Deep learning algorithms for melanoma detection using dermoscopic images: A systematic review and meta-analysis.

BACKGROUND: Melanoma is a serious risk to human health and early identification is vital for treatment success. Deep learning (DL) has the potential to detect cancer using imaging technologies and many studies provide evidence that DL algorithms can achieve high accuracy in melanoma diagnostics. OBJECTIVES: To critically assess different DL performances in diagnosing melanoma using dermatoscopic images and discuss the relationship between dermatologists and DL. METHODS: Ovid-Medline, Embase, IEEE Xplore, and the Cochrane Library were systematically searched from inception until 7th December 2021. Studies that reported diagnostic DL model performances in detecting melanoma using dermatoscopic images were included if they had specific outcomes and histopathologic confirmation. Binary diagnostic accuracy data and contingency tables were extracted to analyze outcomes of interest, which included sensitivity (SEN), specificity (SPE), and area under the curve (AUC). Subgroup analyses were performed according to human-machine comparison and cooperation. The study was registered in PROSPERO, CRD42022367824. RESULTS: 2309 records were initially retrieved, of which 37 studies met our inclusion criteria, and 27 provided sufficient data for meta-analytical synthesis. The pooled SEN was 82 % (range 77-86), SPE was 87 % (range 84-90), with an AUC of 0.92 (range 0.89-0.94). Human-machine comparison had pooled AUCs of 0.87 (0.84-0.90) and 0.83 (0.79-0.86) for DL and dermatologists, respectively. Pooled AUCs were 0.90 (0.87-0.93), 0.80 (0.76-0.83), and 0.88 (0.85-0.91) for DL, and junior and senior dermatologists, respectively. Analyses of human-machine cooperation were 0.88 (0.85-0.91) for DL, 0.76 (0.72-0.79) for unassisted, and 0.87 (0.84-0.90) for DL-assisted dermatologists. CONCLUSIONS: Evidence suggests that DL algorithms are as accurate as senior dermatologists in melanoma diagnostics. Therefore, DL could be used to support dermatologists in diagnostic decision-making. Although, further high-quality, large-scale multicenter studies are required to address the specific challenges associated with medical AI-based diagnostics.

Air pollution, life's essential 8, and risk of severe non-alcoholic fatty liver disease among individuals with type 2 diabetes.

BACKGROUND: The impacts of long-term exposure to air pollution on the risk of subsequent non-alcoholic fatty liver disease (NAFLD) among participants with type 2 diabetes (T2D) is ambiguous. The modifying role of Life's Essential 8 (LE8) remains unknown. METHODS: This study included 23,129 participants with T2D at baseline from the UK Biobank. Annual means of nitrogen dioxide (NO2), nitrogen oxides (NOX), and particulate matter (PM2.5, PM2.5-10, PM10) were estimated using the land-use regression model for each participant. The associations between exposure to air pollution and the risk of severe NAFLD were evaluated using Cox proportional hazard models. The effect modification of LE8 was assessed through stratified analyses. RESULTS: During a median 13.6 years of follow-up, a total of 1,123 severe NAFLD cases occurred. After fully adjusting for potential covariates, higher levels of PM2.5 (hazard ratio [HR] = 1.12, 95%CI:1.02, 1.23 per interquartile range [IQR] increment), NO2 (HR = 1.15, 95%CI:1.04, 1.27), and NOX (HR = 1.08, 95%CI:1.01, 1.17) were associated with an elevated risk of severe NAFLD. In addition, LE8 score was negatively associated with the risk of NAFLD (HR = 0.97, 95% CI: 0.97, 0.98 per point increment). Compared with those who had low air pollution and high LE8, participants with a high air pollution exposure and low LE8 had a significantly higher risk of severe NAFLD. CONCLUSIONS: Our findings suggest that long-term exposure to air pollution was associated with an elevated risk of severe NAFLD among participants with T2D. A lower LE8 may increase the adverse impacts of air pollution on NAFLD.

A Large-Scale Online Survey on Clinical Severity and Associated Risk Factors for SARS-CoV-2 Omicron Infection - China, April-May 2023.

