Prediction of Skin Diseases Using Machine Learning

Skin disease rates have been increasing over the past few decades. It has led to both fatal and non-fatal disabilities all around the world, especially in those areas where medical resources are not good enough. Early diagnosis of skin diseases increases the chances of cure significantly. Therefore, this work is comparing six machine learning algorithms, namely KNN, random forest, neural network, naïve bayes, logistic regression, and SVM, for the prediction of the skin diseases. The information gain, gain ratio, gini decrease, chi-square, and relieff are used to rank the features. This work comprises the introduction, literature review, and proposed methodology parts. In this research paper, a new method of analyzing skin disease has been proposed in which six different data mining techniques are used to develop an ensemble method that integrates all the six data mining techniques as a single one. The ensemble method used on the dermatology dataset gives improved result with 94% accuracy in comparison to other classifier algorithms and hence is more effective in this area.

Multimorbidity among Diverse Communities in New England: Findings from the Healthy Aging Data Reports

The risk for multimorbidity increases with age. Community burden of comorbidities in New England (NE) was assessed by comparing state and community rates of two measures (having no comorbidities and having 4 or more) among Medicare beneficiaries age 65+ in CT, MA, NH, and RI. Data sources were the Medicare Current Beneficiary Summary File (2014-2017) and the American Community Survey (2014-2018). Small area estimation techniques were used to calculate age-sex adjusted community rates. Multimorbidity was measured as people with zero or with 4 or more of the following chronic conditions: Alzheimer’s disease, asthma, atrial fibrillation, cancer (breast, colorectal, lung, and prostate), kidney disease, COPD, depression, diabetes, congestive heart failure, hypertension, hyperlipidemia, ischemic heart disease, osteoporosis, arthritis, and stroke. Rates for 4+ conditions: RI 63.8% (45.76-70.69%), CT 61.8% (47.82-70.05%), MA 60.7% (40-74.96%), NH 54.4% (36.67-62.99%). Results were mapped, showing the statewide and regional distribution of rates. Rates were much higher for having 4+ chronic conditions than not having any comorbidities. RI had the highest rates of 4+ and in MA the highest chronic disease rates were found in lower socioeconomic communities. CT has the highest number of diverse older residents and dual-eligible beneficiaries for Medicare and Medicaid in NE. The rates show late-life health disparities that have implications for independent living, quality of life, and mortality suggesting the need for policies to provide equitable access to care and resources to disadvantaged NE communities.

The association between maternal cytomegalovirus urinary excretion and congenital infection rate

Background In utero Cytomegalovirus (CMV) vertical transmission occurs predominantly during primary maternal infection. There are no known non-invasive methods for diagnosis of fetal infection before delivery, however some risk factors have been suggested. We aimed to evaluate the association between maternal CMV urinary excretion and congenital CMV infection. Methods A retrospective cohort study of all women who were diagnosed with primary CMV infection during pregnancy in a single university affiliated tertiary medical center, between 2012 and 2016. We examined congenital CMV infection and disease rates among infants born to women with and without CMV urinary excretion. Results Overall, 126 women were included, 77 in the positive urinary excretion group, and 49 in the negative urinary excretion group. There was no difference in maternal symptoms between the groups. We found no difference in congenital CMV infection and disease rates between infants born to women with and without urinary excretion of CMV (congenital infection rate 37.1% vs. 24.4%, p = 0.209, congenital disease rate of 18.2% vs. 22.4%, p = 0.648). Women with positive urinary CMV excretion had lower IgG avidity values (36.7% vs 54.6%, p = 0.007), with no additional difference in serology pattern. Compared to asymptomatic women, those with CMV related symptoms did not have significantly higher rates of urinary excretion of CMV (70% vs. 60.5%, p = 0.38) or congenital infection rates (40.7% vs. 31.2%, p = 0.48). Conclusion Among infants of women with primary CMV infection in pregnancy, we did not find an association between urinary excretion of CMV and congenital CMV infection.

