Top Disease Research Articles

Spatial parameters associated with the risk of banana bunchy top disease in smallholder systems.

The Banana Bunchy Top Disease (BBTD), caused by the Banana Bunchy Top Virus (BBTV) is the most important and devastating in many tropical countries. BBTD epidemiology has been little studied, mixed landscape smallholder systems. The relative risks associated with this disease vary between geographical areas and landscapes. This work analyzed the management and vegetation conditions in smallholder gardens to assess the factors linked to landscape-level BBTV transmission and management. Mapping was done in this study area which is in a BBTD-endemic region, involving farmers actively managing the disease, but with household-level decision making. A spatial scanning statistic was used to detect and identify spatial groups at the 5% significance threshold, and a Poisson regression model was used to explore propagation vectors and the effect of surrounding vegetation and crop diversity. Spatial groups with high relative risk were identified in three communities, Dangbo, Houéyogbé, and Adjarra. Significant associations emerged between the BBTD prevalence and some crop diversity, seed systems, and BBTD management linked factors. The identified factors form important candidate management options for the detailed assessment of landscape-scale BBTD management in smallholder communities.

Variabilité de la sensibilité vis-à-vis du Banana Bunchy Top Virus (BBTV) des espèces de Musa spp. cultivées dans le Grand Libreville

Banana Bunchy Top disease is the most devastating viral disease that can attack bananas. Its presence prevents the development of bananas and leads to a decrease in production. It is caused by Banana Bunchy Top Virus (BBTV), the vector agent of which is the aphid aphid Pentalonia nigronervosa. The disease is present in the agroecological zone of the coastal sedimentary basin of Gabon, where the prevalence of the disease is reaching worrying proportions. This study focused on the assessment of varietal resistance of Musa spp. the most common in greater Libreville. The diversity of local banana cultivars can be an asset in the search for varieties resistant to BBTV. The results of this study show that not all cultivars have the same sensitivity. Indeed, dessert cultivars are more susceptible than plantain cultivars. Fougamou and Gros-Michel are the most widely cultivated dessert cultivars in greater Libreville, and are very sensitive to BBTV. Alone, these two cultivars failed to germinate after inoculation of pure ground material from a plant infested with BBTV at the highest stage of the disease. While the plantain cultivars, Obel, ZokEkone and Elate, are much more resistant.

Genome-based identification of beet curly top Iran virus infecting sugar beet in Turkey and investigation of its pathogenicity by agroinfection

Beet curly top disease (BCTD) is a yield-limiting viral infection of sugar beet (Beta vulgaris) throughout the arid and semi-arid regions of the world. Two virus species, belonging to two different genera of the family Geminiviridae (Curtovirus and Becurtovirus) had been described as the disease’s causative agents on sugar beet. Despite the detection of the BCTD in some sugar beet fields of Turkey sixty years ago, the genome based characterization of BCTD-associated viruses have not been studied previously. In this study, 628 sugar beet plants exhibiting BCTD symptoms were collected from fourteen cities in central Anatolia, the major sugar beet production areas in Turkey. PCR assays of these samples using the respective Curtovirus and Becurtovirus genus-specific primers indicated that the Turkish sugar beet samples' viral sequences belong only to the genus Becurtovirus. The results of sequencing and phylogenetic analysis of the partial genome of the virus obtained from fourteen cities confirmed that BCTD-associated virus in Turkish sugar beet fields is beet curly top Iran virus (BCTIV-Becurtovirus) species. The whole genome of the collected viruses from fourteen cities were amplified by the rolling circle amplification (RCA) and the five most phylogenetically diverse viruses obtained from Afyon, Ankara, Adapazarı, Yozgat and Aksaray were sequenced. The results of whole genome sequence analysis indicated >98 % sequence identities with that of a BCTIV variants reported from Urmia province (bordering Turkey) of Iran. A virus genome from Yozgat city had a genomic sequence identity of >97 % with those of BCTIV isolated from cowpea, tomato, pepper and sugar beet in the northern part of Iran. These results suggested that the spread of BCTIV through the region could create a significant threat to the production of sugar beet as well as other agricultural crops. A tandem dimer of a BCTIV-Turkish variant isolated from Ankara city was cloned into Agrobacterium plasmid to be used for agro-infection studies. Agroinoculation of this construct on sugar beet leaves generated severe BCTD symptoms (84 %) which were also confirmed by RCA and qPCR analysis. These results constituted the first genome based characterization of BCTIV Turkish variants and the first report of BCTIV spreading out of Iran.