What is already known about this topic?: Individuals who initially contract severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) lack significant mixed immunity. Therefore, it is crucial to monitor the clinical characteristics and associated factors of these individuals in order to inform policy-making. What is added by this report?: The common symptoms reported were fever, cough, and sore throat. Reinfections and receiving four vaccination doses within a 6-month period were found to be associated with a shorter duration of virus shedding, decreased hospitalization rate, and reduced risk of pneumonia. Individuals aged 60 years and older, as well as those with underlying medical conditions, had a higher risk of developing pneumonia. What are the implication for public health practices?: Online surveys conducted through social media platforms have the potential to complement disease surveillance and data collection efforts. In terms of vaccination prioritization, it is recommended to prioritize older individuals and those with underlying diseases.

COVID-19 Vaccine Hesitancy Among People Living with HIV: A Systematic Review and Meta-Analysis.

Vaccine hesitancy is one of the top 10 threats to global health, which affects the prevalence and fatality of vaccine-preventable diseases over the world. During the COVID-19 pandemic, people living with HIV (PLWH) may have higher risks of infection, more serious complications, and worse prognosis without the protection of the COVID-19 vaccine. A systematic review and meta-analysis aiming to evaluate the prevalence of COVID-19 vaccine hesitancy among PLWH was conducted using PubMed, Embase, and Web of Science databases for studies published between January 1, 2020, and August 31, 2022. The pooled prevalence with a corresponding 95%CI of COVID-19 vaccine hesitancy among PLWH was reported. Subgroup analysis was conducted to explore variation in prevalence across different categories. 23 studies with a total of 19,922 PLWH were included in this study. The prevalence of COVID-19 vaccine hesitancy among PLWH was 34.0%, and the influencing factors included male, influenza vaccination experience, and a CD4 count of more than 200 cells/mm3. Subgroup analysis did not identify significant causes of heterogeneity but showed that the prevalence of COVID-19 vaccine hesitancy among PLWH varies by study period, region, and race. Although all PLWH are recommended to receive the COVID-19 vaccine, a large proportion of them remain hesitant to be vaccinated. Therefore, governments and relevant institutions should take specific measures to encourage and promote vaccination to improve the coverage of the COVID-19 vaccine among PLWH.

Artificial intelligence performance in detecting lymphoma from medical imaging: a systematic review and meta-analysis.

BACKGROUND: Accurate diagnosis and early treatment are essential in the fight against lymphatic cancer. The application of artificial intelligence (AI) in the field of medical imaging shows great potential, but the diagnostic accuracy of lymphoma is unclear. This study was done to systematically review and meta-analyse researches concerning the diagnostic performance of AI in detecting lymphoma using medical imaging for the first time. METHODS: Searches were conducted in Medline, Embase, IEEE and Cochrane up to December 2023. Data extraction and assessment of the included study quality were independently conducted by two investigators. Studies that reported the diagnostic performance of an AI model/s for the early detection of lymphoma using medical imaging were included in the systemic review. We extracted the binary diagnostic accuracy data to obtain the outcomes of interest: sensitivity (SE), specificity (SP), and Area Under the Curve (AUC). The study was registered with the PROSPERO, CRD42022383386. RESULTS: Thirty studies were included in the systematic review, sixteen of which were meta-analyzed with a pooled sensitivity of 87% (95%CI 83-91%), specificity of 94% (92-96%), and AUC of 97% (95-98%). Satisfactory diagnostic performance was observed in subgroup analyses based on algorithms types (machine learning versus deep learning, and whether transfer learning was applied), sample size (≤ 200 or >  200), clinicians versus AI models and geographical distribution of institutions (Asia versus non-Asia). CONCLUSIONS: Even if possible overestimation and further studies with a better standards for application of AI algorithms in lymphoma detection are needed, we suggest the AI may be useful in lymphoma diagnosis.

Corrigendum: Ischemic and haemorrhagic stroke risk estimation using a machine-learning-based retinal image analysis.

[This corrects the article DOI: 10.3389/fneur.2022.916966.].