The interrelationship between female reproductive aging and survival

The link between survival and reproductive function is demonstrated across many species and is under both long-term evolutionary pressures and short-term environmental pressures. Loss of reproductive function is common in mammals and is strongly correlated with increased rates of disease in both males and females. However, the reproduction-associated change in disease rates is more abrupt and more severe in women, who benefit from a significant health advantage over men until the age of menopause. Young women with early ovarian failure also suffer from increased disease risks, further supporting the role of ovarian function in female health. Contemporary experiments where the influence of young ovarian tissue has been restored in post-reproductive-aged females with surgical manipulation were found to increase survival significantly. In these experiments, young, intact ovaries were used to replace the aged ovaries of females that had already reached reproductive cessation. As has been seen previously in primitive species, when the young mammalian ovaries were depleted of germ cells prior to transplantation to the post-reproductive female, survival was increased even further than with germ cell-containing young ovaries. Thus, extending reproductive potential significantly increases survival and appears to be germ cell and ovarian hormone-independent. The current review will discuss historical and contemporary observations and theories that support the link between reproduction and survival and provide hope for future clinical applications to decrease menopause-associated increases in disease risks.

Increased Prevalence of Familial Autoimmune Disease in Children With Opsoclonus-Myoclonus Syndrome

Background and ObjectivesOpsoclonus-myoclonus syndrome (OMS) is a rare autoimmune disorder associated with neuroblastoma in children, although idiopathic and postinfectious etiologies are present in children and adults. Small cohort studies in homogenous populations have revealed elevated rates of autoimmunity in family members of patients with OMS, although no differentiation between paraneoplastic and nonparaneoplastic forms has been performed. The objective of this study was to investigate the prevalence of autoimmune disease in first-degree relatives of pediatric patients with paraneoplastic and nonparaneoplastic OMS.MethodsA single-center cohort study of consecutively evaluated children with OMS was performed. Parents of patients were prospectively administered surveys on familial autoimmune disease. Rates of autoimmune disease in first-degree relatives of pediatric patients with OMS were compared using Fisher exact t test and χ2 analysis: (1) between those with and without a paraneoplastic cause and (2) between healthy and disease (pediatric multiple sclerosis [MS]) controls from the United States Pediatric MS Network.ResultsThirty-five patients (18 paraneoplastic, median age at onset 19.0 months; 17 idiopathic, median age at onset 25.0 months) and 68 first-degree relatives (median age 41.9 years) were enrolled. One patient developed systemic lupus erythematosus 7 years after OMS onset. Paraneoplastic OMS was associated with a 50% rate of autoimmune disease in a first-degree relative compared with 29% in idiopathic OMS (p = 0.31). The rate of first-degree relative autoimmune disease per OMS case (14/35, 40%) was higher than healthy controls (86/709, 12%; p < 0.001) and children with pediatric MS (101/495, 20%; p = 0.007).DiscussionIn a cohort of pediatric patients with OMS, there were elevated rates of first-degree relative autoimmune disease, with no difference in rates observed between paraneoplastic and idiopathic etiologies, suggesting an autoimmune genetic contribution to the development of OMS in children.

Clinical characteristics of non-radiographic versus radiographic axial spondyloarthritis in Asia and non-radiographic axial spondyloarthritis in other regions: results of the cross-sectional ASAS-COMOSPA study