Characteristic People With Hypertension in Yogyakarta Special Region During The First Year of Covid-19 Pandemics

Since 2017, hypertension was the top first disease in the Yogyakarta Special Region (DIY). It cannot be ignored because hypertension is an entrance for other degenerative diseases. Along with the COVID-19 pandemic at the beginning of 2020 raising our curiosity whether there has been a change in the incidence of hypertension in DIY during this year, then what are its characteristics. This study explores the characteristics of people with hypertension by age group and gender in the first year of the COVID-19 pandemic in the Yogyakarta Special Region. A descriptive study was employed in this study, with the main source was the secondary data from the Yogyakarta Special Region health office, the year 2020. Analysis was conducted by univariate tabulation. Data from the Yogyakarta provincial health office shows that in 2020 there will be an increase of more than eight thousand cases of hypertension. In general, this increase was lower than the increase in the previous two years. In 2020, the highest incidence of hypertension was found in women in the age range of 60-69. Meanwhile, in the (15–19) age group, the majority of cases happened in men. This study shows that during 2020, which was the COVID-19 pandemic, the incidence of hypertension increased but not as high as the previous two years. The majority of hypertension occurred in the 60-69 age group, with the majority in men.

Identification of two novel poleroviruses and the occurrence of Tobacco bushy top disease causal agents in natural plants

Tobacco bushy top disease (TBTD) is a devastating tobacco disease in the southwestern region of China. TBTD in the Yunnan Province is often caused by co-infections of several plant viruses: tobacco bushy top virus (TBTV), tobacco vein distorting virus (TVDV), tobacco bushy top virus satellite RNA (TBTVsatRNA) and tobacco vein distorting virus-associated RNA (TVDVaRNA). Through this study, two new poleroviruses were identified in two TBTD symptomatic tobacco plants and these two novel viruses are tentatively named as tobacco polerovirus 1 (TPV1) and tobacco polerovirus 2 (TPV2), respectively. Analyses of 244 tobacco samples collected from tobacco fields in the Yunnan Province through RT-PCR showed that a total of 80 samples were infected with TPV1 and/or TPV2, and the infection rates of TPV1 and TPV2 were 8.61% and 29.51%, respectively. Thirty-three TPV1 and/or TPV2-infected tobacco samples were selected for further test for TBTV, TVDV, TBTVsatRNA and TVDVaRNA infections. The results showed that many TPV1 and/or TPV2-infected plants were also infected with two or more other assayed viruses. In this study, we also surveyed TBTV, TVDV, TBTVsatRNA and TVDVaRNA infections in a total of 1713 leaf samples collected from field plants belonging to 29 plant species in 13 plant families and from 11 provinces/autonomous regions in China. TVDV had the highest infection rates of 37.5%, while TVDVaRNA, TBTV and TBTVsatRNA were found to be at 23.0%, 12.4% and 8.1%, respectively. In addition, TVDV, TBTV, TBTVsatRNA and TVDVaRNA were firstly detected of co-infection on 10 plants such as broad bean, pea, oilseed rape, pumpkin, tomato, crofton weed etc., and 1 to 4 of the TBTD causal agents were present in the samples collected from Guizhou, Hainan, Henan, Liaoning, Inner mongolia and Tibet autonomous regions. The results indicated that TBTD causal agents are expanding its host range and posing a risk to other crop in the field.

Restriction-free cloning for molecular manipulation and augmented expression of banana bunchy top viral coat protein

The online version contains supplementary material available at 10.1007/s13205-021-03017-x.

Host range and genetic diversity of two polerovirus species associated with cotton bunchy top disease

Host range and genetic diversity of two polerovirus species associated with cotton bunchy top disease

