Estimating the burden of vitiligo: a systematic review and modelling study.

BACKGROUND: Vitiligo is a chronic autoimmune disease characterised by depigmented skin patches, which can pose substantial psychosocial challenges particularly in individuals with dark skin tones. Despite its impact on quality of life, there is an absence of standardised global epidemiological data. We sought to address this gap with the present study. METHODS: In this study we did a systematic review and modelling analysis to estimate the global, regional, and national prevalence and incidence of vitiligo. We did a comprehensive search of nine digital libraries (PubMed, Embase, Web of Science, Scientific Electronic Library Online, KCI Korean Journal Database, Russian Science Citation Index, Western Pacific Region Index Medicus, Informit, and Health Research and Development Information Network) from inception up to May 25, 2023. We included cross-sectional or cohort studies reporting the incidence rate or prevalence of vitiligo, or data from which incidence rate or prevalence could be calculated, in the general population of a country or area of a country. Summary estimate data were extracted. A main outcome was to estimate the worldwide, regional, and country-specific lifetime prevalence of vitiligo diagnosed by physicians or dermatologists among the general population and in adults and children (as per age groups defined in included studies). We used a Bayesian hierarchical linear mixed model to estimate prevalence, and calculated number of affected individuals using the UN population structure in 2022. In estimating lifetime prevalence, studies reporting point or period prevalence were excluded. Our other main outcome was to estimate incidence rates of vitiligo, but due to a small number of studies, the data on incidence were presented in a descriptive summary. This study was registered on PROSPERO, CRD42023390433. FINDINGS: Our search identified 22 192 records, of which 90 studies met our inclusion criteria. Of these studies, six focused on the incidence of vitiligo, 79 reported on the prevalence of vitiligo, and five provided data on both incidence and prevalence. 71 studies reported on lifetime prevalence. In the most recent years studied, incidence rates in the general population ranged from 24·7 cases (95% CI 24·3-25·2) per 100 000 person-years in South Korea in 2019, to 61·0 cases (60·6-61·4) in the USA in 2017. In individual studies, incidence rates showed an increasing trend over the periods studied. The global lifetime prevalence of vitiligo diagnosed by a physician or dermatologist was estimated at 0·36% (95% credible interval [CrI] 0·24-0·54) in the general population (28·5 million people [95% CrI 18·9-42·6]), 0·67% (0·43-1·07) in the adult population (37·1 million adults [23·9-58·9]), and 0·24% (0·16-0·37) in the child population (5·8 million children [3·8-8·9]). Vitiligo prevalence was higher in adults than in children across all regions. Central Europe and south Asia reported the highest prevalence (0·52% [0·28-1·07] and 0·52% [0·33-0·82], respectively, in the general population). INTERPRETATION: This study highlights the need for standardised epidemiological data collection globally to inform public health policies and improve vitiligo diagnosis and management. Emphasis on the impact on individuals with darker skin tones is crucial to reducing stigma and improving quality of life. Furthermore, our study highlights the need to conduct more research in regions and populations that have been historically under-represented, to effectively address the worldwide burden of vitiligo. FUNDING: None.

Global, Regional, and National Epidemiology of Alopecia Areata: A Systematic Review and Modelling Study.

