

This scoping review aims to examine current technologies, sensors, and sleep parameters used for home-based sleep monitoring in older adults. It also aims to explore various predictors and outcomes associated with sleep to understand the factors of sleep monitoring at home. 

We identified 54 relevant articles using PubMed, Scopus, Web of Science, and an AI tool (Research Rabbit), with 48 studies using wearable technologies and eight studies using non-wearable technologies. Further, six types of sensors were utilized. The most common technology employed was actigraphy wearables, while ballistocardiography and electroencephalography were less common. The most frequent objective parameters of sleep measured were Total Sleep Time (TST), Wakeup After Sleep Onset (WASO), and Sleep Efficiency (SE), with only six studies evaluating sleep architecture in terms of sleep stages. Additionally, six categories of predictors and outcomes associated with sleep were analyzed, including Health-related, Environmental, Interventional, Behavioral, Time and Place, and Social associations. These associations correlate with TST, WASO, and SE and include in-bed behaviors, exterior housing conditions, aerobic exercise, living place, relationship status, and seasonal thermal environments.

Depression emerged as a major public health concern in older adults, and timely prediction of depression has become a difficult problem in medical informatics. The latest studies have attentiveed on feature transformation and selection for better depression prediction. In this study, we assess the performance of various feature extraction algorithms, including principal component analysis (PCA), independent component analysis (ICA), locally linear Embedding (LLE), and t-distributed stochastic neighbor embedding (TSNE). These algorithms are combined with machine learning (ML) classifier algorithms such as Gaussian Naive Bayes (GNB), Logistic Regression (LR), K-nearest-neighbor (KNN), and Decision Tree (DT) to enhance depression prediction. In total, sixteen automated integrated systems are constructed based on the above-mentioned feature extraction methods and ML classifiers. The performance of all of these integrated models is assessed using data from the Swedish National Study on Aging and Care (SNAC). According to the experimental results, the PCA algorithm combined with the Logistic Regression (LR) model provides 89.04% depression classification accuracy. As a result, it is demonstrated that the PCA is a more suitable feature extraction method for depression data than ICA, LLE, and TSNE. © 2024 IEEE.

Objectives: The study aimed to investigate how the objective use of a powered toothbrush in frequency and duration affects plaque index, bleeding on probing, and periodontal pocket depth ≥ 4 mm in elderly individuals with MCI. A second aim was to compare the objective results with the participants’ self-estimated brush use.

Materials and methods: Objective brush usage data was extracted from the participants’ powered toothbrushes and related to the oral health variables plaque index, bleeding on probing, and periodontal pocket depth ≥ 4 mm. Furthermore, the objective usage data was compared with the participants’ self-reported brush usage reported in a questionnaire at baseline and 6- and 12-month examination.

Results: Out of a screened sample of 213 individuals, 170 fulfilled the 12-month visit. The principal findings are that despite the objective values registered for frequency and duration being lower than the recommended and less than the instructed, using powered toothbrushes after instruction and information led to improved values for PI, BOP, and PPD ≥ 4 mm in the group of elderly with MIC.

Conclusions: Despite lower brush frequency and duration than the generally recommended, using a powered toothbrush improved oral health. The objective brush data recorded from the powered toothbrush correlates poorly with the self-estimated brush use. Clinical relevance: Using objective brush data can become one of the factors in the collaboration to preserve and improve oral health in older people with mild cognitive impairment.

Trial registration: ClinicalTrials.gov Identifier: NCT05941611, retrospectively registered 11/07/2023. © 2023, The Author(s).

Background: The number of older individuals with mild cognitive impairment and neurocognitive diseases is increasing, which may rapidly deteriorate oral health and Quality of life. Therefore, removing dental biofilm is essential for maintaining good oral health. The present study aimed to investigate whether introducing a powered toothbrush reduces the presence of dental plaque, bleeding on probing, and periodontal pockets ≥4 mm, leading to maintained or improved oral health and improved Quality of life in a group of older individuals with mild cognitive impairment. Methods: Two hundred and thirteen individuals aged 55 or older living without official home care with a Mini–Mental State Examination (MMSE) score between 20 and 28 and a history of memory problems in the previous 6 months were recruited and screened for the study. The individuals received a powered toothbrush and thorough instructions on how to use it. Clinical oral examinations, Quality of life examinations, and MMSE tests were conducted at baseline, 6, 12, and 24 months. The intervention group was compared to control groups at baseline and 24-month examination. It was divided into an MMSE high group with a score of more than 26 and an MMSE low group with a score of 26 and lower or decreasing two steps or more for 12 months. Results: PI, BOP, and PPD≥4 mm improved continuously in both MMSE groups during the 24 months of the study. The values for QoL-AD deteriorated over time, while the oral health-related Quality of life did not show any statistically significant changes. Conclusions: Introducing a powered toothbrush improved PI, BOP, and PPD≥4 mm over 24 months, even among individuals with low or declining MMSE scores. Improved oral health is associated with a preserved OHR-QoL. © 2024 The Author(s). Special Care in Dentistry published by Special Care Dentistry Association and Wiley Periodicals LLC.