ObjectivesTo delineate characteristics of non-radiographic axial spondyloarthritis (nr-axSpA) in Asia versus non-Asian regions, and compare radiographic axSpA (r-axSpA) with nr-axSpA within Asia.MethodsData were collected from the Assessment of SpondyloArthritis international Society-COMOrbidities in SPondyloArthritis database. Categorising patients by region, we compared clinical characteristics between nr-axSpA from Asia vs elsewhere (Europe, the Americas and Africa). Within Asians, we additionally compared patient characteristics of those with nr-axSpA versus r-axSpA.ResultsAmong 3984 SpA cases, 1094 were from Asian countries. Of 780 axSpA patients in Asia, 112 (14.4%) had nr-axSpA, less than in non-Asian countries (486/1997, 24.3%). Nr-axSpA patients in Asia were predominantly male (75.9% vs 47.1%), younger at onset (22.8 vs 27.8 years) and diagnosis (27.2 vs 34.5 years), and experienced less diagnostic delay (1.9 vs 2.9 years) compared with nr-axSpA in non-Asian countries. Nr-axSpA in Asia exhibited higher human leucocyte antigens-B27 prevalence (90.6% vs 61.9%), fewer peripheral SpA features (53.6% vs 66.3%) and similar extra-articular and comorbid disease rates compared with those with nr-axSpA in non-Asian countries. Disease activity, functional impairment and MRI sacroiliitis were less in nr-axSpA in Asia, with higher rates of non-steroidal anti-inflammatory drug response and less methotrexate and biological disease-modifying antirheumatic drugs use. Within Asia, r-axSpA showed higher disease activity and structural damage compared with nr-axSpA, with no differences in other features.ConclusionAmong axSpA, lower frequency of nr-axSpA was observed in Asia. Our results offer an opportunity to better understand clinical characteristics and optimise diagnostic strategies, such as ensuring access and availability of MRI resources for accurate diagnosis of nr-axSpA in Asia.

Burden of disease among the world’s poorest billion people: An expert-informed secondary analysis of Global Burden of Disease estimates

Background The health of populations living in extreme poverty has been a long-standing focus of global development efforts, and continues to be a priority during the Sustainable Development Goal era. However, there has not been a systematic attempt to quantify the magnitude and causes of the burden in this specific population for almost two decades. We estimated disease rates by cause for the world’s poorest billion and compared these rates to those in high-income populations. Methods We defined the population in extreme poverty using a multidimensional poverty index. We used national-level disease burden estimates from the 2017 Global Burden of Disease Study and adjusted these to account for within-country variation in rates. To adjust for within-country variation, we looked to the relationship between rates of extreme poverty and disease rates across countries. In our main modeling approach, we used these relationships when there was consistency with expert opinion from a survey we conducted of disease experts regarding the associations between household poverty and the incidence and fatality of conditions. Otherwise, no within-country variation was assumed. We compared results across multiple approaches for estimating the burden in the poorest billion, including aggregating national-level burden from the countries with the highest poverty rates. We examined the composition of the estimated disease burden among the poorest billion and made comparisons with estimates for high-income countries. Results The composition of disease burden among the poorest billion, as measured by disability-adjusted life years (DALYs), was 65% communicable, maternal, neonatal, and nutritional (CMNN) diseases, 29% non-communicable diseases (NCDs), and 6% injuries. Age-standardized DALY rates from NCDs were 44% higher in the poorest billion (23,583 DALYs per 100,000) compared to high-income regions (16,344 DALYs per 100,000). Age-standardized DALY rates were 2,147% higher for CMNN conditions (32,334 DALYs per 100,000) and 86% higher for injuries (4,182 DALYs per 100,000) in the poorest billion, compared to high-income regions. Conclusion The disease burden among the poorest people globally compared to that in high income countries is highly influenced by demographics as well as large disparities in burden from many conditions. The comparisons show that the largest disparities remain in communicable, maternal, neonatal, and nutritional diseases, though NCDs and injuries are an important part of the “unfinished agenda” of poor health among those living in extreme poverty.

