Machine-Learning-Based Disease Diagnosis: A Comprehensive Review

Abstract

Globally, there is a substantial unmet need to diagnose various diseases effectively. The complexity of the different disease mechanisms and underlying symptoms of the patient population presents massive challenges in developing the early diagnosis tool and effective treatment. Machine learning (ML), an area of artificial intelligence (AI), enables researchers, physicians, and patients to solve some of these issues. Based on relevant research, this review explains how machine learning (ML) is being used to help in the early identification of numerous diseases. Initially, a bibliometric analysis of the publication is carried out using data from the Scopus and Web of Science (WOS) databases. The bibliometric study of 1216 publications was undertaken to determine the most prolific authors, nations, organizations, and most cited articles. The review then summarizes the most recent trends and approaches in machine-learning-based disease diagnosis (MLBDD), considering the following factors: algorithm, disease types, data type, application, and evaluation metrics. Finally, in this paper, we highlight key results and provides insight into future trends and opportunities in the MLBDD area.

Accurate Numerical Treatment on a Stochastic SIR Epidemic Model with Optimal Control Strategy

“…The effectiveness of MNIM in this research motivates us to extend its applicability to more complex infectious disease models. Further work should reconsider applying these techniques in developing a dynamic model for other conditions such as heart disease [35][36][37], suicide prevention [38], and combine the suggested model with machine learning techniques in developing optimal solutions for infectious diseases such as COVID-19, Pneumonia, and so on [39][40][41].…”

Systematic review on ensuring the global food security and covid-19 pandemic resilient food systems: towards accomplishing sustainable development goals targets

“…Original research papers and review articles were obtained from the ScienceDirect and Web of Science databases, which are well-known for their high-quality and higher peer-reviewed paper indexes. The title search was conducted as follows, using keywords and the Boolean operators [66]. "Covid-19 pandemic" AND ("global food security" OR "food system resilience" OR "global pandemics" OR "agroecosystems" OR "build back better" OR "systematic thinking" OR "potential response mechanisms" OR "policy instruments").…”

Tracking Health, Performance and Recovery in Athletes Using Machine Learning

“…The traditional analysis and interpretation of the results of clinical observations is a laborious process, often depending on the practical experience of the doctor. Today, the literature is actively discussing approaches to the application of machine learning methods for the classification and diagnosis of multifactorial diseases, such as coronary heart disease, cancer, diabetes mellitus and many other pathologies [ 9 , 10 , 11 , 12 , 13 ]. It is important to use the intellectual analysis of large clinical data on the health status of athletes, for which there is a significant shift in the generally accepted reference ranges of clinical indicators compared to those obtained for a sedentary population, generally reflecting the body’s adaptations to regular and prolonged physical activity.…”

“…Despite the actively developing field of data mining, there is no “gold” standard in methodological approaches yet. Depending on the task and the dimension of the dataset under study, the most popular machine learning approaches are logistic regression, support vector classifier, decision tree, multinomial naive Bayes, random forest, and multinomial regression [ 10 , 11 , 14 , 15 ].…”