-
PloS One 2024Sleep is critical to a person's physical and mental health and there is a need to create high performing machine learning models and critically understand how models... (Comparative Study)
Comparative Study
IMPORTANCE
Sleep is critical to a person's physical and mental health and there is a need to create high performing machine learning models and critically understand how models rank covariates.
OBJECTIVE
The study aimed to compare how different model metrics rank the importance of various covariates.
DESIGN, SETTING, AND PARTICIPANTS
A cross-sectional cohort study was conducted retrospectively using the National Health and Nutrition Examination Survey (NHANES), which is publicly available.
METHODS
This study employed univariate logistic models to filter out strong, independent covariates associated with sleep disorder outcome, which were then used in machine-learning models, of which, the most optimal was chosen. The machine-learning model was used to rank model covariates based on gain, cover, and frequency to identify risk factors for sleep disorder and feature importance was evaluated using both univariable and multivariable t-statistics. A correlation matrix was created to determine the similarity of the importance of variables ranked by different model metrics.
RESULTS
The XGBoost model had the highest mean AUROC of 0.865 (SD = 0.010) with Accuracy of 0.762 (SD = 0.019), F1 of 0.875 (SD = 0.766), Sensitivity of 0.768 (SD = 0.023), Specificity of 0.782 (SD = 0.025), Positive Predictive Value of 0.806 (SD = 0.025), and Negative Predictive Value of 0.737 (SD = 0.034). The model metrics from the machine learning of gain and cover were strongly positively correlated with one another (r > 0.70). Model metrics from the multivariable model and univariable model were weakly negatively correlated with machine learning model metrics (R between -0.3 and 0).
CONCLUSION
The ranking of important variables associated with sleep disorder in this cohort from the machine learning models were not related to those from regression models.
Topics: Humans; Sleep Initiation and Maintenance Disorders; Male; Female; Machine Learning; Middle Aged; Cross-Sectional Studies; Adult; Retrospective Studies; Risk Factors; Nutrition Surveys; Logistic Models; Aged; Models, Statistical
PubMed: 38954735
DOI: 10.1371/journal.pone.0306359 -
Journal of Patient-reported Outcomes Jun 2024The Insomnia Severity Index (ISI) is a widely used measure of insomnia severity. Various ISI research findings suggest different factor solutions and meaningful... (Randomized Controlled Trial)
Randomized Controlled Trial
Re-examining the factor structure of the Insomnia Severity Index (ISI) and defining the meaningful within-individual change (MWIC) for subjects with insomnia disorder in two phase III clinical trials of the efficacy of lemborexant.
BACKGROUND
The Insomnia Severity Index (ISI) is a widely used measure of insomnia severity. Various ISI research findings suggest different factor solutions and meaningful within-individual change (MWIC) to detect treatment response in patients with insomnia. This study examined an ISI factor solution and psychometric indices to define MWIC in a robust patient sample from clinical trial settings.
METHODS
We endeavored to improve upon previous validation of ISI by examining structural components of confirmatory factor analysis (CFA) models using two large, placebo-controlled clinical trials of lemborexant for insomnia. Using the best-fitting two-factor solution, we evaluated anchor-based, distribution-based and receiver operating characteristic (ROC) curve methods to derive an estimate of the MWIC.
RESULTS
The model structure for the 7-item scale proposed in other research did not fit the observed data from our two lemborexant clinical trials (N = 1956) as well as a two-factor solution based on 6 items did. Using triangulation of anchor-based, distribution-based, and ROC methods, we determined that a 5-point reduction using 6 items best represented a clinically meaningful improvement in individuals with insomnia in our patient sample.
CONCLUSIONS
A 6-item two-factor scale had better psychometric properties than the 7-item scale in this patient sample. On the 6-item scale, a reduction of 5 points in the ISI total score represented the MWIC. Generalizability of the proposed MWIC may be limited to patient populations with similar demographic and clinical characteristics.