Trajectories of antepartum depressive symptoms and birthweight: a multicenter and prospective cohort study.

BACKGROUND: Antepartum depression is a prevalent unhealthy mental health problem worldwide, particularly in low-income countries. It is a major contributor to adverse birth outcomes. Previous studies linking antepartum depression to birthweight have yielded conflicting results, which may be the reason that the depressive symptoms were only measured once during pregnancy. This study aimed to explore the associations between trajectories of antepartum depressive symptoms and birthweight. METHODS: Depressive symptoms were assessed prospectively at each trimester in 3699 pregnant women from 24 hospitals across 15 provinces in China, using the Edinburgh Postpartum Depression Scale (EPDS). Higher scores of EPDS indicated higher levels of depressive symptoms. Associations between trajectories of depressive symptoms and birthweight were examined using group-based trajectory modeling (GBTM), propensity score-based inverse probability of treatment weighting (IPTW), and logistic regression. RESULTS: GBTM identified five trajectories. Compared with the low-stable trajectory of depressive symptoms, only high-stable (OR = 1.35, 95% CI: 1.15-2.52) and moderate-rising (OR = 1.18, 95% CI: 1.12-1.85) had an increased risk of low birthweight (LBW) in the adjusted longitudinal analysis of IPTW. There was no significant increase in the risk of LBW in moderate-stable and high-falling trajectories. However, trajectories of depressive symptoms were not associated with the risk of macrosomia. CONCLUSION: Antepartum depressive symptoms were not constant. Trajectories of depressive symptoms were associated with the risk of LBW. It is important to optimize and implement screening, tracking, and intervention protocols for antepartum depression, especially for high-risk pregnant women, to prevent LBW.

Trajectories of depressive symptoms during pregnancy and risk of premature birth: A multicenter and prospective cohort study.

Previous studies only assessed the association between depressive symptoms and risk of preterm birth (PTB) at a time-point during pregnancy, resulting in inconsistent or contradictory results. Therefore, we aimed to explore the associations between the trajectories of depressive symptoms during pregnancy and risk of PTB. In total, 7732 pregnant women were included in 24 hospitals from 15 provinces of China. The Edinburgh Postpartum Depression Scale (EPDS) was used to evaluate depressive symptoms in the first, second, and third trimesters. Associations between depressive symptoms and risk of PTB were performed by group-based trajectory modeling (GBTM), propensity score-based inverse probability of treatment weighting (IPTW), and logistic regression. GBTM identified five trajectories: compared with persistently low-stable trajectory of depressive symptoms, women with moderate-stable (OR = 1.23, 95% CI: 1.02-1.76), high-falling (OR = 1.35, 95% CI: 1.11-2.21), moderate-rising (OR = 1.38, 95% CI: 1.06-2.04), and high-stable trajectory of depressive symptoms (OR = 1.40, 95% CI: 1.16-3.28) had an increased risk of PTB. In addition, the associations between trajectories of depressive symptoms and risk of PTB were most significant in multiparous women with a history of PTB. There was no difference in the risk of early-moderate PTB among different trajectories of depressive symptoms and only the risk of late PTB was different among different trajectories. In conclusion, the depressive symptoms of pregnant women were not constant during pregnancy, and different trajectories of depressive symptoms were associated with different risks of PTB.

Pregnancy Loss in Relation to the Risks of Female-Specific Cancers in a Population-Based Cohort and Mendelian Randomization Study - China, 2004-2017.

What is already known about this topic?: Limited evidence exists regarding the relationship between pregnancy loss and female-specific cancers within the Chinese population from prospective cohort studies. What is added by this report?: Terminations were associated with a 13% lower risk of endometrial cancer, whereas stillbirths were related to an 18% higher risk of cervical cancer. Rural residents with a history of pregnancy loss experienced a 19% and 38% increased risk of breast and cervical cancers, respectively, compared to their urban counterparts. Moreover, a positive graded relationship between live births and pregnancy loss on cervical cancer was observed. What are the implications for public health practice?: This study has significant implications for identifying women at an increased risk for breast and genital cancers and contributes to the development of effective public health strategies for female cancer prevention. Future research on reproductive history, particularly in rural areas, should be given priority in efforts to improve female cancer screening and early detection.

