Prediction Of Causes Research Articles

New perspectives of forensic pathology through machine learning approach on autopsy data: a pilot study.

The analysis, interpretation and storage of information is entrusted to the individual expert, who bases his judgments on the knowledge resulting from the experience. The aim of this experimental study is to analyse and introduce a new line of research applicable to forensic pathology, based on the use of artificial intelligence techniques as a possible tool for data collection and analysis. The sample analysed is represented by judicial autop-sies performed at the University of Catanzaro from 01/01/2020 to 31/12/2021. For each case were performed: study of medical records; autopsy; histological examinations; toxicological analysis of blood samples. Continuous variables were presented as means ± standard deviations, and categorical variables were expressed as percentages. A random forest regression model was conducted, as a machine learning approach, to estimate the importance of individual solid organ weight variables in predicting cause of death. This study aimed to evaluate autopsy data to aid in the description and study of forensic cases, using a machine learning approach. To date, this study appears to be the first to evaluate the weight of organs in predicting a cause of death. Artificial intelligence techniques are an optimal solution in solving forensic dilemmas. The results of this study demonstrate that routine data can be submitted using machine learning techniques in order to identify key elements of procedures that provide more information in relation to the predic-tion of cause of death.

Prediction of causes and effects of obesity in India by supervise learning approaches

Obesity is one of the basic and becomes the most common health problem all over the globe. Indian people are not being untouched by it. Although changes and the vast variety of lifestyles are major causes of the problems related to obesity. In this paper, the researcher collected data from more than 550 Indian subjects on different parameters and tried to understand the predictability of obesity in these subjects with the help of machine learning. Researchers used anaconda orange as a tool to implement machine learning algorithms and tried to predict obesity in the Indian context. A comparison of algorithms was done to see its best fit and the best algorithm would be applied to find the best predictive results. • Obesity is one of the basic and becomes most common health problem all over the globe. • Indian people are not being untouched from it. • Although changes and vast variety of life style are major causes of the problems related to obesity. • In this paper, researcher collected data from more than 550 Indian subjects on different parameters and tried to understand predictability of obesity on these subject with the help of machine learning. • Researchers used anaconda orange as tool to implement machine learning algorithms and tried to predict obesity in Indian context. • A comparison of algorithms was done to see its best fit and best algorithm would be applied to find best predictive results. • So, we can say it's going to be a major health problem in coming days. • The problem will be supplemented by the current Covid 19 pandemic, when kids are limited to house only. • Lots of study in past has proved that BMI & some other clinical parameters are the major parameter to determine prevalence of metabolic & cardiovascular diseases.

An integrated risk prediction model for corrosion-induced pipeline incidents using artificial neural network and Bayesian analysis

In onshore hazardous liquid transmission pipelines, corrosion-induced incidents are potentially significant hazard to people, property and environment. Therefore, several statistical data analysis methods have been developed to analyze their risks. These existing models utilize only a few attributes from a wide incident database and generally assume failure rates as homogeneous or constant over time which is not true. There is also a lack of frameworks to predict risk by utilizing the current condition of pipelines and historical incident data simultaneously. This article presents an integrated risk prediction model which leverages rich incident database of Pipeline Hazardous Material Safety Administration (PHMSA) and utilizes nonhomogeneous failure rates derived from data. From incident data for 2010–2019, 70 attributes are selected based on their significance to corrosion-induced pipeline incidents, and artificial neural network (ANN) models are developed for the prediction of causes and consequences of incidents. Next, the probability of incident is predicted using Bayesian analysis with nonhomogeneous failure rates. Here, ANN models employ current conditions of pipelines and Bayesian analysis utilizes historical incident data simultaneously. The predicted consequences and probability are multiplied to predict risk of corrosion-induced incidents. The effectiveness of the proposed framework is demonstrated using the PHMSA database.

Deep Learning Natural Language Processing Successfully Predicts the Cerebrovascular Cause of Transient Ischemic Attack-Like Presentations.

Background and Purpose- Triaging of referrals to transient ischemic attack (TIA) clinics is aided by risk stratification. Deep learning-based natural language processing, a type of machine learning, may be able to assist with the prediction of cerebrovascular cause of TIA-like presentations from free-text information. Methods- Consecutive TIA clinic notes were retrieved from existing databases. Texts associated with cerebrovascular and noncerebrovascular diagnoses were preprocessed before classification experiments, using a variety of classifier models, based on only the free-text description of the history of presenting complaint. The primary outcome was area under the curve (AUC) of the receiver operator curve. The model with the greatest AUC was then used in classification experiments in which it was provided with additional clinical information. Results- Of the classifier models trialed on the history of presenting complaint, the convolutional neural network achieved the greatest predictive capability (AUC±SD; 81.9±2.0). The effects of additional clinical information on AUC were variable. The greatest AUC was achieved when the convolutional neural network was provided with the history of presenting complaint and magnetic resonance imaging report (88.3±3.6). Conclusions- Deep learning-based natural language processing, in particular convolutional neural networks, based on medical free-text, may prove effective in prediction of the cause of TIA-like presentations. Future research investigating the role of the application of deep learning-based natural language processing to the automated triaging of clinic referrals in TIA, and potentially other specialty areas, is indicated.

