Early identification of disease progression in ALK-rearranged lung cancer using circulating tumor DNA analysis

Targeted kinase inhibitors improve the prognosis of lung cancer patients with ALK alterations (ALK+). However, due to the emergence of acquired resistance and varied clinical trajectories, early detection of disease progression is warranted to guide patient management and therapy decisions. We utilized 343 longitudinal plasma DNA samples from 43 ALK+ NSCLC patients receiving ALK-directed therapies to determine molecular progression based on matched panel-based targeted next-generation sequencing (tNGS), and shallow whole-genome sequencing (sWGS). ALK-related alterations were detected in 22 out of 43 (51%) patients. Among 343 longitudinal plasma samples analyzed, 174 (51%) were ctDNA-positive. ALK variant and fusion kinetics generally reflected the disease course. Evidence for early molecular progression was observed in 19 patients (44%). Detection of ctDNA at therapy baseline indicated shorter times to progression compared to cases without mutations at baseline. In patients who succumbed to the disease, ctDNA levels were highly elevated towards the end of life. Our results demonstrate the potential utility of these NGS assays in the clinical management of ALK+ NSCLC.

Acute respiratory infection symptoms and COVID-19 testing behaviour: results based on South Australian health surveys

Background Effective syndromic surveillance alongside COVID-19 testing behaviours in the population including in higher risk and hard to reach subgroups is vital to detect re-emergence of COVID-19 transmission in the community. The aim of this paper was to identify the prevalence of acute respiratory infection symptoms and coronavirus testing behaviour among South Australians using data from a population based survey. Methods We used cross-sectional data from the 2020 state-wide population level health survey on 6857 respondents aged 18 years and above. Descriptive statistics were used to explore the risk factors and multivariable logistic regression models were used to assess the factors associated with the acute respiratory infection symptoms and coronavirus testing behaviour after adjusting for gender, age, household size, household income, Aboriginal and/or Torres Strait Islander status, SEIFA, Country of birth, number of chronic diseases, wellbeing, psychological distress, and mental health. Results We found that 19.3% of respondents reported having symptoms of acute respiratory infection and the most commonly reported symptoms were a runny nose (11.2%), coughing (9.9%) and sore throat (6.2%). Fever and cough were reported by 0.8% of participants. Of the symptomatic respondents, 32.6% reported seeking health advice from a nurse, doctor or healthcare provider. Around 18% (n = 130) of symptomatic respondents had sought testing and a further 4.3% (n = 31) reported they intended to get tested. The regression results suggest that older age, larger household size, a higher number of chronic disease, mental health condition, poor wellbeing, and psychological distress were associated with higher odds of ARI symptoms. Higher household income was associated with lower odds of being tested or intending to be tested for coronavirus after adjusting for other explanatory variables. Conclusions There were relatively high rates of self-reported acute respiratory infection during a period of very low COVID-19 prevalence and low rate of coronavirus testing among symptomatic respondents. Ongoing monitoring of testing uptake, including in higher-risk groups, and possible interventions to improve testing uptake is key to early detection of disease.

Cucumber disease recognition using machine learning and transfer learning

Cucumber is grown, as a cash crop besides it is one of the main and popular vegetables in Bangladesh. As Bangladesh's economy is largely dependent on the agricultural sector, cucumber farming could make economic and productivity growth more sustainable. But many diseases diminish the situation of cucumber. Early detection of disease can help to stop disease from spreading to other healthy plants and also accurate identifying the disease will help to reduce crop losses through specific treatments. In this paper, we have presented two approaches namely traditional machine learning (ML) and CNN-based transfer learning. Then we have compared the performance of the applied techniques to find out the most appropriate techniques for recognizing cucumber diseases. In our ML approach, the system involves five steps. After collecting the image, pre-processing is done by resizing, filtering, and contrast-enhancing. Then we have compared various ML algorithms using k-means based image segmentation after extracted 10 relevant features. Random forest gives the best accuracy with 89.93% in the traditional ML approach. We also studied and applied CNN-based transfer learning to investigate the further improvement of recognition performance. Lastly, a comparison among various transfer learning models such as InceptionV3, MobileNetV2, and VGG16 has been performed. Between these two approaches, MobileNetV2 achieves the highest accuracy with 93.23%.

