No abstract

The report of the World Health Organization (WHO) about the poor accessibility of people living in low-to-middle-income countries to medical facilities and personnel has been a concern to both professionals and nonprofessionals in healthcare. This poor accessibility has led to high morbidity and mortality rates in tropical regions, especially when such a disease presents itself with confusable symptoms that are not easily differentiable by inexperienced doctors, such as those found in febrile diseases. This prompted the development of the fuzzy cognitive map (FCM) model to serve as a decision-support tool for medical health workers in the diagnosis of febrile diseases. With 2465 datasets gathered from four states in the febrile diseases-prone regions in Nigeria with the aid of 60 medical doctors, 10 of those doctors helped in weighting and fuzzifying the symptoms, which were used to generate the FCM model. Results obtained from computations to predict diagnosis results for the 2465 patients, and those diagnosed by the physicians on the field, showed an average of 87% accuracy for the 11 febrile diseases used in the study. The number of comorbidities of diseases with varying degrees of severity for most patients in the study also covary strongly with those found by the physicians in the field.

Machine learning is a form of artificial intelligence that is applicable in all fields of study. It incorporates many algorithms used in carrying out various tasks such as classification, predictions, estimations, comparisons, approximations, optimization and selections. In estimating original oil in place, which affords the explorationist the foresight on the total amount of crude oil that is potentially in reservoir. Machine learning is found to perform reserves estimation with speed                 and accuracy where insufficient data are available. These among other attributes of Machine Learning motivated a systematic literature review of studies undertaken between 2010 and 2021 and explore the strengths and limitations reported in the studies. In the oil industry, different                     types of data are gathered from subsurface and surface in order to know the reservoir hydrocarbon potential. Sensorsare known to be able to collect these data in large quantity, analyse and                 used to predict the output.3127 articles related to the study were collated from 4 databases and after a series of inclusion and exclusion criteria were conducted on the articles, 104 journal articles met the criteria and were used for the review. Results of the study reveal that between the years under review, 2019 had the greatest number of articles (20 of the 104) pertaining to the topic reviewed. 61% of authors reported inadequate data while 39 % reported under-performance of              the algorithm. It was also revealed that machine learning was applied to perform predictions/forecasting in the industry than it was used to solve other problems, while Artificial Neural Network (ANN) was the most used artificial intelligence technique. The study opens another vista of knowledge for researchers to navigate machine learning in the estimation of original oil in place and petrophysics analysis. This emerging technology is smart and makes data evaluation easy and straightforward.