BACKGROUND: Alopecia areata (AA) is a chronic autoimmune disease that leads to a high psychiatric, economic, and systemic disease burden. A comprehensive understanding of AA epidemiology is essential for evaluating healthcare source utilization; however, there is a lack of systematic approach for summarizing epidemiologic data on AA. OBJECTIVES: To systematically investigate the global, regional, and national incidence and prevalence of AA. METHODS: A structured search was conducted using the Ovid MEDLINE, EMBASE, Cochrane Library, Web of Science, SciELO, and Korean journal databases from their inception date to October 4, 2023. Studies that reported the prevalence or incidence of AA were included. We used a Bayesian hierarchical linear mixed model to analyse the prevalence estimates. The primary outcomes of our study were the global, regional, and national prevalence of physician-diagnosed AA for overall population, adults, and children. The incidence data were summarised descriptively. RESULTS: In total, 88 studies from 28 countries were included in the analysis. The reported incidence of alopecia areata tended to be higher in adults aged 19-50 years, and this trend was consistent with its estimated prevalence. The reported prevalence in overall population tended to be higher in men compared to in women. The estimated lifetime prevalence of AA was 0.10% (95% credible intervals, 0.03%-0.39%) in the general population worldwide, 0.12% (95% credible intervals, 0.02%-0.52%) in adults, and 0.03% (95% credible intervals, 0.01%-0.12%) in children. The estimated prevalence was highest in the Asian region and lowest in the African region. CONCLUSIONS: In this study, 48% of the total Global Burden of Disease regions had insufficient data reporting the prevalence or incidence of AA. Further studies are needed to provide epidemiological information on middle- and low-income countries. Our study can serve as a crucial reference in terms of healthcare policy decisions.

Comparing the diagnostic accuracy of PCR-reverse blot hybridization assay and conventional fungus study in superficial fungal infection of the skin: A systematic review.

BACKGROUND: In superficial fungal infections, prompt diagnosis and treatment are essential to prevent the spread of infection and minimise the impact on patients' quality of life. Traditional diagnostic methods, such as KOH smear and fungal culture, have limitations in terms of sensitivity and turnaround time. Recently, the PCR-reverse blot hybridization assay (PCR-REBA) has been developed for the direct detection of dermatophyte DNA. However, there is a lack of information assessing the diagnostic accuracy of PCR-REBA. OBJECTIVES: This systematic review aimed to evaluate the diagnostic accuracy of PCR-REBA in superficial fungal infections compared to conventional and molecular methods. METHODS: The comprehensive search containing Ovid MEDLINE and Embase databases was conducted on 7 August 2022. Two reviewers independently reviewed the included articles. Quality assessment was performed using the Newcastle-Ottawa Scale tool. RESULTS: The included studies were conducted in Korea (five studies) and the Netherlands (two studies), all of which were conducted in a single institution. The quality assessment of these studies indicated low risk of bias. When compared to the potassium hydroxide (KOH) smear and fungus culture, the sensitivity of PCR-REBA ranged from 85% to 100%, and the positive predictive values ranged from 58.9% to 100%. When compared to the RT-PCR, the sensitivity of PCR-REBA ranged from 93.3% to 100%, and the positive and negative predictive values were 91.6%-99.6% and 81.0%-89.1%, respectively. CONCLUSIONS: The PCR-REBA shows promise as a valuable diagnostic tool for dermatophytosis, offering practical and cost-effective benefits.

Testosterone replacement in men with sexual dysfunction.