Topics: Humans; Sleep Initiation and Maintenance Disorders; Male; Female; Severity of Illness Index; Middle Aged; Psychometrics; Adult; Factor Analysis, Statistical; Treatment Outcome; ROC Curve; Pyridines; Pyrimidines
PubMed: 38951287
DOI: 10.1186/s41687-024-00744-6 -
Frontiers in Public Health 2024Scalable PTSD screening strategies must be brief, accurate and capable of administration by a non-specialized workforce.
BACKGROUND
Scalable PTSD screening strategies must be brief, accurate and capable of administration by a non-specialized workforce.
METHODS
We used PTSD as determined by the structured clinical interview as our gold standard and considered predictors sets of (a) Posttraumatic Stress Checklist-5 (PCL-5), (b) Primary Care PTSD Screen for the DSM-5 (PC-PTSD) and, (c) PCL-5 and PC-PTSD questions to identify the optimal items for PTSD screening for public sector settings in Kenya. A logistic regression model using LASSO was fit by minimizing the average squared error in the validation data. Area under the receiver operating characteristic curve (AUROC) measured discrimination performance.
RESULTS
Penalized regression analysis suggested a screening tool that sums the Likert scale values of two PCL-5 questions-intrusive thoughts of the stressful experience (#1) and insomnia (#21). This had an AUROC of 0.85 (using hold-out test data) for predicting PTSD as evaluated by the MINI, which outperformed the PC-PTSD. The AUROC was similar in subgroups defined by age, sex, and number of categories of trauma experienced (all AUROCs>0.83) except those with no trauma history- AUROC was 0.78.
CONCLUSION
In some East African settings, a 2-item PTSD screening tool may outperform longer screeners and is easily scaled by a non-specialist workforce.
Topics: Humans; Stress Disorders, Post-Traumatic; Female; Male; Adult; Kenya; Mass Screening; Middle Aged; Regression Analysis; Young Adult; Adolescent; Surveys and Questionnaires
PubMed: 38947359
DOI: 10.3389/fpubh.2024.1383171 -
Scientific Reports Jun 2024Correctional workers (CWs) report high levels of work stressors, frequent exposures to potentially psychologically traumatic events (PPTEs), and substantial mental...
Correctional workers (CWs) report high levels of work stressors, frequent exposures to potentially psychologically traumatic events (PPTEs), and substantial mental health challenges. There is evidence of associations between sleep disturbances and diverse mental health challenges, including preliminary evidence from public safety personnel; however, replications and extensions would better inform interventions to support mental health. The current study was designed to examine associations between quality of sleep, work stress, and mental health disorders in a sample of diverse CWs employed in a provincial correctional service in Ontario, Canada. Data were analyzed from 943 CWs who participated in the cross-sectional, web-based Ontario Provincial Correctional Worker Mental Health and Well-Being Study conducted from December 2017 to June 2018. Sleep quality indicators included symptoms of insomnia, total hours of sleep per night on work nights and off-shift nights, number of days feeling rested per week, and overall sleep quality. Descriptive statistics, analyses of variance, correlational analyses, and logistic regression were used to examine relationships among sleep quality, stress of shift work, and mental health disorder symptoms. CWs slept an average of 6.0 h per night when working and 7.2 h during off-shift nights. CWs reported waking up feeling rested an average of 2.6 days per week and rated their overall quality of sleep in the fair to poor range. Many CWs (64.9%) screened positive for clinically significant symptoms of insomnia. There were also differences across occupational groups such that CWs working as correctional officers reported the most sleep problems. There were statistically significant relationships between insomnia and mental health disorder symptoms. Higher levels of stress from shift work were associated with worse sleep quality. CWs, especially those working as correctional officers in a provincial prison, reported many indicators consistent with poorer quality of sleep. Poor quality of sleep was also associated with work stress and mental health disorders.