Correction: Unassisted Clinicians Versus Deep Learning-Assisted Clinicians in Image-Based Cancer Diagnostics: Systematic Review With Meta-analysis.

[This corrects the article DOI: 10.2196/43832.].

Suicidal ideation and associated risk factors among COVID-19 patients who recovered from the first wave of the pandemic in Wuhan, China.

BACKGROUND: Symptoms of psychiatric, neurological, and physical illnesses with post-COVID syndrome could increase suicidal ideation (SI) and behavior in Corona Virus Disease 2019 (COVID-19) survivors. However, information on the level of SI among COVID-19 survivors in China is still limited. AIM: To assess the prevalence and risk factors of SI among COVID-19 survivors in Wuhan, China. DESIGN: The cross-sectional study was carried out among former COVID-19 patients in Jianghan District (Wuhan, China) from June 10 to July 25, 2021. METHODS: SI, fatigue, stigma, sleep disorder, resilience, peace of mind, and social support of the participants were measured by the SI-related item, Fatigue Scale (FS-14), short version of COVID-19 Stigma Scale, Pittsburgh Sleep Quality Index (PSQI), The Peace of Mind Scale (PoM), The Resilience Style Questionnaire (RSQ) and two single separate items for measuring social support. Logistic regression was utilized to identify associated factors of SI. Mediation analysis was performed to assess the potential mechanisms between psychological factors and SI. RESULTS: A total of 1,297 participants were included in this study. 6.7% of them reported SI. Marriage (AOR = 0.389, P = 0.003) and peace of mind (AOR = 0.854, P < 0.001) were negatively associated with SI. History of psychological or emotional counseling before COVID-19 infection (AOR = 1.889, P = 0.049), fatigue (AOR = 1.110, P = 0.007), higher self-reported COVID-19 related stigma (AOR = 1.054, P = 0.003) and sleep disorder (AOR = 1.112, P = 0.001) were positively associated with SI. CONCLUSIONS: Consideration should be taken into account to develop appropriate alleviating measures such as mindfulness-based cognitive therapy to reduce the rates of SI among COVID-19 survivors and improve their resilience to cope with the personal impact of the COVID-19 pandemic.

Associations of urinary organophosphate esters metabolites with asthma and lung function in adolescents.

BACKGROUND: Organophosphate esters (OPEs) are ubiquitously detected in environments and their exposure may affect respiratory health. However, epidemiological evidence, particularly among adolescents, is very limited. OBJECTIVE: We aimed to investigate the associations of urinary OPEs metabolites with asthma and lung function among adolescents and to identify potential effect modifiers. METHODS: Included were 715 adolescents aged 12-19 years old participating in the National Health and Nutrition Examination Survey (NHANES) 2011-2014. Multivariable binary logistic regression and linear regression were used to assess associations with asthma and lung function, respectively. Stratified analyses were conducted to assess the effect modifications of serum sex hormones, vitamin D levels, and body mass index (BMI). RESULTS: After multivariable adjustment, we found that bis(2-chloroethyl) phosphate (BCEP) (3rd tertile [T3] vs 1st tertile [T1], OR = 1.87, 95% CI: 1.08, 3.25; P-trend=0.029) and diphenyl phosphate (DPHP) (T3 vs T1, OR = 2.52, 95%CI: 1.25, 5.04; P-trend=0.013) were associated with elevated odds of asthma in all adolescents. Sex-stratified analyses revealed that associations of these two OPEs metabolites tended to be stronger in males. Meanwhile, BCEP and the molecular sum of OPEs metabolites (∑OPEs) were significantly associated with declined lung function, either in all adolescents or by sex. Furthermore, stratified analyses revealed that positive associations of OPEs metabolites with asthma tended to be stronger among adolescents with insufficient levels of Vitamin D (VD < 50 nmol/L), relatively high levels of total testosterone (≥356 ng/dL and ≥22.5 ng/dL for males and females, respectively), or low levels of estradiol (<19.1 pg/mL and <47.3 pg/mL for males and females, respectively). SIGNIFICANCE: Certain urinary OPEs metabolites, especially DPHP and BCEP, were associated with elevated odds of asthma and declined lung function in adolescents. Such associations might be partly modified by levels of VD and sex steroid hormones. IMPACT STATEMENT: The observed associations of urinary OPEs metabolites with increased risk of asthma and declined lung function highlight the potential hazard of OPEs exposure to respiratory health among adolescents.

