Categories
Nevin Manimala Statistics

Comparing machine learning algorithms for multimorbidity prediction: An example from the Elsa-Brasil study

PLoS One. 2022 Oct 7;17(10):e0275619. doi: 10.1371/journal.pone.0275619. eCollection 2022.

ABSTRACT

BACKGROUND: Multimorbidity is a worldwide concern related to greater disability, worse quality of life, and mortality. The early prediction is crucial for preventive strategies design and integrative medical practice. However, knowledge about how to predict multimorbidity is limited, possibly due to the complexity involved in predicting multiple chronic diseases.

METHODS: In this study, we present the use of a machine learning approach to build cost-effective multimorbidity prediction models. Based on predictors easily obtainable in clinical practice (sociodemographic, clinical, family disease history and lifestyle), we build and compared the performance of seven multilabel classifiers (multivariate random forest, and classifier chain, binary relevance and binary dependence, with random forest and support vector machine as base classifiers), using a sample of 15105 participants from the Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). We developed a web application for the building and use of prediction models.

RESULTS: Classifier chain with random forest as base classifier performed better (accuracy = 0.34, subset accuracy = 0.15, and Hamming Loss = 0.16). For different feature sets, random forest based classifiers outperformed those based on support vector machine. BMI, blood pressure, sex, and age were the features most relevant to multimorbidity prediction.

CONCLUSIONS: Our results support the choice of random forest based classifiers for multimorbidity prediction.

PMID:36206287 | DOI:10.1371/journal.pone.0275619

Categories
Nevin Manimala Statistics

A comparison of the functional connectome in mild traumatic brain injury and post-traumatic stress disorder

Hum Brain Mapp. 2022 Oct 7. doi: 10.1002/hbm.26101. Online ahead of print.

ABSTRACT

Post-traumatic stress disorder (PTSD) and mild traumatic brain injury (mTBI) often co-occur in the context of threat to one’s life. These conditions also have an overlapping symptomatology and include symptoms of anxiety, poor concentration and memory problems. A major challenge has been articulating the underlying neurobiology of these overlapping conditions. The primary aim of this study was to compare intrinsic functional connectivity between mTBI (without PTSD) and PTSD (without mTBI). The study included functional MRI data from 176 participants: 42 participants with mTBI, 67 with PTSD and a comparison group of 66 age and sex-matched healthy controls. We used network-based statistical analyses for connectome-wide comparisons of intrinsic functional connectivity between mTBI relative to PTSD and controls. Our results showed no connectivity differences between mTBI and PTSD groups. However, we did find that mTBI had significantly reduced connectivity relative to healthy controls within an extensive network of regions including default mode, executive control, visual and auditory networks. The mTBI group also displayed hyperconnectivity between dorsal and ventral attention networks and perceptual regions. The PTSD group also demonstrated abnormal connectivity within these networks relative to controls. Connectivity alterations were not associated with severity of PTSD or post-concussive symptoms in either clinical group. Taken together, the similar profiles of intrinsic connectivity alterations in these two conditions provide neural evidence that can explain, in part, the overlapping symptomatology between mTBI and PTSD.

PMID:36206284 | DOI:10.1002/hbm.26101

Categories
Nevin Manimala Statistics

Timing of submissions to The Journal of Paediatrics and Child Health: Associations with the COVID-19 pandemic and editorial decisions

J Paediatr Child Health. 2022 Oct 7. doi: 10.1111/jpc.16242. Online ahead of print.

ABSTRACT

AIM: To determine if the timing of manuscript submissions to The Journal of Paediatrics and Child Health (JPCH) changed following the onset of the COVID-19 pandemic and to determine if the timing of manuscript submissions influenced editorial decisions.

METHODS: A retrospective observational study of submissions to JPCH from 1 January 2015 to 1 August 2022 was performed. Regression models were used to explore the change over time. Editorial decisions were examined using a multinomial regression model with the three-category ordinal outcome of reject, revise and accept. All statistical models were fitted using a Bayesian approach and show 95% credible intervals (CI).