Topics: Humans; Ontario; Male; Adult; Female; Mental Disorders; Middle Aged; Cross-Sectional Studies; Sleep Quality; Occupational Stress; Prisons; Sleep Initiation and Maintenance Disorders; Mental Health; Young Adult; Correctional Facilities Personnel
PubMed: 38942803
DOI: 10.1038/s41598-024-65891-8 -
Scientific Reports Jun 2024Self-reported shorter/longer sleep duration, insomnia, and evening preference are associated with hyperglycaemia in observational analyses, with similar observations in...
Self-reported shorter/longer sleep duration, insomnia, and evening preference are associated with hyperglycaemia in observational analyses, with similar observations in small studies using accelerometer-derived sleep traits. Mendelian randomization (MR) studies support an effect of self-reported insomnia, but not others, on glycated haemoglobin (HbA1c). To explore potential effects, we used MR methods to assess effects of accelerometer-derived sleep traits (duration, mid-point least active 5-h, mid-point most active 10-h, sleep fragmentation, and efficiency) on HbA1c/glucose in European adults from the UK Biobank (UKB) (n = 73,797) and the MAGIC consortium (n = 146,806). Cross-trait linkage disequilibrium score regression was applied to determine genetic correlations across accelerometer-derived, self-reported sleep traits, and HbA1c/glucose. We found no causal effect of any accelerometer-derived sleep trait on HbA1c or glucose. Similar MR results for self-reported sleep traits in the UKB sub-sample with accelerometer-derived measures suggested our results were not explained by selection bias. Phenotypic and genetic correlation analyses suggested complex relationships between self-reported and accelerometer-derived traits indicating that they may reflect different types of exposure. These findings suggested accelerometer-derived sleep traits do not affect HbA1c. Accelerometer-derived measures of sleep duration and quality might not simply be 'objective' measures of self-reported sleep duration and insomnia, but rather captured different sleep characteristics.
Topics: Humans; Mendelian Randomization Analysis; Glycated Hemoglobin; Accelerometry; Sleep; Blood Glucose; Male; Female; Middle Aged; Adult; Self Report; Aged; Sleep Initiation and Maintenance Disorders
PubMed: 38942746
DOI: 10.1038/s41598-024-58007-9 -
Medicine Jun 2024This is a prospective cohort study to investigate the effects of instrumented lumbar fusion surgery on psychiatric problems, including anxiety, insomnia, and depression,... (Observational Study)
Observational Study
This is a prospective cohort study to investigate the effects of instrumented lumbar fusion surgery on psychiatric problems, including anxiety, insomnia, and depression, in patients with degenerative spinal stenosis, as well as on pain and the activities of daily living. Surgery was performed in the patients with Schizas grade C or D spinal stenosis with; if a patient's quality of life was impaired for at least 3 months or if patient had neurologic deficits. Finally, 69 patients were reviewed. Beck anxiety inventory, insomnia severity index, geriatric depression scale short form-Korean, visual analog scale for back pain, visual analog scale for leg pain, and Oswestry disability index was measured on the day surgery was decided on (T1), the day before surgery (T2), the day before discharge (T3), and 6 months after surgery (T4). The patients had mild degrees of anxiety, insomnia, and depression at T1, and Beck anxiety inventory, insomnia severity index, visual analog scale for back pain, visual analog scale for leg pain, and Oswestry disability index improved significantly by T4. In elderly patients with degenerative spinal stenosis, instrumented lumbar fusion surgery improves not only pain and activities of daily living, but also anxiety and insomnia. However, there was no improvement in depression over the 6-month follow-up period.
Topics: Humans; Aged; Spinal Stenosis; Female; Male; Spinal Fusion; Prospective Studies; Lumbar Vertebrae; Activities of Daily Living; Anxiety; Quality of Life; Depression; Sleep Initiation and Maintenance Disorders; Aged, 80 and over; Pain Measurement; Middle Aged
PubMed: 38941422
DOI: 10.1097/MD.0000000000038719 -
PloS One 2024Spinal cord injury (SCI) is a consequence of significant disability and health issues globally, and long COVID represents the symptoms of neuro-musculoskeletal,...