BACKGROUND: Clinical practice guidelines recommend testosterone replacement therapy (TRT) for men with sexual dysfunction and testosterone deficiency. However, TRT is commonly promoted in men without testosterone deficiency and existing trials often do not clearly report participants' testosterone levels or testosterone-related symptoms. This review assesses the potential benefits and harms of TRT in men presenting with complaints of sexual dysfunction. OBJECTIVES: To assess the effects of testosterone replacement therapy compared to placebo or other medical treatments in men with sexual dysfunction. SEARCH METHODS: We performed a comprehensive search of CENTRAL (the Cochrane Library), MEDLINE, EMBASE, and the trials registries ClinicalTrials.gov and World Health Organization International Clinical Trials Registry Platform, with no restrictions on language of publication or publication status, up to 29 August 2023. SELECTION CRITERIA: We included randomized controlled trials (RCTs) in men (40 years or over) with sexual dysfunction. We excluded men with primary or secondary hypogonadism. We compared testosterone or testosterone with phosphodiesterase-5 inhibitors (PDEI5I) to placebo or PDE5I alone. DATA COLLECTION AND ANALYSIS: Two review authors independently screened the literature, assessed the risk of bias, extracted data, and rated the certainty of evidence (CoE) according to GRADE using a minimally contextualized approach. We performed statistical analyses using a random-effects model and interpreted them according to standard Cochrane methodology. Predefined primary outcomes were self-reported erectile dysfunction assessed by a validated instrument, sexual quality of life assessed by a validated instrument, and cardiovascular mortality. Secondary outcomes were treatment withdrawal due to adverse events, prostate-related events, and lower urinary tract symptoms (LUTS). We distinguished between short-term (up to 12 months) and long-term (> 12 months) outcomes. MAIN RESULTS: We identified 43 studies with 11,419 randomized participants across three comparisons: testosterone versus placebo, testosterone versus PDE5I, and testosterone with PDE5I versus PDE5I alone. This abstract focuses on the most relevant comparison of testosterone versus placebo. Testosterone versus placebo (up to 12 months) Based on a predefined sensitivity analysis of studies at low risk of bias, and an analysis combing data from the similar International Index of Erectile Function (IIEF-EF) and IIEF-5 instruments, TRT likely results in little to no difference in erectile function assessed with the IIEF-EF (mean difference (MD) 2.37, 95% confidence interval (CI) 1.67 to 3.08; I² = 0%; 6 RCTs, 2016 participants; moderate CoE) on a scale from 6 to 30 with larger values reflecting better erectile function. We assumed a minimal clinically important difference (MCID) of greater than or equal to 4. TRT likely results in little to no change in sexual quality of life assessed with the Aging Males' Symptoms scale (MD -2.31, 95% CI -3.63 to -1.00; I² = 0%; 5 RCTs, 1030 participants; moderate CoE) on a scale from 17 to 85 with larger values reflecting worse sexual quality of life. We assumed a MCID of greater than or equal to 10. TRT also likely results in little to no difference in cardiovascular mortality (risk ratio (RR) 0.83, 95% CI 0.21 to 3.26; I² = 0%; 10 RCTs, 3525 participants; moderate CoE). Based on two cardiovascular deaths in the placebo group and an assumed MCID of 3%, this would correspond to no additional deaths per 1000 men (95% CI 1 fewer to 4 more). TRT also likely results in little to no difference in treatment withdrawal due to adverse events, prostate-related events, or LUTS. Testosterone versus placebo (later than 12 months) We are very uncertain about the longer-term effects of TRT on erectile dysfunction assessed with the IIEF-EF (MD 4.20, 95% CI -2.03 to 10.43; 1 study, 42 participants; very low CoE). We did not find studies reporting on sexual quality of life or cardiovascular mortality. We are very uncertain about the effect of testosterone on treatment withdrawal due to adverse events. We found no studies reporting on prostate-related events or LUTS. AUTHORS' CONCLUSIONS: In the short term, TRT probably has little to no effect on erectile function, sexual quality of life, or cardiovascular mortality compared to a placebo. It likely results in little to no difference in treatment withdrawals due to adverse events, prostate-related events, or LUTS. In the long term, we are very uncertain about the effects of TRT on erectile function when compared to placebo; we did not find data on its effects on sexual quality of life or cardiovascular mortality. The certainty of evidence ranged from moderate (signaling that we are confident that the reported effect size is likely to be close to the true effect) to very low (indicating that the true effect is likely to be substantially different). The findings of this review should help to inform future guidelines and clinical decision-making at the point of care.

All-Cause and Cause-Specific Mortality among Patients with Vitiligo: A Nationwide Population-Based Study in Korea.