RESULTS: The analyses included 11 499 manuscript submissions between 2015 and 2022. The mean number of manuscript submissions increased by 17 papers per month (CI 15-19), with a larger 4-month long increase after the COVID-19 pandemic was declared of 86 submissions per month (CI 67-103). There was no clear effect of the pandemic on weekend submissions, mean difference in probability 0.003 (CI -0.021 to 0.026). Throughout the study period, the peak submission time was later in the day and was shifted +37 min later post-March 2020 (CI +22 to +52 min). Throughout the study period, submissions out-of-hours and on weekends were less likely to get an editorial decision of ‘accept’ or ‘revise’: odds ratio weekend versus weekday 0.87 (CI 0.78-0.97).

CONCLUSION: The COVID-19 pandemic had a limited effect on the timing of manuscript submissions to JPCH. However, the timing of manuscript submission impacted the likelihood of a more positive editorial decision. While the time of manuscript submission is only one part of the research process, it is postulated that it may be associated with research quality.

PMID:36206278 | DOI:10.1111/jpc.16242

Categories
Nevin Manimala Statistics

Evaluation of circulating microRNA profiles in Brazilian women with polycystic ovary syndrome: A preliminary study

PLoS One. 2022 Oct 7;17(10):e0275031. doi: 10.1371/journal.pone.0275031. eCollection 2022.

ABSTRACT

OBJECTIVE: Polycystic ovary syndrome (PCOS) is a heterogeneous endocrinopathy, which etiology encompasses complex genetic traits associated with epigenetic factors, including differences in microRNA (miRNA) expression in a variety of tissues. The circulating form of these molecules is raising attention in the syndrome not only as potential biomarkers of PCOS but also as possible therapeutic targets. The aim of this study was to explore the circulating miRNA profiles present in a cohort of Brazilian women with and without PCOS and to evaluate the potential role of miRNAs in the pathophysiology of the syndrome.

METHODS: Cross-sectional study of 36 well-characterized PCOS women and 16 healthy controls. Clinical, hormone and metabolic data were recorded and evaluated. The expression profile of the 201 circulating miRNA selected were analyzed by taqman quantitative real time polymerase chain reactions (RT-PCR) using a customized Open Array platform. Statistical and bioinformatic analyzed were performed.

RESULTS: Circulating miR-21-5p, miR-23a-3p and miR-26a-5p were upregulated, and miR-103a-3p, miR-376a-3p, miR-19b-3p and miR-222-3p were downregulated in women with PCOS compared to healthy normo-ovulatory controls. miR-21-5p, miR-103a-3p and miR-376a-3p levels correlated positively with androgen levels. These miRNAs, in combination, were related to pathways involved in insulin signaling, steroids biosynthesis and endothelial regulation as well as in folliculogenesis.

CONCLUSION: In this study, we identified a specific circulating miRNA signature in Brazilian women with PCOS. According to our data, circulating miR-21-5p, miR-23a-3p, miR-26a-5p, miR-103a-3p, miR-376a-3p, miR-19b-3p and miR-222-3p may represent potential candidates for differential diagnosis of PCOS in the future.

PMID:36206272 | DOI:10.1371/journal.pone.0275031

Categories
Nevin Manimala Statistics

An exploratory study on the handwritten allographic features of multi-ethnic population with different educational backgrounds

PLoS One. 2022 Oct 7;17(10):e0268756. doi: 10.1371/journal.pone.0268756. eCollection 2022.