BACKGROUND
Spinal cord injury (SCI) is a consequence of significant disability and health issues globally, and long COVID represents the symptoms of neuro-musculoskeletal, cardiovascular and respiratory complications.
PURPOSE
This study aimed to identify the symptom responses and disease burden of long COVID in individuals with spinal cord injury.
METHODS
This case-control study was conducted on patients with SCI residing at a specialised rehabilitation centre in Bangladesh. Forty patients with SCI with and without long COVID symptoms (LCS) were enrolled in this study at a 1:1 ratio according to WHO criteria.
RESULT
Twelve LCS were observed in patients with SCI, including fatigue, musculoskeletal pain, memory loss, headache, respiratory problems, anxiety, depression, insomnia, problem in ADL problem in work, palpitation, and weakness. The predictors of developing long COVID include increasing age (p<0.002), increasing BMI (p<0.03), and longer duration of spinal cord injury (p<0.004). A significant difference (p<0.01) in overall years of healthy life lost due to disability (YLD) for non-long COVID cases was 2.04±0.596 compared to long COVID (LC) cases 1.22±2.09 was observed.
CONCLUSION
Bangladeshi patients of SCI presented 12 long COVID symptoms and have a significant disease burden compared to non long COVID cases.
Topics: Humans; Spinal Cord Injuries; Male; Female; COVID-19; Case-Control Studies; Adult; Middle Aged; Bangladesh; Disabled Persons; SARS-CoV-2; Post-Acute COVID-19 Syndrome
PubMed: 38941308
DOI: 10.1371/journal.pone.0304824 -
Frontiers in Public Health 2024Human prion disease (PrD), a group of fatal and transmissible neurodegenerative diseases, consists of Creutzfeldt-Jakob disease (CJD), kuru, fatal familial insomnia...
INTRODUCTION
Human prion disease (PrD), a group of fatal and transmissible neurodegenerative diseases, consists of Creutzfeldt-Jakob disease (CJD), kuru, fatal familial insomnia (FFI), Gerstmann-Sträussler-Scheinker disease (GSS), and variably protease-sensitive prionopathy (VPSPr). The emergence of bovine spongiform encephalopathy (BSE) in cattle and variant CJD (vCJD) has greatly threatened public health, both in humans and animals. Since the 1990's, dozens of countries and territories have conducted PrD surveillance programs.
METHODS
In this study, the case numbers and alternative trends of different types of PrD globally and in various countries or territories from 1993 to 2020 were collected and analyzed based on the data from the websites of the international and national PrD surveillance programs, as well as from relevant publications.
RESULTS
The total numbers of the reported PrD and sporadic CJD (sCJD) cases in 34 countries with accessible annual case numbers were 27,872 and 24,623, respectively. The top seven countries in PrD cases were the USA ( = 5,156), France ( = 3,276), Germany ( = 3,212), Italy ( = 2,995), China ( = 2,662), the UK ( = 2,521), Spain ( = 1,657), and Canada ( = 1,311). The annual PrD case numbers and mortalities, either globally or in the countries, showed an increased trend in the past 27 years. Genetic PrD cases accounted for 10.83% of all reported PrD cases; however, the trend varied largely among the different countries and territories. There have been 485 iatrogenic CJD (iCJD) cases and 232 vCJD cases reported worldwide.
DISCUSSION
The majority of the countries with PrD surveillance programs were high- and upper-middle-income countries. However, most low- and lower-middle-income countries in the world did not conduct PrD surveillance or even report PrD cases, indicating that the number of human PrD cases worldwide is markedly undervalued. Active international PrD surveillance for both humans and animals is still vital to eliminate the threat of prion disease from a public health perspective.