Vitiligo is a common autoimmune skin disorder; however, there is limited information about risks of mortality among patients with vitiligo. Therefore, we aimed to investigate the mortality in patients with vitiligo. A population-based cohort study was conducted using the data linkage of the National Health Insurance Service database and the National Death Registry. Patients with incident vitiligo were matched with sociodemographic factors-matched controls without vitiligo in a 1:5 ratio. All-cause and cause-specific mortalities were compared between patients with vitiligo and controls. In total, 107,424 patients with incident vitiligo and 537,120 matched controls were included. The mortality rates were 34.8 and 45.3 per 10,000 person-years in patients and controls, respectively. Patients with vitiligo showed a significantly lower risk of mortality (adjusted hazard ratio = 0.75, 95% confidence interval = 0.72-0.78). The cause-specific mortality from infectious diseases, oncologic diseases, hematologic diseases, endocrine diseases, neurologic diseases, cardiovascular diseases, respiratory diseases, and renal/urogenital disease was significantly lower in patients with vitiligo. Patients with vitiligo were associated with a lower risk of mortality, suggesting that vitiligo-associated autoimmunity might contribute to reduced morbidity and mortality.

Autoimmune and Autoinflammatory Connective Tissue Disorders Following COVID-19.

Importance: Multiple cases of autoimmune and autoinflammatory diseases after COVID-19 have been reported. However, their incidences and risks have rarely been quantified. Objective: To investigate the incidences and risks of autoimmune and autoinflammatory connective tissue disorders after COVID-19. Design, Setting, and Participants: This was a retrospective population-based study conducted between October 8, 2020, and December 31, 2021, that used nationwide data from the Korea Disease Control and Prevention Agency COVID-19 National Health Insurance Service cohort and included individuals who received a diagnosis of COVID-19 via polymerase chain reaction testing and a control group with no evidence of COVID-19 identified from National Health Insurance Service of Korea cohort. Data analysis was conducted from September 2022 to August 2023. Exposures: Receipt of diagnosis of COVID-19. Main Outcomes and Measures: The primary outcomes were the incidence and risk of autoimmune and autoinflammatory connective tissue disorders following COVID-19. A total of 32 covariates, including demographics, socioeconomic statuses, lifestyle factors, and comorbidity profiles, were balanced through inverse probability weighting. The incidences and risks of autoimmune and autoinflammatory connective tissue disorders were compared between the groups using multivariable Cox proportional hazard analyses. Results: A total of 354 527 individuals with COVID-19 (mean [SD] age, 52.24 [15.55] years; 179 041 women [50.50%]) and 6 134 940 controls (mean [SD] age, 52.05 [15.63] years; 3 074 573 women [50.12%]) were included. The risks of alopecia areata (adjusted hazard ratio [aHR], 1.12; 95% CI, 1.05-1.19), alopecia totalis (aHR, 1.74; 95% CI, 1.39-2.17), antineutrophil cytoplasmic antibody-associated vasculitis (aHR, 2.76; 95% CI, 1.64-4.65), Crohn disease (aHR, 1.68; 95% CI, 1.31-2.15), and sarcoidosis (aHR, 1.59; 95% CI, 1.00-2.52) were higher in the COVID-19 group. The risks of alopecia totalis, psoriasis, vitiligo, vasculitis, Crohn disease, ulcerative colitis, rheumatoid arthritis, adult-onset Still disease, Sjögren syndrome, ankylosing spondylitis, and sarcoidosis were associated with the severity of COVID-19. Conclusions and Relevance: In this retrospective cohort study, COVID-19 was associated with a substantial risk for autoimmune and autoinflammatory connective tissue disorders, indicating that long-term management of patients with COVID-19 should include evaluation for such disorders.

Deep Learning-Based Evaluation of Ultrasound Images for Benign Skin Tumors.

In this study, a combined convolutional neural network for the diagnosis of three benign skin tumors was designed, and its effectiveness was verified through quantitative and statistical analysis. To this end, 698 sonographic images were taken and diagnosed at the Department of Dermatology at Severance Hospital in Seoul, Korea, between 10 November 2017 and 17 January 2020. Through an empirical process, a convolutional neural network combining two structures, which consist of a residual structure and an attention-gated structure, was designed. Five-fold cross-validation was applied, and the train set for each fold was augmented by the Fast AutoAugment technique. As a result of training, for three benign skin tumors, an average accuracy of 95.87%, an average sensitivity of 90.10%, and an average specificity of 96.23% were derived. Also, through statistical analysis using a class activation map and physicians' findings, it was found that the judgment criteria of physicians and the trained combined convolutional neural network were similar. This study suggests that the model designed and trained in this study can be a diagnostic aid to assist physicians and enable more efficient and accurate diagnoses.