Corn Disease Classification Using Transfer Learning and Convolutional Neural Network

Indonesia is an agricultural country with abundant agricultural products. One of the crops used as a staple food for Indonesians is corn. This corn plant must be protected from diseases so that the quality of corn harvest can be optimal. Early detection of disease in corn plants is needed so that farmers can provide treatment quickly and precisely. Previous research used machine learning techniques to solve this problem. The results of the previous research were not optimal because the amount of data used was slightly and less varied. Therefore, we propose a technique that can process lots and varied data, hoping that the resulting system is more accurate than the previous research. This research uses transfer learning techniques as feature extraction combined with Convolutional Neural Network as a classification. We analysed the combination of DenseNet201 with a Flatten or Global Average Pooling layer. The experimental results show that the accuracy produced by the combination of DenseNet201 with the Global Average Pooling layer is better than DenseNet201 with Flatten layer. The accuracy obtained is 93% which proves the proposed system is more accurate than previous studies.

Detection of Disease-Specific Volatile Organic Compounds Using Infrared Spectroscopy

Many life-threatening diseases at an early stage remain unrecognized due to a lack of pronounced symptoms. It is also accepted that the early detection of disease is a key ingredient for saving many lives. Unfortunately, in most of the cases, diagnostics implies an invasive sample collection, being problematic at the asymptomatic stage. Infrared spectroscopy of breath offers reliable noninvasive diagnostics at every stage and has already been tested for several diseases. This approach offers not only the detection of specific metabolites, but also the analysis of their imbalance and transportation. In this article, the power of infrared spectroscopy is demonstrated for diabetes, cerebral palsy, acute gastritis caused by bacterial infection, and prostate cancer.

Comparison of Kidney Segmentation Under Attention U-Net Architectures

One of the most prominent machine learning advantages in the medical industry is the early detection of disease. Automatic kidney detection is of great importance for rapid diagnosis and treatment, where related diseases occupy over 73,750 new cases in the US in 2020 [1]. Today, the performance of diagnosis has been by highly trained radiologists. However, the complex structures contribute to speckle noise and inhomogeneous intensity profiles. Thus, there is a necessity to automate segmentation on kidney ultrasounds using U-Net Deep Learning architectures - an innovative solution for Medical Imaging Analysis. In this research, our focus is on the comparison of Attention U-Net in the context of different backbones such as VGG19, ResNet152V2, and EfficientNetB7. By providing this comparison, we will accomplish a survey for future researchers to more effectively decide on which Attention U-Net architecture to utilize for their segmentation projects.