105 The Epigenetics and Plasticity of CD4+ T Cells in Poultry Health

Abstract Marek’s disease (MD) is one of the top priority diseases in chicken. The mechanisms through which immune cells react to virus infection and pathway signals represent the fundamental cell biological question to defeat MD. We hypothesized epigenetic status in immune organs and cells is directly associated with how the Marek’s disease virus (MDV) infection influences intrinsic transcriptional and regulatory networks in MD. To investigate the epigenetics in CD4+ T cells induced by MDV infection, we assembled a multifaceted approach with epigenetics, deep sequencing, and computational methods together to explore the roles of epigenetics in unique inbred lines of chickens. First, a genome-wide transcriptome analysis in the immune organs from resistant line 63 and susceptible line 72 chickens was performed to explore disease resistance mechanisms. MDV infection influences both cytokine-cytokine receptor interaction and cellular development in resistant and susceptible chickens. Second, we examined the epigenetic status of CD4+ T cells induced by MDV infection, including DNA methylations, histone modifications, chromatin accessibility, and 3D chromatin structures. Our results revealed more than 5,000 epigenetic modification changes (FDR< 0.01) and methylation changes (>15,000, FDR< 0.01) caused by MDV infection. Only resistant line 63 chickens could initiate robust adaptive immune responses at the transcription level (>200 genes, FDR< 0.05). The increase in chromatin accessibility (P < 0.001) and chromosome reorganization represented by A/B compartment flipping were related to up-regulated genes induced by MDV infection ten days post-infection in line 63 chickens. Our findings provided a deeper insight into the CD4+ T cell commitment and responses toward viral infection. In particular, the identifications of cis-acting and trans-acting regulations and lipid pathways will improve our understanding of the sequence, structural basis of RNA-protein, and RNA-DNA interactions and serve as the impetus for mechanistic studies to refine the genomic and epigenetic control of MD resistance in poultry.

First report of banana bunchy top disease caused by Banana bunchy top virus in Uganda

First report of banana bunchy top disease caused by <i>Banana bunchy top virus</i> in Uganda

First report of banana bunchy top virus in banana (Musa spp.) and its eradication in Togo.

Banana (including plantain; Musa spp.) is a vegetatively propagated semi-perennial crop in fields and backyard gardens in Togo. Banana bunchy top disease (BBTD), caused by banana bunchy top virus (BBTV, genus Babuvirus) is the most economically important viral disease, infection of which causes severe stunting and production losses of 90-100% within two seasons. The virus is spread by banana aphid, Pentalonia nigronervosa, and through vegetative propagation from infected sources. BBTV occurrence was first reported in West Africa in 2011 with confirmation in Republic of Benin and in Nigeria in 2012 . A regional alliance (www.bbtvalliance.org) has been established for BBTV surveillance through frequent surveys in countries neighboring those affected, such as Togo. The surveys conducted in September 2018 in banana growing areas in Togo revealed plants with typical symptoms (severe stunting, bunchy growth with shortened petioles with chlorotic streaks and yellow leaf margins) in three banana fields. Locations were Tsévié, Préfecture de Zio, (6.44°N, 1.21028°E), Lilicope, Préfecture de Zio in Maritime region (6.56583°N, 1.18639°E), and Amoutchou, Préfecture de l'Ogou in Plateaux region (7.3775°N, 1.17472°E). Leaf samples were collected from symptomatic (N=8) and asymptomatic plants (N=30) and used for DNA extraction followed by a polymerase chain reaction (PCR) for BBTV detection to amplify ~240 bp sequence of DNA-R encoding for core replicase gene. All samples from symptomatic plants (N=8) tested positive and asymptomatic plants were negative. To ascertain virus identity the 240-bp PCR product was purified and sequenced in both directions. A BLAST search of the sequence (NCBI GenBank Acc.# MK073116) revealed 99% identity with DNA-R sequences of BBTV isolates from Africa (e.g., JQ437549-Benin, JN290301-Nigeria). Further analysis of the 240-bp nucleotide sequence with Maximum-likelihood phylogenetic analysis using MEGA-X software has grouped the BBTV isolate with sub-Saharan African sub-clade of the South Pacific group. To further confirm the virus identity, two samples from symptomatic (PCR positive) and asymptomatic (PCR negative) plants from Tsévié were tested by TAS-ELISA using BBTV ELISA reagent set (Cat. No. SRA24700-1000, Agdia, France) following the manufacturers' protocol. Only samples from two symptomatic plants that were positive in PCR reacted positively in TAS-ELISA; asymptomatic plants were negative. BBTV was not observed in any of the 22 locations surveyed as a follow-up in banana producing areas. To our knowledge, this is the first report of BBTV infecting banana in Togo. The plants detected in the three sites were eradicated in the follow-up action implemented by the alliance team together with the Direction de la Protection des Végétaux of Togo. Follow-up surveys were conducted in the same regions in 2019 and 2020 to ensure disease-free status in these sites and other banana producing regions in Togo. Efforts have been made to raise awareness about BBTD recognition, diagnosis, and eradication. To the best of our knowledge this is the first case of rapid detection and eradication of BBTD in sub-Saharan Africa. This study illustrates the importance of regular surveillance for early detection of invasive virus threats and the value of rapid eradication to contain viruses before spread and establishment in a new territory.