Prevalence and incidence of comorbid diseases and mortality risk associated with lichen planopilaris: a Korean nationwide population-based study.

BACKGROUND: Various comorbid diseases have been reported in patients with lichen planopilaris (LPP); however, data regarding the risks of incident diseases and mortality are lacking. OBJECTIVES: To investigate the risks of incident diseases and mortality associated with LPP. METHODS: This was a retrospective nationwide population-based study, using data from the National Health Insurance Service Database of Korea from 2002 to 2019. Patients aged ≥ 18 years with three or more documented medical visits for LPP were included. The adjusted hazard ratios (aHRs) for incident disease outcomes and mortality were compared with 1 : 20 age-, sex-, insurance type- and income-level-matched controls. RESULTS: In total, 2026 patients with LPP and 40 520 controls were analysed. The risks of incident systemic lupus erythematosus [aHR 1.91, 95% confidence interval (CI) 1.21-3.03], psoriasis (aHR 3.42, 95% CI 2.83-4.14), rheumatoid arthritis (aHR 1.39, 95% CI 1.19-1.63), lichen planus (aHR, 10.07, 95% CI 7.17-14.15), atopic dermatitis (aHR 2.15, 95% CI 1.90-2.44), allergic rhinitis (aHR 1.29, 95% CI 1.13-1.49), thyroid diseases (hyperthyroidism: aHR 1.42, 95% CI 1.14-1.77, hypothyroidism aHR 1.19 95% CI 1.01-1.41, and thyroiditis: aHR, 1.35, 95% CI 1.08-1.69), nonmelanoma skin cancer (aHR 2.33, 95% CI 1.00-5.44) and vitamin D deficiency (aHR 1.23, 95% CI 1.03-1.47) were higher in patients with LPP. Patients with LPP had a higher mortality rate than controls (aHR 1.30, 95% CI 1.04-1.61), although the risk was not significant after adjusting for comorbidities (aHR 1.08, 95% CI 0.87-1.34). CONCLUSIONS: Patients with LPP had a higher risk of various diseases following LPP diagnosis. Close follow-up is needed to optimize comprehensive patient care.

CoAt-Mixer: Self-attention deep learning framework for left ventricular hypertrophy using electrocardiography.

Left ventricular hypertrophy is a significant independent risk factor for all-cause mortality and morbidity, and an accurate diagnosis at an early stage of heart change is clinically significant. Electrocardiography is the most convenient, economical, and non-invasive method for screening in primary care. However, the coincidence rate of the actual left ventricular hypertrophy and diagnostic findings was low, consequently increasing the interest in algorithms using big data and deep learning. We attempted to diagnose left ventricular hypertrophy using big data and deep learning algorithms, and aimed to confirm its diagnostic power according to the differences between males and females. This retrospective study used electrocardiographs obtained at Yonsei University Wonju Severance Christian Hospital, Wonju, Korea, from October 2010 to February 2020. Binary classification was performed for primary screening for left ventricular hypertrophy. Three datasets were used for the experiment: the male, female, and entire dataset. A cutoff for binary classification was defined as the meaningful as a screening test (<132 g/m2 vs. ≥132 g/m2, <109 g/m2 vs. ≥109 g/m2). Six types of input were used for the classification tasks. We attempted to determine whether electrocardiography had predictive power for left ventricular hypertrophy diagnosis. For the entire dataset, the model achieved an area under the receiver operating characteristic (AUROC) curve of 0.836 (95% CI, 0.833-838) with a sensitivity of 78.37% (95% CI, 76.79-79.95). For the male dataset, the AUROC was 0.826 (95% CI, 0.822-830) with a sensitivity of 76.73% (95% CI, 75.14-78.33). For the female dataset, the AUROC was 0.772 (95% CI, 0.769-775) with a sensitivity of 72.90% (95% CI, 70.33-75.46). Our model confirmed that left ventricular hypertrophy can be classified to some extent using electrocardiography, demographics, and electrocardiography features. In particular, a learning environment that considered gender differences was constructed. Consequently, the difference in diagnostic power between men and women was confirmed. Our model will help patients with suspected left ventricular hypertrophy to undergo screening tests at a low cost. In addition, our research and attempts will show the expected effect that gender-consideration approaches can help with various currently proposed diagnostic methods.