Globally, cancer is the second-leading cause of death after cardiovascular disease. To improve survival rates, risk factors and cancer predictors must be identified early. From the literature, researchers have developed several kinds of machine learning-based diagnostic systems for early cancer prediction. This study presented a diagnostic system that can identify the risk factors linked to the onset of cancer in order to anticipate cancer early. The newly constructed diagnostic system consists of two modules: the first module relies on a statistical F-score method to rank the variables in the dataset, and the second module deploys the random forest (RF) model for classification. Using a genetic algorithm, the hyperparameters of the RF model were optimized for improved accuracy. A dataset including 10 765 samples with 74 variables per sample was gathered from the Swedish National Study on Aging and Care (SNAC). The acquired dataset has a bias issue due to the extreme imbalance between the classes. In order to address this issue and prevent bias in the newly constructed model, we balanced the classes using a random undersampling strategy. The model's components are integrated into a single unit called F-RUS-RF. With a sensitivity of 92.25% and a specificity of 85.14%, the F-RUS-RF model achieved the highest accuracy of 86.15%, utilizing only six highly ranked variables according to the statistical F-score approach. We can lower the incidence of cancer in the aging population by addressing the risk factors for cancer that the F-RUS-RF model found. © 2024 The Author(s). International Journal of Imaging Systems and Technology published by Wiley Periodicals LLC.

Background: Normal voice production depends on the synchronized cooperation of multiple physiological systems, which makes the voice sensitive to changes. Any systematic, neurological, and aerodigestive distortion is prone to affect voice production through reduced cognitive, pulmonary, and muscular functionality. This sensitivity inspired using voice as a biomarker to examine disorders that affect the voice. Technological improvements and emerging machine learning (ML) technologies have enabled possibilities of extracting digital vocal features from the voice for automated diagnosis and monitoring systems. Objective: This study aims to summarize a comprehensive view of research on voice-affecting disorders that uses ML techniques for diagnosis and monitoring through voice samples where systematic conditions, nonlaryngeal aerodigestive disorders, and neurological disorders are specifically of interest. Methods: This systematic literature review (SLR) investigated the state of the art of voice-based diagnostic and monitoring systems with ML technologies, targeting voice-affecting disorders without direct relation to the voice box from the point of view of applied health technology. Through a comprehensive search string, studies published from 2012 to 2022 from the databases Scopus, PubMed, and Web of Science were scanned and collected for assessment. To minimize bias, retrieval of the relevant references in other studies in the field was ensured, and 2 authors assessed the collected studies. Low-quality studies were removed through a quality assessment and relevant data were extracted through summary tables for analysis. The articles were checked for similarities between author groups to prevent cumulative redundancy bias during the screening process, where only 1 article was included from the same author group. Results: In the analysis of the 145 included studies, support vector machines were the most utilized ML technique (51/145, 35.2%), with the most studied disease being Parkinson disease (PD; reported in 87/145, 60%, studies). After 2017, 16 additional voice-affecting disorders were examined, in contrast to the 3 investigated previously. Furthermore, an upsurge in the use of artificial neural network-based architectures was observed after 2017. Almost half of the included studies were published in last 2 years (2021 and 2022). A broad interest from many countries was observed. Notably, nearly one-half (n=75) of the studies relied on 10 distinct data sets, and 11/145 (7.6%) used demographic data as an input for ML models. Conclusions: This SLR revealed considerable interest across multiple countries in using ML techniques for diagnosing and monitoring voice-affecting disorders, with PD being the most studied disorder. However, the review identified several gaps, including limited and unbalanced data set usage in studies, and a focus on diagnostic test rather than disorder-specific monitoring. Despite the limitations of being constrained by only peer-reviewed publications written in English, the SLR provides valuable insights into the current state of research on ML-based voice-affecting disorder diagnosis and monitoring and highlighting areas to address in future research. © 2023 Journal of Medical Internet Research. All rights reserved.