What happened to infectious diseases and anti-infective therapy in 2020 beyond COVID-19?

The year 2020 was the year of infectious diseases with the arrival of SARS-CoV-2, which represented a profound change in the world we knew. However, we present a brief description of some of the top infectious diseases articles from 2020 not related with SARS-CoV-2. We reviewed a selection of the most important and relevant achievements in diagnosis and therapy related to bacteremia, nosocomial pneumonia, skin and soft tissue infections, infections by Clostridioides difficile, mycobacterial infections and invasive fungal infections. This year entailed a significant step forward in the indisputable value of the health care stewardship programs.

Trends of High-Impact Studies in Pharmacology and Pharmacy: A Cross-Sectional Study.

Objective: To investigate the trends of high-impact studies in pharmacology and pharmacy research and to provide evidence for future research in the field of pharmacology and pharmacy.Methods: A cross-sectional study was performed to understand the current status of high-impact studies (top 1%) in pharmacology and pharmacy research via InCites tool based on Web of Science Core Collection. VOSViewer software was used to visualize the results. The outcomes included development trends, countries, subject areas, research institutes, collaborative networks, and subject terms.Results: We found 4,273 high-impact (top 1%) studies between 2011 and 2020 in the field of pharmacology and pharmacy. The number of studies increased from 366 in 2011 to 510 in 2020. These studies were mainly distributed in the following Web of Science subject categories: pharmacology and pharmacy (n = 4,188); neurosciences (n = 397); chemistry, multidisciplinary (n = 359); chemistry, medicinal (n = 314); microbiology (n = 301); biotechnology and applied microbiology (n = 280). These studies were cited in 646,855 studies from more than 100 Web of Science subject categories, and studies in pharmacology pharmacy accounted for the largest share of these citations. The top three countries that contributed the highest number of studies were the United States, United Kingdom, and China. The top three institutions that contributed the highest number of studies in the United States were the University of California System, the National Institutes of Health (NIH), and Harvard University. The top research collaborative circle was from universities in the United States. The top international collaborative circle was from universities from the United States, United Kingdom, Australia, and China. The subject-term analysis indicated that cancer was still the top disease, NF-κB was the top signaling pathway, and drug-delivery and nanoparticles were the top methods.Conclusion: The high-impact studies in pharmacology and pharmacy research have grown over time. The United States, the United Kingdom, and China are the top countries that contributed the high-impact studies. Cancer is still the greatest challenge in the field of disease treatment. It calls for more international collaboration in pharmacology and pharmacy research, which will help discover novel drugs.

An Integrative Network Science and Artificial Intelligence Drug Repurposing Approach for Muscle Atrophy in Spaceflight Microgravity.

Muscle atrophy is a side effect of several terrestrial diseases which also affects astronauts severely in space missions due to the reduced gravity in spaceflight. An integrative graph-theoretic network-based drug repurposing methodology quantifying the interplay of key gene regulations and protein–protein interactions in muscle atrophy conditions is presented. Transcriptomic datasets from mice in spaceflight from GeneLab have been extensively mined to extract the key genes that cause muscle atrophy in organ muscle tissues such as the thymus, liver, and spleen. Top muscle atrophy gene regulators are selected by Bayesian Markov blanket method and gene–disease knowledge graph is constructed using the scalable precision medicine knowledge engine. A deep graph neural network is trained for predicting links in the network. The top ranked diseases are identified and drugs are selected for repurposing using drug bank resource. A disease drug knowledge graph is constructed and the graph neural network is trained for predicting new drugs. The results are compared with machine learning methods such as random forest, and gradient boosting classifiers. Network measure based methods shows that preferential attachment has good performance for link prediction in both the gene–disease and disease–drug graphs. The receiver operating characteristic curves, and prediction accuracies for each method show that the random walk similarity measure and deep graph neural network outperforms the other methods. Several key target genes identified by the graph neural network are associated with diseases such as cancer, diabetes, and neural disorders. The novel link prediction approach applied to the disease drug knowledge graph identifies the Monoclonal Antibodies drug therapy as suitable candidate for drug repurposing for spaceflight induced microgravity. There are a total of 21 drugs identified as possible candidates for treating muscle atrophy. Graph neural network is a promising deep learning architecture for link prediction from gene–disease, and disease–drug networks.