Risk of autoimmune skin and connective tissue disorders after mRNA-based COVID-19 vaccination.

BACKGROUND: Data on the association between the development of autoimmune diseases and COVID-19 vaccination are limited. OBJECTIVE: To investigate the incidence and risk of autoimmune connective tissue disorders following mRNA-based COVID-19 vaccination. METHODS: This nationwide population-based study was conducted in South Korea. Individuals who received vaccination between September 8, 2020-December 31, 2021, were identified. Historical prepandemic controls were matched for age and sex in 1:1 ratio. The incidence rate and risk of disease outcomes were compared. RESULTS: A total of 3,838,120 vaccinated individuals and 3,834,804 controls without evidence of COVID-19 were included. The risk of alopecia areata, alopecia totalis, primary cicatricial alopecia, psoriasis, vitiligo, anti-neutrophil cytoplasmic antibody-associated vasculitis, sarcoidosis, Behcet disease, Crohn disease, ulcerative colitis, rheumatoid arthritis, systemic lupus erythematosus, systemic sclerosis, Sjogren syndrome, ankylosing spondylitis, dermato/polymyositis, and bullous pemphigoid was not significantly higher in vaccinated individuals than in controls. The risk was comparable according to age, sex, type of mRNA-based vaccine, and cross-vaccination status. LIMITATIONS: Possible selection bias and residual confounders. CONCLUSION: These findings suggest that most autoimmune connective tissue disorders are not associated with a significant increase in risk. However, caution is necessary when interpreting results for rare outcomes due to limited statistical power.

Autoimmune, Inflammatory, Atopic, Thyroid, and Psychiatric Outcomes of Offspring Born to Mothers With Alopecia Areata.

Importance: Alopecia areata (AA) is associated with diverse autoimmune and psychiatric disorders. However, an investigation on the long-term outcomes for offspring born to mothers diagnosed with AA is lacking. Objective: To investigate the risks for autoimmune, inflammatory, atopic, thyroid, and psychiatric outcomes of offspring born to mothers with AA. Design, Setting, and Participants: This retrospective population-based birth cohort study used the linked birth registration database with the Nationwide Health Insurance Service database of Korea. The participants included all newborns born to mothers with 3 or more visits with International Classification of Diseases, Tenth Revision code of L63 and 1:10 birth year, sex, insurance, income, and location of residence-matched control offspring born to mothers without AA during the years from 2003 to 2015. The analysis was conducted from July 2022 to January 2023. Exposure: Maternal AA. Main Outcomes and Measures: The occurrence of the following diseases was measured in newborns from birth to December 31, 2020: AA, alopecia totalis/universalis (AT/AU), vitiligo, psoriasis, inflammatory bowel disease, rheumatoid arthritis, atopic dermatitis, allergic rhinitis, asthma, hyperthyroidism, hypothyroidism, Graves disease, Hashimoto thyroiditis, attention-deficit hyperactivity disorder, mood disorder, and anxiety disorder. Multivariable Cox proportional hazard analyses were performed with the following covariates: birth year, age, insurance type, income level, location of residence, maternal age, mode of delivery, maternal history of atopic disorders, and autoimmune disorders. Results: In total, 67 364 offspring born to 46 352 mothers with AA and 673 640 controls born to 454 085 unaffected mothers were analyzed. The risk of AA (adjusted hazard ratio [aHR], 2.08; 95% CI, 1.88-2.30), AT/AU (aHR, 1.57; 95% CI, 1.18-2.08), vitiligo (aHR, 1.47; 95% CI, 1.32-1.63), atopic disorders (aHR, 1.07; 95% CI, 1.06-1.09), hypothyroidism (aHR, 1.14; 95% CI, 1.03-1.25), and psychiatric disorders (aHR, 1.15; 95% CI, 1.11-1.20) was significantly increased in offspring born to mothers with AA. Among them, 5088 born to mothers with AT/AU were at much greater risk for the development of AT/AU (aHR, 2.98; 95% CI, 1.48-6.00) and psychiatric disorders (aHR, 1.27; 95% CI, 1.12-1.44). Conclusions and Relevance: In this Korean retrospective population-based birth cohort study, maternal AA was associated with the development of autoimmune/inflammatory, atopic, thyroid, and psychiatric disorders in their offspring. Clinicians and parents need to be aware of the potential for these comorbidities to occur.