Unassisted Clinicians Versus Deep Learning-Assisted Clinicians in Image-Based Cancer Diagnostics: Systematic Review With Meta-analysis.

BACKGROUND: A number of publications have demonstrated that deep learning (DL) algorithms matched or outperformed clinicians in image-based cancer diagnostics, but these algorithms are frequently considered as opponents rather than partners. Despite the clinicians-in-the-loop DL approach having great potential, no study has systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification. OBJECTIVE: We systematically quantified the diagnostic accuracy of clinicians with and without the assistance of DL in image-based cancer identification. METHODS: PubMed, Embase, IEEEXplore, and the Cochrane Library were searched for studies published between January 1, 2012, and December 7, 2021. Any type of study design was permitted that focused on comparing unassisted clinicians and DL-assisted clinicians in cancer identification using medical imaging. Studies using medical waveform-data graphics material and those investigating image segmentation rather than classification were excluded. Studies providing binary diagnostic accuracy data and contingency tables were included for further meta-analysis. Two subgroups were defined and analyzed, including cancer type and imaging modality. RESULTS: In total, 9796 studies were identified, of which 48 were deemed eligible for systematic review. Twenty-five of these studies made comparisons between unassisted clinicians and DL-assisted clinicians and provided sufficient data for statistical synthesis. We found a pooled sensitivity of 83% (95% CI 80%-86%) for unassisted clinicians and 88% (95% CI 86%-90%) for DL-assisted clinicians. Pooled specificity was 86% (95% CI 83%-88%) for unassisted clinicians and 88% (95% CI 85%-90%) for DL-assisted clinicians. The pooled sensitivity and specificity values for DL-assisted clinicians were higher than for unassisted clinicians, at ratios of 1.07 (95% CI 1.05-1.09) and 1.03 (95% CI 1.02-1.05), respectively. Similar diagnostic performance by DL-assisted clinicians was also observed across the predefined subgroups. CONCLUSIONS: The diagnostic performance of DL-assisted clinicians appears better than unassisted clinicians in image-based cancer identification. However, caution should be exercised, because the evidence provided in the reviewed studies does not cover all the minutiae involved in real-world clinical practice. Combining qualitative insights from clinical practice with data-science approaches may improve DL-assisted practice, although further research is required. TRIAL REGISTRATION: PROSPERO CRD42021281372; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=281372.

Pre-pregnancy body mass index and risk of maternal or infant complications with gestational diabetes mellitus as a mediator: A multicenter, longitudinal cohort study in China.

AIMS: We explored the complex relationships between pre-pregnancy body mass index (pBMI) and maternal or infant complications and the mediating role of gestational diabetes mellitus (GDM) in these relationships. METHODS: Pregnant women from 24 hospitals in 15 different provinces of China were enrolled in 2017 and followed through 2018. Propensity score-based inverse probability of treatment weighting, logistic regression, restricted cubic spline models, and causal mediation analysis were utilized. In addition, the E-value method was used to evaluate unmeasured confounding factors. RESULTS: A total of 6174 pregnant women were finally included. Compared to women with a normal pBMI, obese women had a higher risk for gestational hypertension (odds ratio [OR] = 5.38, 95% confidence interval [CI]: 3.48-8.34), macrosomia (OR = 2.65, 95% CI: 1.83-3.84), and large for gestational age (OR = 2.05, 95% CI: 1.45-2.88); 4.73% (95% CI: 0.57%-8.88%), 4.61% (95% CI: 0.51%-9.74%), and 5.02% (95% CI: 0.13%-10.18%) of the associations, respectively, were mediated by GDM. Underweight women had a high risk for low birth weight (OR = 1.42, 95% CI: 1.15-2.08) and small for gestational age (OR = 1.62, 95% CI: 1.23-2.11). Dose-response analyses indicated that 21.0 kg/m2 may be the appropriate tipping point pBMI for risk for maternal or infant complications in Chinese women. CONCLUSION: A high or low pBMI is associated with the risk for maternal or infant complications and partly mediated by GDM. A lower pBMI cutoff of 21 kg/m2 may be appropriate for risk for maternal or infant complications in pregnant Chinese women.