FACTORS RELATED TO FIRST ANTENATAL VISITS IN PREGNANT WOMEN

Background: Pregnancy is a physiological event but in its developmen it has risks. In Nagekeo district in 2018 and 2019 there were 6 cases of maternal death and 121 cases of infant mortality with 52 deaths occurring antepartum. There were 10 infant deaths at the Boawae Health Center in 2019 with 5 cases of death occurring antepartum. In addition, there is a gap in achieving the first antenatal visit target of 19% and 14.8% in 2018 and 2019 where not all pregnant women have had their first pregnancy examination in the first trimester. Several factors can influence the behavior of pregnant women in conducting the first antenatal visit such as education level and cost. The importance of carrying out a pregnancy check in the first trimester allows for early detection of disease, administration of folic acid, communication and health information as well as management of problems found. This study aims to analyze the factors associated with the first antenatal visit in pregnant women. Methods: This type of research is observational analytic with a cross sectional design. The sample in this study were all pregnant women in the 2nd and 3rd trimesters who were in the working area of the Boawae Health Center. Data collected through questionnaires were then processed and analyzed by frequency distribution and cross distribution as well as Multiple Logistics Regression analysis with a significance level of 5% (p = 0.05). The research sample size is 86 respondents. The sampling technique is non-probability sampling with consecutive sampling. Bivariate data analysis using chi square and multivariate test using multiple logistic regression. Results: The results showed that the factors associated with the first antenatal visit were maternal health status with a p-value of 0.001 (p < 0.005), husband's education with a p-value of 0.000 (p < 0.005), pregnancy complications with a p-value of 0.001 (p < 0.005), costs with a p-value of 0.002 (p < 0.005) and the presence of a companion with a p-value of 0.000 (p < 0.005). Multivariate analysis showed that the most dominant factor influencing was the cost and presence of a companion, so it can be concluded that pregnant women who have KIS and are supported by a companion are more likely to have their first visit in the first trimester of pregnancy. Conclusion: There is a relationship between health status, husband's education, costs, presence of companions, pregnancy complications with the first antenatal visit.

Metal Nanoparticles and Carbon-Based Nanomaterials for Improved Performances of Electrochemical (Bio)Sensors with Biomedical Applications

Monitoring human health for early detection of disease conditions or health disorders is of major clinical importance for maintaining a healthy life. Sensors are small devices employed for qualitative and quantitative determination of various analytes by monitoring their properties using a certain transduction method. A “real-time” biosensor includes a biological recognition receptor (such as an antibody, enzyme, nucleic acid or whole cell) and a transducer to convert the biological binding event to a detectable signal, which is read out indicating both the presence and concentration of the analyte molecule. A wide range of specific analytes with biomedical significance at ultralow concentration can be sensitively detected. In nano(bio)sensors, nanoparticles (NPs) are incorporated into the (bio)sensor design by attachment to the suitably modified platforms. For this purpose, metal nanoparticles have many advantageous properties making them useful in the transducer component of the (bio)sensors. Gold, silver and platinum NPs have been the most popular ones, each form of these metallic NPs exhibiting special surface and interface features, which significantly improve the biocompatibility and transduction of the (bio)sensor compared to the same process in the absence of these NPs. This comprehensive review is focused on the main types of NPs used for electrochemical (bio)sensors design, especially screen-printed electrodes, with their specific medical application due to their improved analytical performances and miniaturized form. Other advantages such as supporting real-time decision and rapid manipulation are pointed out. A special attention is paid to carbon-based nanomaterials (especially carbon nanotubes and graphene), used by themselves or decorated with metal nanoparticles, with excellent features such as high surface area, excellent conductivity, effective catalytic properties and biocompatibility, which confer to these hybrid nanocomposites a wide biomedical applicability.

Covid-19 Disaster Management through Websites and Social Media Regency/City Government in the Special Region of Yogyakarta

The severity of criticism in handling the COVID-19 pandemic has made local governments turn to information and communication technology to back up various important information in mitigating the handling of COVID-19. Although the district/city government in Yogyakarta has taken advantage of digitalization in the operation of its government system, it is still a question mark whether the district/city local government can utilize websites and social media as a means and media for handling COVID -19 effectively and efficiently mapping COVID-19 data. And socialization of its handling to the community. The research method used is descriptive qualitative research to obtain comprehensive data related to disaster management through websites and social media by the district/city government in Yogyakarta. The results show that the use of websites and social media by the Sleman Regency Government and Yogyakarta City Government to mitigate the COVID-19 pandemic is utilizing online data sources for early detection of disease; in the form of notification of diagnosed cases, data visualization tools for decision support, namely the use of collecting public health data in real-time, as well as the use of public communications related to the mitigation of the covid-19 pandemic. The conclusion obtained is that the use of pages and social media used by the Sleman Regency Government and the Yogyakarta City Government has similarities in their use, both back office and front office. However, there are differences in information content both on the page and social media users.