A mathematical model to estimate the incidence of child wasting in Yemen

Introduction The ongoing civil war in Yemen has severely restricted imports of food and fuel, disrupted livelihoods and displaced millions, worsening already high pre-war levels of food insecurity. Paired with frequent outbreaks of disease and a collapsed health system, this has brought rates of wasting in children under five to the country’s highest recorded levels, which continue to increase as the crisis worsens and aid becomes increasingly limited. In their planning of services to treat and prevent wasting in children, humanitarian agencies rely on a standard calculation to estimate the expected number of cases for the coming year, where incidence is estimated from prevalence and the average duration of an episode of wasting. The average duration of an episode of moderate and severe wasting is currently estimated at 7.5 months—a globally-used value derived from historical cohort studies. Given that incidence varies considerably by context—where food production and availability, treatment coverage and disease rates all vary—a single estimate cannot be applied to all contexts, and especially not a highly unstable crisis setting such as Yemen. While recent studies have aimed to derive context-specific incidence estimates in several countries, little has been done to estimate the incidence of both moderate and severe wasting in Yemen. Methods In order to provide context-specific estimates of the average duration of an episode, and resultingly, incidence correction factors for moderate and severe wasting, we have developed a Markov model. Model inputs were estimated using a combination of treatment admission and outcome records compiled by the Yemen Nutrition Cluster, 2018 and 2019 SMART surveys, and other estimates from the literature. The model derived estimates for the governorate of Lahj, Yemen; it was initialized using August 2018 SMART survey prevalence data and run until October 2019—the date of the subsequent SMART survey. Using a process of repeated model calibration, the incidence correction factors for severe wasting and moderate wasting were found, validating the resulting prevalence against the recorded value from the 2019 SMART survey. Results The average durations of an episode of moderate and severe wasting were estimated at 4.86 months, for an incidence correction factor k of 2.59, and 3.86 months, for an incidence correction factor k of 3.11, respectively. It was found that the annual caseload of moderate wasting was 36% higher and the annual caseload of severe wasting 58% higher than the originally-assumed values, estimated with k = 1.6. Conclusion The model-derived incidence rates, consistent with findings from other contexts that a global incidence correction factor cannot be sufficient, allow for improved, context-specific estimates of the burden of wasting in Yemen. In crisis settings such as Yemen where funding and resources are extremely limited, the model’s outputs holistically capture the burden of wasting in a way that may guide effective decision-making and may help ensure that limited resources are allocated most effectively.

The drop in reported invasive pneumococcal disease among adults during the first COVID-19 wave in the Netherlands explained.

Streptococcus pneumoniae is the main bacterial pathogen causing respiratory infections. Since the COVID-19 pandemic emerged, less pneumococcal disease was identified by surveillance systems around the world. Measures to prevent transmission of SARS-CoV-2 also reduce transmission of pneumococci, but this would gradually lead to lower disease rates. Here, we explore additional factors that have contributed to the instant drop in pneumococcal disease cases captured in surveillance. Our observations on referral practices and other impediments to diagnostic testing indicate that residual IPD has likely occurred but remained undetected by conventional hospital-based surveillance. Depending on setting, we discuss alternative monitoring strategies that could improve sight on pneumococcal disease dynamics.

The Effect of District Health Spending on Disease Rates in Sumatra Island

This study aims to find the effect of district health spending on disease rates namely dengue fever, diarrhea, and tuberculosis in 130 districts in Sumatra Island in 2016. A quantitative approach with 3 multiple linear regression (MLR) methods that employ robust standard errors is used for this study. The study finds that district health spending reduces the number of dengue fever, diarrhea, and tuberculosis, but not significantly. This condition can be caused by the inefficient use of district health expenditure. This study finds the number of health centers has negative and significant effect on the number of dengue fever, diarrhea, and tuberculosis. Conversely, population and population density have a positive and significant effect on dengue fever, diarrhea, and tuberculosis. Economic losses due to diseases like dengue fever, diarrhea, and tuberculosis are very high. Therefore, the government must use effective and various policies to overcome the problem of existing diseases, one of which is to improve the efficiency of using the health budget. The government should also control birth rates to reduce population growth and encourage transmigration to reduce population density.