Depressive symptoms, perceived social support, and anticipated HIV stigma among HIV-negative/unknown men who have sex with men in China during the COVID-19 pandemic: A multicenter online cross-sectional study.

OBJECTIVE: To investigate the prevalence of depressive symptoms among human immunodeficiency virus (HIV)-negative/unknown men who have sex with men (MSM) in China and explore the relationship between perceived social support, anticipated HIV stigma, and depressive symptoms. METHODS: Participants in this study were recruited from a gay social networking app (Blued) in China by convenience sampling from December 16, 2020 to March 1, 2021. Perceived Social Support Questionnaire, Anticipated HIV Stigma Questionnaire, and Center for Epidemiologic Studies Depression Scale were used to measure the social support, anticipated HIV stigma, and depressive symptoms of participants. Confirmatory factor analysis was performed to assess the reliability and validity of the measurement model. Structural equation modeling was employed to evaluate the association of perceived social support, anticipated HIV stigma, and depressive symptoms, as well as the mediation effects. RESULTS: Overall, 47.70% (665/1394) of the participants had depressive symptoms. Perceived social support could have both direct and indirect effects on depressive symptoms with the mediating role of anticipated HIV stigma among HIV-negative/unknown MSM. CONCLUSION: Tailored interventions regarding perceived social support and anticipated HIV stigma, such as group therapy, mutual support groups and mindfulness training, with the involvement of non-governmental or governmental organizations, should be taken into account to reduce depressive symptoms and stigma among HIV-negative/unknown MSM in China.

Associations of urinary organophosphate esters metabolites and diet quality with nonalcoholic/metabolic dysfunction-associated fatty liver diseases in adults.

Whether exposure to organophosphate esters (OPEs) is associated with metabolic dysfunction-associated fatty liver disease (MAFLD) and nonalcoholic fatty liver disease (NAFLD) remains unclear. A healthy diet is crucial to metabolic health and dietary intake is also an important route for OPEs exposure. However, the joint associations of OPEs, diet quality, and the effect modification by diet quality remain unknown. This study comprised 2618 adults with complete data on 6 urinary OPEs metabolites, 24 h dietary recalls, and definitions of NAFLD and MAFLD from the 2011-2018 National Health and Nutrition Examination Survey cycles. Multivariable binary logistic regression was applied to assess the associations of OPEs metabolites with NAFLD, MAFLD, and components of MAFLD. We also adopted the quantile g-Computation method to examine the associations of OPEs metabolites mixture. Our results revealed that OPEs metabolites mixture and three individual metabolites [i.e., bis(1,3-dichloro-2-propyl) phosphate (BDCIPP), bis(2-chloroethyl) phosphate, and diphenyl phosphate] were significantly and positively associated with NAFLD and MAFLD (P-trend<0.001), with BDCIPP being identified as the dominant metabolite, whereas the 4 diet quality scores were monotonically and inversely associated with both MAFLD and NAFLD (P-trend<0.001). Of note, 4 diet quality scores were by and large negatively associated with BDCIPP, but not with other OPEs metabolites. Joint association analyses revealed that individuals with higher diet quality and lower BDCIPP concentration tend to have lower odds of having MAFLD and NAFLD in comparison with people in the low diet quality and high BDCIPP group, but the associations of BDCIPP were not modified by diet quality. Our findings suggest that certain OPEs metabolites and diet quality exhibited opposing associations with both MAFLD and NAFLD. Individuals adherent to a healthier diet may have a lower level of certain OPEs metabolites, and thus could have lower odds of having NAFLD and MAFLD.