THE EFFECT OF INADEQUATE ACCESS TO POTABLE WATER ON THE HEALTH OF THE PEOPLE IN THE WA MUNICIPALITY OF GHANA

Accessibility to safe drinking water is regarded as a fundamental human right since it is essential to preserving healthy livelihoods and the basic human dignity of all human beings. The study examined the effect of inadequate potable water supply on the health of the people in the Wa Municipality of Ghana. Findings of the study revealed that water related diseases are very common in the municipality due to the inadequate supply of potable water. About 55% of respondents, mentioned schistosomiasis as the top disease burden in the area. Again, the analysis of data on water provision and accessibility in the study suggested that most of the residents of the Municipality precisely 69.2% covered distances more than the standard distance of 1km stipulated by World Health Organization in search for potable water. The impacts of the time spent and distance traveled to acquire water in the Municipality were largely experienced by children and women, owing to the fact that in Ghana, water collection is considered to be the primary duty of children and women. Based on the findings the study recommends that more boreholes should be provided in the Wa Municipality to enable the residents have easy access to potable water supply. KEYWORDS: Ghana, Wa Municipality, Potable water accessibility.

Global Burden of Skin Disease Representation in the Literature: Bibliometric Analysis.

The global burden of skin disease may be reduced through research efforts focused on skin diseases with the highest reported disability-adjusted life years. This study evaluates the representation of dermatologic conditions comprising the highest disability-adjusted life years in dermatology literature to identify areas that could benefit from greater research focus. The top 10 skin disorders according to their respective disability-adjusted life years as per the 2013 Global Burden of Disease were identified using previous studies. The top 5 dermatology journals ranked by the 2019 h-index were also identified. A PubMed search of each journal was performed using individual skin disease terms. From 2015 to 2020, all indexed publications pertaining to each disease were recorded and compared to the total number of publications for each journal surveyed. A total of 19,727 papers were published in the 5 journals over the span of 2015-2020. Although melanoma ranked as the eighth highest in disability-adjusted life years, it had the highest representation in the literature (1995/19,727, 10.11%). Melanoma was followed in representation by psoriasis (1936/19,727, 9.81%) and dermatitis (1927/19,727, 9.77%). These 3 conditions comprised a total of 29.69% (5858/19,727) of the total publications, while the remaining 7 skin conditions were represented by a combined 6.79% (1341/19,727) of the total publications. This research identifies gaps in the literature related to the top skin diseases contributing to the global burden of disease. Our study provides insight into future opportunities of focused research on less-studied skin diseases to potentially aid in reducing the global burden of skin disease.

Oat Intake and Risk of Type 2 Diabetes, Cardiovascular Disease and All-Cause Mortality: A Systematic Review and Meta-Analysis.

Cardiovascular disease (CVD) and type 2 diabetes (T2D) remain the top disease and mortality burdens worldwide. Oats have been shown to benefit cardiovascular health and improve insulin resistance. However, the evidence linking oat consumption with CVD, T2D and all-cause mortality remains inconclusive. We conducted a comprehensive systematic review and meta-analysis of prospective cohort studies to evaluate the associations between oat consumption and risks of T2D, CVD and all-cause mortality in the general population. Five electronic databases were searched until September, 2020. Study specific relative risks (RR) were meta-analyzed using random effect models. Of 4686 relevant references, we included 9 articles, based on 8 unique studies and 471,157 participants. Comparing oat consumers versus non-consumers, RRs were 0.86 (95% CI 0.72–1.03) for T2D incidence and 0.73 (95% CI 0.5–1.07) for combined CVD incidence. Comparing participants with highest versus lowest oat intake, RRs were 0.78 (95% CI 0.74–0.82) for T2D incidence, 0.81 (95% CI 0.61–1.08) for CHD incidence and 0.79 (95% CI 0.59–1.07) for stroke. For all-cause mortality one study based on three cohorts found RR for men and women were 0.76 (95% CI 0.69–0.85) and 0.78 (95% CI 0.70–0.87), respectively. Most studies (n = 6) were of fair to good quality. This meta-analysis suggests that consumption of oat could reduce the risk for T2D and all-cause mortality, while no significant association was found for CVD. Future studies should address a lack of standardized methods in assessing overall oat intake and type of oat products, and investigate a dose-dependent response of oat products on cardiometabolic outcomes in order to introduce oat as preventive and treatment options for the public.