ABSTRACT

Ethnicity, native and/or foreign language knowledge, as well as the learned writing systems potentially influence the development of an individual’s handwriting. The unique education system consisting of National schools, Chinese-medium vernacular schools, Tamil-medium vernacular schools, and Islamic religious schools in Malaysia may have established specific characteristic handwritten allographic features that deserve investigation within the intelligence context. This study was aimed to explore handwritten allographic features of handwriting samples from 120 subjects (30 writers from four different educational backgrounds mentioned above). Characteristic features which could be attributed to the study groups were statistically analyzed and identified. In this study, thirteen allographic features, including letters “A”, “B”, “D”, “H”, “p”, “T”, “t”, “w”, “X” and “x”, were found to be discriminative. Such information could serve to indicate the primary education system undergone by a writer; enabling the comparison of different handwriting profiles and allowing characterization of writers to a specific group of people.

PMID:36206268 | DOI:10.1371/journal.pone.0268756

Categories
Nevin Manimala Statistics

Association between lifestyle choices and mental health among medical students during the COVID-19 pandemic: A cross-sectional study

PLoS One. 2022 Oct 7;17(10):e0274525. doi: 10.1371/journal.pone.0274525. eCollection 2022.

ABSTRACT

INTRODUCTION: Mental health is recognized as a critical component of public health Given the close relationship between mental health and life style and the importance of students as valuable human resources, the present study aimed at determining the relationship between life style and mental health among medical students in Sousse during COVID-19 pandemic.

METHODS: We conducted a cross-sectional observational study in university students from the first to the fifth grade of the Faculty of Medicine of Sousse during the academic year 2020/2021. Data were collected anonymously via an online questionnaire published on the Facebook groups of each grade, on december 2020. The online survey consisted of three sections. The first one aimed to collect sociodemographic information. The second section of the survey addressed recent lifestyle choices and the third one assessed psychological distress using the French version of 12 items of The General Health Questionnaire (GHQ-12). The significance level was considered 0.05.

RESULTS: Overall 147 were studied. Using the bimodal scoring, the total score was between 0 and 12, to evoke psychiatric disorders, we set the threshold of 4. For our sample, the median scale was 7 [4-9], and more than half of the students (68%; n = 100) had a score higher than 4. Psychiatric disorder was significantly more frequent in female students (73.3% vs 42.3%; p = 0.002). Higher GHQ-scale was found in younger students, foreigners, students who need more than 30 minutes to get to the faculty, unemployed students, and students of fifth grade. However, differences were not statistically significant. Regarding lifestyle choices, we found that physical inactivity, no smoking habits, no alcohol use, no illicit substance use, other substance use, changing in eating habits, and absence of coping methods of stress were higher in students with psychiatric disorders. However, this association was statistically significant only for physical activity (p = 0.016). The results of the regression analysis suggest female gender as an independent predictor of high GHQ-12 scores. Practicing physical activity was found as protective factor for psychiatric disorders.

CONCLUSION: Considering the vital role of medical students in providing and promoting community health, the need for more detailed planning and interventions to improve their life style and mental health is essential.

PMID:36206267 | DOI:10.1371/journal.pone.0274525

Categories
Nevin Manimala Statistics

Population trends of seabirds in Mexican Islands at the California Current System

PLoS One. 2022 Oct 7;17(10):e0258632. doi: 10.1371/journal.pone.0258632. eCollection 2022.