Topics: Humans; Prion Diseases; Global Health; Creutzfeldt-Jakob Syndrome; Animals; Cattle
PubMed: 38939567
DOI: 10.3389/fpubh.2024.1411489 -
PloS One 2024Although breast cancer has a markedly higher incidence in developed countries, seven out of ten deaths occur in developing countries, including Ethiopia. However, there...
BACKGROUND
Although breast cancer has a markedly higher incidence in developed countries, seven out of ten deaths occur in developing countries, including Ethiopia. However, there is a limited information on the quality of life (QoL) among breast cancer patients in Ethiopia, notably in the Amhara region. Therefore, this study aimed to assess the QoL and its associated factors among patients with breast cancer in the Amhara Region, Ethiopia.
METHODS
An institutional based cross-sectional study was conducted from 25th March 2019 to 7th July 2019. A systematically selected sample of 256 breast cancer patients were participated in the study. A standardized interviewer-administered Amharic version questionnaire was used to collect the data. We used the European Organization for Research and Treatment of Cancer quality of life questionnaire core 30 (EORTC QLQ C30) and breast cancer supplementary measure (QLQ-BR23) to measure QoL. The data were analyzed by SPSS version 23. A binary logistic regression model was fitted to identify the predictors of QoL. The adjusted odds ratio (AOR) with a 95% confidence interval (CI) was reported to show the strength of the association.
RESULTS
Sixty-eight percent of breast cancer patients had poor QoL (68.4%; 95% CI: 62.5-73.8). The mean score of QoL was 70.6 (standard deviation (SD) ±13.9; 95% CI: 69.0-72.4). All functional component scores were less than 75 on the symptom scale. Diarrhea (11.6), constipation (17.5), and dyspnea (24.7) were less noticeable symptoms. Being out of marriage (AOR = 2.59, 95% CI: 1.32-5.07), being poor (AOR = 2.39, 95%CI: 1.32-5.03), being non-housewife (AOR = 3.25, 95% CI: 1.16-7.22), and being complaints of dyspnea (AOR = 3.48, 95% CI: 1.79-6.79), and insomnia (AOR = 2.03, 95% CI: 1.05-3.91) were significantly associated with QoL.
CONCLUSIONS
The proportion of poor QoL among breast cancer patients was high. Health care professionals should give attention to breast cancer patients who are out of marriage, poor and non-housewife while offering the recommended treatment courses.
Topics: Humans; Quality of Life; Ethiopia; Female; Breast Neoplasms; Cross-Sectional Studies; Middle Aged; Adult; Surveys and Questionnaires; Aged
PubMed: 38935776
DOI: 10.1371/journal.pone.0305263 -
PloS One 2024The present study investigated how life stress and sleep disturbance impact depressive symptoms among Chinese (N = 185) and Japanese (N = 464) workers. Based on a...
The present study investigated how life stress and sleep disturbance impact depressive symptoms among Chinese (N = 185) and Japanese (N = 464) workers. Based on a hypothesis that sleep disturbance can cause depression, a statistical model is established, expecting that work-related life stress indirectly increases depressive symptoms by worsening sleep disturbance rather than initiating depression directly. The study also examined the buffering effects of social support on depression. The extent of depressive symptoms, sleep disturbance symptoms (insomnia, hypersomnia, and nightmare), work-related stressors, and available social support were measured. The result revealed that the extent of depression was equivalent for both groups, but the Chinese reported more stress, less social support, and more severe sleep disturbance symptoms than the Japanese. Despite those differences, the statistical model fitted both groups well, suggesting that addressing sleep disturbance at the earliest opportunity can effectively prevent depression onset for workers.
Topics: Humans; Depression; Male; Female; Adult; Sleep Wake Disorders; Japan; Middle Aged; China; Stress, Psychological; Social Support; Asian People; Occupational Stress; East Asian People
PubMed: 38935694
DOI: 10.1371/journal.pone.0305936