Deep Learning Algorithms for Estimation of Demographic and Anthropometric Features from Electrocardiograms.

The electrocardiogram (ECG) has been known to be affected by demographic and anthropometric factors. This study aimed to develop deep learning models to predict the subject's age, sex, ABO blood type, and body mass index (BMI) based on ECGs. This retrospective study included individuals aged 18 years or older who visited a tertiary referral center with ECGs acquired from October 2010 to February 2020. Using convolutional neural networks (CNNs) with three convolutional layers, five kernel sizes, and two pooling sizes, we developed both classification and regression models. We verified a classification model to be applicable for age (<40 years vs. ≥40 years), sex (male vs. female), BMI (<25 kg/m2 vs. ≥25 kg/m2), and ABO blood type. A regression model was also developed and validated for age and BMI estimation. A total of 124,415 ECGs (1 ECG per subject) were included. The dataset was constructed by dividing the entire set of ECGs at a ratio of 4:3:3. In the classification task, the area under the receiver operating characteristic (AUROC), which represents a quantitative indicator of the judgment threshold, was used as the primary outcome. The mean absolute error (MAE), which represents the difference between the observed and estimated values, was used in the regression task. For age estimation, the CNN achieved an AUROC of 0.923 with an accuracy of 82.97%, and a MAE of 8.410. For sex estimation, the AUROC was 0.947 with an accuracy of 86.82%. For BMI estimation, the AUROC was 0.765 with an accuracy of 69.89%, and a MAE of 2.332. For ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98%. For the ABO blood type estimation, the CNN showed an inferior performance, with a top-1 accuracy of 31.98% (95% CI, 31.98-31.98%). Our model could be adapted to estimate individuals' demographic and anthropometric features from their ECGs; this would enable the development of physiologic biomarkers that can better reflect their health status than chronological age.

Automated Mass Screening for Comorbidities of Vitiligo Using the National Health Insurance Database.

Although the study design for identifying specific disease associations using a health insurance database has been well-established, few studies explore unknown comorbidities. We conducted a series of automated case-control studies for all International Classification of Disease, Tenth Revision, Clinical Modification diagnostic codes (A01-Z99) using the Korean National Health Insurance database from 2007 to 2017 to reveal undiscovered disease associations of vitiligo. A total of 90,297 patients with vitiligo and 90,297 age- and sex-matched controls without vitiligo were included, and disease associations for 1,265 relevant diagnostic codes were screened. A meta-analysis of the individual ORs for each International Classification of Disease, Tenth Revision code was performed to identify the possibility of selection bias. Finally, the association with vitiligo was significantly increased in 45 diseases and decreased in 6 diseases. We not only reaffirmed the positive correlation between vitiligo and other autoimmune diseases but also observed associations with obsessive-compulsive disorder and melanoma. In contrast, femur fracture showed a negative correlation. In this study, we attempted an automated mass screening and suggested a possible selection bias. In the era of large-scale databases, a systematic and comprehensive approach might be needed.