ABSTRACT

The Baja California Pacific Islands (BCPI) is a seabird hotspot in the southern California Current System supporting 129 seabird breeding populations of 23 species and over one million birds annually. These islands had a history of environmental degradation because of invasive alien species, human disturbance, and contaminants that caused the extirpation of 27 seabird populations. Most of the invasive mammals have been eradicated and colonies have been restored with social attraction techniques. We have recorded the number of breeding pairs annually for most of the colonies since 2008. To assess population trends, we analyzed these data and show results for 19 seabird species on ten island groups. The maximum number of breeding pairs for each nesting season was used to estimate the population growth rate (λ) for each species at every island colony. We performed a moving block bootstrap analysis to assess whether seabird breeding populations are increasing or decreasing. San Benito, Natividad, and San Jerónimo are the top three islands in terms of abundance of breeding pairs. The most widespread species is Cassin’s Auklet (Ptychoramphus aleuticus) with 14 colonies. Thirty-one populations of 14 species are significantly increasing while eleven populations of seven species are decreasing. We did not find statistical significance for 19 populations, however, 15 have λ>1 which suggest they are growing. Twelve of the 18 species for which we estimated a regional population trend are significantly increasing, including seven surface-nesting species: Brandt’s Cormorant (Phalacrocorax penicillatus), Brown Pelican (Pelecanus occidentalis), Caspian Tern (Hydroprogne caspia), Double-crested Cormorant (P. auritus), Elegant Tern (Thalasseus elegans), Laysan Albatross (Phoebastria immutabilis) and Western Gull (Larus occidentalis), and five burrow-nesting species: Ainley’s (Hydrobates cheimomnestes), Ashy (H. homochroa) and Townsend’s (H. socorroensis) Storm-Petrels, and Craveri’s (Synthliboramphus craveri) and Guadalupe (S. hypoleucus) Murrelets. The BCPI support between 400,000 and 1.4 million breeding individuals annually. Our results suggest that these islands support healthy and growing populations of seabirds that have shown to be resilient to extreme environmental conditions such as the “Blob”, and that such resilience has been strengthen from conservation and restoration actions such as the eradication of invasive mammals, social attraction techniques and island biosecurity.

PMID:36206266 | DOI:10.1371/journal.pone.0258632

Categories
Nevin Manimala Statistics

Relationship between finger movement characteristics and brain voxel-based morphometry

PLoS One. 2022 Oct 7;17(10):e0269351. doi: 10.1371/journal.pone.0269351. eCollection 2022.

ABSTRACT

BACKGROUND: Aging is the most significant risk factor for dementia. Alzheimer’s disease (AD) accounts for approximately 60-80% of all dementia cases in older adults. This study aimed to examine the relationship between finger movements and brain volume in AD patients using a voxel-based reginal analysis system for Alzheimer’s disease (VSRAD) software.

METHODS: Patients diagnosed with AD at the Center for Comprehensive Care and Research on Memory Disorders were included. The diagnostic criteria were based on the National Institute on Aging-Alzheimer’s Association. A finger-tapping device was used for all measurements. Participants performed the tasks in the following order: with their non-dominant hand, dominant hand, both hands simultaneously, and alternate hands. Movements were measured for 15 s each. The relationship between distance and output was measured. Magnetic resonance imaging measurements were performed, and VSRAD was conducted using sagittal section 3D T1-weighted images. The Z-score was used to calculate the severity of medial temporal lobe atrophy. Pearson’s product-moment correlation coefficient analyzed the relationship between the severity of medial temporal lobe atrophy and mean values of the parameters in the finger-tapping movements. The statistical significance level was set at <5%. The calculated p-values were corrected using the Bonferroni method.

RESULTS: Sixty-two patients were included in the study. Comparison between VSRAD and MoCA-J scores corrected for p-values showed a significant negative correlation with the extent of gray matter atrophy (r = -0. 52; p< 0.001). A positive correlation was observed between the severity of medial temporal lobe atrophy and standard deviation (SD) of the distance rate of velocity peak in extending movements in the non-dominant hand (r = 0. 51; p< 0.001).

CONCLUSIONS: The SD of distance rate of velocity peak in extending movements extracted from finger taps may be a useful parameter for the early detection of AD and diagnosis of its severity.

PMID:36206254 | DOI:10.1371/journal.pone.0269351

Categories
Nevin Manimala Statistics

Prevalence of active trachoma and associated factors among children 1-9 years old at Arsi Negele Town, West Arsi Zone, Oromia Regional State, Southern Ethiopia

PLoS One. 2022 Oct 7;17(10):e0273808. doi: 10.1371/journal.pone.0273808. eCollection 2022.