Prediction of cause of death from forensic autopsy reports using text classification techniques: A comparative study

ObjectivesAutomatic text classification techniques are useful for classifying plaintext medical documents. This study aims to automatically predict the cause of death from free text forensic autopsy reports by comparing various schemes for feature extraction, term weighing or feature value representation, text classification, and feature reduction. MethodsFor experiments, the autopsy reports belonging to eight different causes of death were collected, preprocessed and converted into 43 master feature vectors using various schemes for feature extraction, representation, and reduction. The six different text classification techniques were applied on these 43 master feature vectors to construct a classification model that can predict the cause of death. Finally, classification model performance was evaluated using four performance measures i.e. overall accuracy, macro precision, macro-F-measure, and macro recall. ResultsFrom experiments, it was found that that unigram features obtained the highest performance compared to bigram, trigram, and hybrid-gram features. Furthermore, in feature representation schemes, term frequency, and term frequency with inverse document frequency obtained similar and better results when compared with binary frequency, and normalized term frequency with inverse document frequency. Furthermore, the chi-square feature reduction approach outperformed Pearson correlation, and information gain approaches. Finally, in text classification algorithms, support vector machine classifier outperforms random forest, Naive Bayes, k-nearest neighbor, decision tree, and ensemble-voted classifier. ConclusionOur results and comparisons hold practical importance and serve as references for future works. Moreover, the comparison outputs will act as state-of-art techniques to compare future proposals with existing automated text classification techniques.

Prediction of cause of stroke and Correlation cause between anxiety and depression on some man young adults and middle-aged people

본 연구는 청장년층을 대상으로 10년 이내 뇌졸중 위험예측도와 불안 및 우울과의 상관성을 파악하고자 하였다. 연구 대상은 2013년 10월부터 12월까지 일개 종합병원을 방문한 대상자로 총 230명이었다(남성 230명). 자료 수집은 공복혈당, 총콜레스테롤, 중성지방, 흡연, 체질량지수, 저?고지단백 콜레스테롤을 측정하였고 성별, 불안, 우울을 조사하였다. 한국형 뇌졸중 예측 모형을 적용하여 분석하였다.<BR> 연구결과 뇌졸중 환자의 평균 연령은 41.6±5.1세이었다. 뇌졸중 위험예측도와 고혈압(p<.001), 비만 (p<.001), 고콜레스테롤(p<.001)이 유의한 차이가 있었다. 불안과 우울은 뇌졸중 위험요인이지만 본 연구에서는 관련성이 없어 추후 연구의 확대가 필요할 것으로 생각된다.

Using Phylogenetic Approaches for the Analysis of Plant Breeding System Evolution

▪ Abstract Until recently, studies of plant reproductive systems have been at the population level, using microevolutionary approaches. The development of cladistic approaches, combined with the emergence of molecular systematics, has resulted in an explosion of phylogenetic studies and an increase in interdisciplinary approaches combining ecological and systematic methodology. These new approaches offer the possibility of testing explicit hypotheses about the number of evolutionary transitions in reproductive characters and the evolutionary relationship of these characters to changes in the environment. Character mapping may be especially useful for detecting convergent evolution. In a number of cases, character mapping has provided new insights into the evolution of plant breeding systems and pollination biology, especially in suggesting the number of times evolutionary transitions have taken place, indicating where there have been reversals and suggesting when preadaptation has been important. The insights provided by character mapping are determined by a number of factors, including the degree of confidence in phylogenies underlying these studies and the identification of appropriate outgroups. Assumptions about character coding, character ordering, inclusion vs. exclusion of characters that are mapped on trees in the data matrix, and weighting of characters will have profound effects on interpretation of character evolution. Highly labile characters that evolve frequently and have the potential to undergo reversals may make it difficult to detect the pattern of character evolution. Characters that are very strongly correlated with each other or with ecological shifts may make prediction of cause and effect using phylogenetic approaches difficult because changes in characters and ecological shifts will occur, apparently simultaneously, on the same branches. Results from microevolutionary studies have been used in several cases to weight transitions, suggesting that results of phylogenetic studies may not provide fully independent assessments of character evolution. While not a simple cure to understanding problems that have been studied only in the realm of microevolutionary studies, phylogenetic approaches offer clear potential for providing new insights for evolutionary studies.

Some Observations on Grossarth-Maticek's Data Base

Some Observations on Grossarth-Maticek's Data Base