Associations of metal mixtures with metabolic-associated fatty liver disease and non-alcoholic fatty liver disease: NHANES 2003-2018.

Objective: The hepatotoxicity of exposure to a single heavy metal has been examined in previous studies. However, there is limited evidence on the association between heavy metals mixture and non-alcoholic fatty liver disease (NAFLD) and metabolic-associated fatty liver disease (MAFLD). This study aims to investigate the associations of 13 urinary metals, individually and jointly, with NAFLD, MAFLD, and MAFLD components. Methods: This study included 5,548 adults from the National Health and Nutrition Examination Survey (NHANES) 2003-2018. Binary logistic regression was used to explore the associations between individual metal exposures and MAFLD, NAFLD, and MAFLD components. Bayesian kernel machine regression (BKMR) and Quantile-based g-computation (QGC) were used to investigate the association of metal mixture exposure with these outcomes. Results: In single metal analysis, increased levels of arsenic [OR 1.09 (95%CI 1.03-1.16)], dimethylarsinic acid [1.17 (95%CI 1.07-1.27)], barium [1.22 (95%CI 1.14-1.30)], cobalt [1.22 (95%CI 1.11-1.34)], cesium [1.35 (95%CI 1.18-1.54)], molybdenum [1.45 (95%CI 1.30-1.62)], antimony [1.18 (95%CI 1.08-1.29)], thallium [1.49 (95%CI 1.33-1.67)], and tungsten [1.23 (95%CI 1.15-1.32)] were significantly associated with MAFLD risk after adjusting for potential covariates. The results for NAFLD were similar to those for MAFLD, except for arsenic, which was insignificantly associated with NAFLD. In mixture analysis, the overall metal mixture was positively associated with MAFLD, NAFLD, and MAFLD components, including obesity/overweight, diabetes, and metabolic dysfunction. In both BKMR and QGC models, thallium, molybdenum, tungsten, and barium mainly contributed to the positive association with MAFLD. Conclusion: Our study indicated that exposure to heavy metals, individually or cumulatively, was positively associated with NAFLD, MAFLD, and MAFLD components, including obesity/overweight, diabetes, and metabolic dysfunction. Additional research is needed to validate these findings in longitudinal settings.

The Causal Relationship between the Morning Chronotype and the Gut Microbiota: A Bidirectional Two-Sample Mendelian Randomization Study.

BACKGROUND: Numerous observational studies have documented an association between the circadian rhythm and the composition of the gut microbiota. However, the bidirectional causal effect of the morning chronotype on the gut microbiota is unknown. METHODS: A two-sample Mendelian randomization study was performed, using the summary statistics of the morning chronotype from the European Consortium and those of the gut microbiota from the largest available genome-wide association study meta-analysis, conducted by the MiBioGen consortium. The inverse variance-weighted (IVW), weighted mode, weighted median, MR-Egger regression, and simple mode methods were used to examine the causal association between the morning chronotype and the gut microbiota. A reverse Mendelian randomization analysis was conducted on the gut microbiota, which was identified as causally linked to the morning chronotype in the initial Mendelian randomization analysis. Cochran's Q statistics were employed to assess the heterogeneity of the instrumental variables. RESULTS: Inverse variance-weighted estimates suggested that the morning chronotype had a protective effect on Family Bacteroidaceae (ß = -0.072; 95% CI: -0.143, -0.001; p = 0.047), Genus Parabacteroides (ß = -0.112; 95% CI: -0.184, -0.039; p = 0.002), and Genus Bacteroides (ß = -0.072; 95% CI: -0.143, -0.001; p = 0.047). In addition, the gut microbiota (Family Bacteroidaceae (OR = 0.925; 95% CI: 0.857, 0.999; p = 0.047), Genus Parabacteroides (OR = 0.915; 95% CI: 0.858, 0.975; p = 0.007), and Genus Bacteroides (OR = 0.925; 95% CI: 0.857, 0.999; p = 0.047)) demonstrated positive effects on the morning chronotype. No significant heterogeneity in the instrumental variables, or in horizontal pleiotropy, was found. CONCLUSION: This two-sample Mendelian randomization study found that Family Bacteroidaceae, Genus Parabacteroides, and Genus Bacteroides were causally associated with the morning chronotype. Further randomized controlled trials are needed to clarify the effects of the gut microbiota on the morning chronotype, as well as their specific protective mechanisms.