ABSTRACT

BACKGROUND: Trachoma is a public health issue in more than 50 nations worldwide, mainly in Sub-Saharan Africa, where hundreds of millions of people are considered blind. Ethiopia is projected to have 30% of the global active trachoma burden. The frequency of Trachoma Folliculitis in children aged 1 to 9 years old is 30% in the Oromia Region. Therefore, the aim of this study was to assess the prevalence of active trachoma and associated variables among children aged 1 to 9 years old in Arsi Negele Town, West Arsi Zone, Oromia Regional State, Southern Ethiopia, December 24-26, 2019.

METHODS: A community-based cross-sectional study was conducted in the Arsi Negele town community on December 24-26, 2019. A total of 178 study volunteers were recruited using a single population proportion formula and assigned to families in the town’s three kebeles in proportion. A simple random selection procedure was used to choose study participants from the identified households. Madda Walabu University provided ethical approval, and different government structures provided letters of permission. Pre-tested structured questionnaires and binocular loupes X 2.5 were used to collect data from either mothers or fathers of eligible children for eye examination; torches with bottles of alcohol were used to gather data from either mothers or fathers of eligible children for eye examination. For analysis, data was entered into (IBM, SPSS) version 22. To assess factors associated with active trachoma, bivariate and multivariable logistic regressions were used. The crude and adjusted odds ratios with 95% confidence intervals were calculated to investigate the degree of association between the independent variables and active trachoma. Multivariate logistic regression was used to find connections between dependent and independent variables with a p≤ 0.05 confidence levels and a 95% confidence interval.

RESULT: The prevalence of active trachoma was determined to be 21.91% TF among 178 children aged 1 to 9 years. Flies on children’s faces (AOR = 3.427; 95 percent CI: 1.432-8.171), unclean children’s faces (AOR = 3.99; 95 percent CI: 1.427-11.158), face washing habits (AOR = 3.064; 95 percent CI: 1.273-7.373), and not using soap while face washing (AOR = 4.564; 95 percent CI 1.561-13.342) were found to be statistically significant associated factors with the prevalence of active trachoma.

CONCLUSION: The prevalence of active trachoma was found to be relatively high. Face washing practices and the lack of soap use while washing faces were found as associated factors requiring optimal interventions to prevent trachoma infection among children aged 1-9 years in Arsi Negele town.

PMID:36206245 | DOI:10.1371/journal.pone.0273808

Categories
Nevin Manimala Statistics

Non-invasive electrophysiological differences between women and men:differences in body size not an explanation

Am J Physiol Heart Circ Physiol. 2022 Oct 7. doi: 10.1152/ajpheart.00454.2022. Online ahead of print.

ABSTRACT

There are numerous sex-related differences in cardiac electrophysiology and arrhythmia propensity but very little knowledge about the reasons. Difference in body size has been proposed as one reason and was tested in this study of >20 cardiac electrophysiology parameters in 319 (158 women) apparently healthy 50-64 years old subjects from a randomly enrolled population sample, the SCAPIS pilot study (Swedish CArdio-Pulmonary bioImaging Study), using Frank vectorcardiography. We studied conventional conduction intervals, parameters reflecting electrical heterogeneity (dispersion) in the ventricles, QRS- and T-vector directions, spatial QRS-T angles, and T-vector loop morphology. Body surface area (BSA; two methods) and lean body mass (LBM), both estimated from body weight and height, were used as body size parameters. According to multivariable linear regression analysis adjusted for sex, there was no association between electrophysiological parameters and body size apart from QRS duration and QRSarea. In conclusion, most electrophysiological parameters assessed completely non-invasively and showing statistically significant differences between women and men on the group level show no association with BSA or LBM. Scaling (indexing) the electrophysiological parameters for body size parameters are therefore not an option. As a consequence, the explanation for the sex-related electrophysiological differences should be sought along other lines.

PMID:36206051 | DOI:10.1152/ajpheart.00454.2022