Detection of tuberculosis from chest X-ray images: Boosting the performance with vision transformer and transfer learning

Tuberculosis (TB) caused by Mycobacterium tuberculosis is a contagious disease which is among the top deadly diseases in the world. Research in Medical Imaging has been done to provide doctors with techniques and tools to early detect, monitor and diagnose the disease using Artificial Intelligence. Recently, many attempts have been made to automatically recognize TB from chest X-ray (CXR) images. Still, while the obtained performance is encouraging, according to our investigation, many of the existing approaches have been evaluated on small and undiverse datasets. We suppose that such a good performance might not hold for heterogeneous data sources, which originate from real world scenarios. Our present work aims to fill the gap and improve the prediction performance on larger datasets. In particular, we present a practical solution for the detection of tuberculosis from CXR images, making use of cutting-edge Machine Learning and Computer Vision algorithms. We conceptualize a framework by adopting three recent deep neural networks as the main classification engines, namely modified EfficientNet, modified original Vision Transformer, and modified Hybrid EfficientNet with Vision Transformer. Moreover, we also empower the learning process with various augmentation techniques. We evaluated the proposed approach using a large dataset which has been curated by merging various public datasets. The resulting dataset has been split into training, validation, and testing sets which account for 80%, 10%, and 10% of the original dataset, respectively. To further study our proposed approach, we compared it with two state-of-the-art systems. The obtained results are encouraging: the maximum accuracy of 97.72% with AUC of 100% is achieved with ViT_Base_EfficientNet_B1_224. The experimental results demonstrate that our conceived tool outperforms the considered baselines with respect to different quality metrics.

Gastrointestinal tuberculosis: A systematic review of epidemiology, presentation, diagnosis and treatment.

Tuberculosis (TB) once considered a disease of the developing world is infrequent in the developing world too. Its worldwide prevalence with a huge impact on the healthcare system both in economic and health terms has prompted the World Health Organization to make it a top priority infectious disease. Tuberculous infection of the pulmonary system is the most common form of this disease, however, extrapulmonary TB is being increasingly recognized and more often seen in immunocompromised situations. Gastrointestinal TB is a leading extrapulmonary TB manifestation that can defy diagnosis. Overlap of symptoms with other gastrointestinal diseases and limited accuracy of diagnostic tests demands more awareness of this disease. Untreated gastrointestinal TB can cause significant morbidity leading to prolonged hospitalization and surgery. Prompt diagnosis with early initiation of therapy can avoid this. This timely review discusses the epidemiology, risk factors, pathogenesis, clinical presentation, current diagnostic tools and therapy.

Faktor Risiko Lingkungan Kejadian ISPA Pada Balita di Wilayah Kerja Puskesmas Panambungan

Acute respiratory infections (ARI) is a disease that attacks one or more parts of the respiratory tract from the nose to the alveoli or lung. This disease which is caused by various factors (multifactorial) is the top rank disease in Indonesia, and is the biggest cause (17%) of the death of children under five years (toddlers). This study aims to determine the environmental risk factors for the incidence of ARI in children under five in the working area of the Panambungan Health Center. This type of research uses an observational analytic study with a cross-sectional design with a sample of 88 respondents obtained by simple random sampling technique. Data analysis was performed by using chi-square test and the magnitude of the risk with the odds ratio value. The results of statistical tests showed that the use of anti-mosquito coils (p = 0.021; OR = 3.573), kitchen ventilation (p = 0.000; OR = 0.112), and smoking habits of family members significantly affected ARI cases on toddlers in the working area of Panambungan Health Center, Makassar in 2020. Meanwhile, bedroom ventilation (p = 0.538; OR = 0.570) and the type of house floor (p = 0.269; OR = 1.889) did not significantly affect ARI cases on toddlers in the working area of Panambungan Health Center, Makassar in 2020.

Pneumonia Detection using Chest X-Ray Images

Pneumonia is among the top diseases which cause most of the deaths all over the world. Virus, bacteria and fungi can all cause pneumonia. However, it is difficult to judge the pneumonia just by looking at chest X-rays. The aim of this study is to simplify the pneumonia detection process for experts as well as for novices. We suggest a novel deep learning framework for the detection of pneumonia using the concept of transfer learning. In this approach, features from images are extracted using different neural network models pre-trained on Image Net, which then are fed into a classifier for prediction. We prepared five different models and analyzed their performance. Thereafter, we proposed an ensemble model that combines outputs from all pre-trained models, which outperformed individual models, reaching the state-of-the-art performance in pneumonia recognition. Our ensemble model reached an accuracy of 96.4% with a recall of 99.62% on unseen data from the Guangzhou Women and Children’s Medical Center dataset.