Stacking Ensemble Method for Gestational Diabetes Mellitus Prediction in Chinese Pregnant Women: A Prospective Cohort Study.

Gestational diabetes mellitus (GDM) is closely related to adverse pregnancy outcomes and other diseases. Early intervention in pregnant women who are at high risk of developing GDM could help prevent adverse health consequences. The study aims to develop a simple model using the stacking ensemble method to predict GDM for women in the first trimester based on easily available factors. We used the data from the Chinese Pregnant Women Cohort Study from July 2017 to November 2018. A total of 6,848 pregnant women in the first trimester were included in the analysis. Logistic regression (LR), random forest (RF), and extreme gradient boosting (XGBoost) were considered as base learners. Optimal feature subsets for each learner were chosen by using recursive feature elimination cross-validation. Then, we built a pipeline to process imbalance data, tune hyperparameters, and evaluate model performance. The learners with the best hyperparameters were employed in the first layer of the proposed stacking method. Their predictions were obtained using optimal feature subsets and served as meta-learner's inputs. Another LR was used as a meta-learner to obtain the final prediction results. Accuracy, specificity, error rate, and other metrics were calculated to evaluate the performance of the models. A paired samples t-test was performed to compare the model performance. In total, 967 (14.12%) women developed GDM. For base learners, the RF model had the highest accuracy (0.638 (95% confidence interval (CI) 0.628-0.648)) and specificity (0.683 (0.669-0.698)) and lowest error rate (0.362 (0.352-0.372)). The stacking method effectively improved the accuracy (0.666 (95% CI 0.663-0.670)) and specificity (0.725 (0.721-0.729)) and decreased the error rate (0.333 (0.330-0.337)). The differences in the performance between the stacking method and RF were statistically significant. Our proposed stacking method based on easily available factors has better performance than other learners such as RF.

Ischemic and haemorrhagic stroke risk estimation using a machine-learning-based retinal image analysis.

Background: Stroke is the second leading cause of death worldwide, causing a considerable disease burden. Ischemic stroke is more frequent, but haemorrhagic stroke is responsible for more deaths. The clinical management and treatment are different, and it is advantageous to classify their risk as early as possible for disease prevention. Furthermore, retinal characteristics have been associated with stroke and can be used for stroke risk estimation. This study investigated machine learning approaches to retinal images for risk estimation and classification of ischemic and haemorrhagic stroke. Study design: A case-control study was conducted in the Shenzhen Traditional Chinese Medicine Hospital. According to the computerized tomography scan (CT) or magnetic resonance imaging (MRI) results, stroke patients were classified as either ischemic or hemorrhage stroke. In addition, a control group was formed using non-stroke patients from the hospital and healthy individuals from the community. Baseline demographic and medical information was collected from participants' hospital medical records. Retinal images of both eyes of each participant were taken within 2 weeks of admission. Classification models using a machine-learning approach were developed. A 10-fold cross-validation method was used to validate the results. Results: 711 patients were included, with 145 ischemic stroke patients, 86 haemorrhagic stroke patients, and 480 controls. Based on 10-fold cross-validation, the ischemic stroke risk estimation has a sensitivity and a specificity of 91.0% and 94.8%, respectively. The area under the ROC curve for ischemic stroke is 0.929 (95% CI 0.900 to 0.958). The haemorrhagic stroke risk estimation has a sensitivity and a specificity of 93.0% and 97.1%, respectively. The area under the ROC curve is 0.951 (95% CI 0.918 to 0.983). Conclusion: A fast and fully automatic method can be used for stroke subtype risk assessment and classification based on fundus photographs alone.