The primary focus of this paper review is to summarize the most important facts and findings regarding the use of Artificial Intelligence (AI) in the modeling, processing and analysis of biomedical data and to give an insight on the contributions of AI, Machine learning and Deep learning to the field of medicine. This study compiled and analyzed work published in the period between 1986 and 2021 related to the use of AI in medicine, its various applications and historical development, with a focus on papers published from 2015 until today, due to the accumulation and development of newer technologies. Out of a total of 117 papers reviewed, 52 were selected for a more detailed analysis and presented in a table summarizing the key points, advances, advantages and disadvantages of AI, its subfields and algorithms. The goal of this paper was to extract the most famous AI learning algorithms, past and current, and focus on the methods of modeling, processing and analysis by which these algorithms operate and perform tasks in order to help doctors and experts better understand the underlying mechanisms behind biological processes, and in some cases, even replace humans in data classification, identification, diagnosis and prediction of different conditions associated with diseases.

While examining biomedical signals, signal classification as well as measurements, quantifications and their assessment is very important for studying different diseases and disorders. Through this paper, we have focused on different signals and biomedical devices, whose purpose is to give high quality information about diseases and disorders in prenatal age. The main focus was on ultrasound techniques and the relationship between 2D, 3D and 4D ultrasound, on Doppler ultrasound, cardiotocography, KANET test, and in general, comparison of standardized and automated techniques. Purpose of this paper is to compare some of the available techniques used to assess the fetus in the womb, how they advance through time and whether they are being automated.

Pulmonary emphysema is a complicated disease caused by irreversible damage to the wall of the pulmonary alveoli and causes 5% of the total mortality worldwide. This paper presents the development of an artificial neural network (ANN) for the diagnosis of pulmonary emphysema. Following biomarkers were used for the development of the ANN: AAT (alphal-antitrypsin), FEV1 (forced expiratory volume in 1 second), FVC (forced vital capacity) and FEV1/FVC (ratio forced expiratory volume in 1 second / forced vital capacity). The dataset consisted of 300 patients: 210 healthy subjects and 90 subject with disease. The neural network has 4 input parameters and 1 output parameter. For the final architecture, a neural network with 13 neurons in hidden layer was chosen based on the training results. The developed ANN has shown good performance and has a potential for use in this field.

As a consequence of the progress of the modern mobile medicine, wearable technologies, especially ECG wearables tend to become indispensable part of peoples' lives. As applications and devices for tracking cardiac electrical activity are rapidly entering the market, it is important to compare individual ECG wearable devices. This review takes a systematic approach on the analysis of wearable ECG devices. It provides a detailed introduction on the updated methods, to create a comparison between individual features of devices, and to evaluate techniques for fall risk assessment, diagnosis, and prevention. PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) instructions were used as a report standard. In an effort to collect the appropriate data, various databases were queried together with specific subject-oriented keywords. This was combined with different inclusion and exclusion criteria to find the relevant data. To further improve the data gathering and reduce bias, a Zotero tool was used. The results of this paper show the comparison of the different devices and their features. All findings can be observed in the table and in words. As information for the QardioCore are scarce, all six authors consolidated on the VitalCore being the most accurate ECG wearable device, as its sensitivity and specificity are the highest. Recent advances in wearable ECG devices allow for more trouble free out of clinic fall risk assessment, detection and prevention. As people tend to prefer the comfort of their home over doctors, such progress will assure the everyday emerging of new wearables.

Machine learning algorithms have been drawing attention in lung disease research. However, due to their algorithmic learning complexity and the variability of their architecture, there is an ongoing need to analyze their performance. This study reviews the input parameters and the performance of machine learning applied to diagnosis of chronic obstructive pulmonary disease (COPD). One research focus of this study was on clearly identifying problems and issues related to the implementation of machine learning in clinical studies. Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) protocol, 179, 1032, and 36,500 titles were identified from the PubMed, Scopus, and Google Scholar databases respectively. Studies that used machine learning to detect COPD and provided performance measures were included in our analysis. In the final analysis, 24 studies were included. The analysis of machine learning methods to detect COPD reveals the limited usage of the methods and the lack of standards that hinder the implementation of machine learning in clinical applications. The performance of machine learning for diagnosis of COPD was considered satisfactory for several studies; however, given the limitations indicated in our study, further studies are warranted to extend the potential use of machine learning to clinical settings.

Diagnostic medical imaging and the interpretation of the imaging results pose a great challenge for the medical profession as the final conclusions are highly susceptible to human error and subjectivity. The necessity for standardization of interpretation of medical images is very necessary to bypass these problems. The only way of achieving this is using a methodology which excludes the human eye and employs artificial intelligence. However, another challenge is selecting the most suitable AI algorithm fit for the challenging task of imaging results interpretation. This study was conducted following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines published in 2020. Research was done using PubMed, ScienceDirect and Google Scholar databases where the key inclusion criteria were language, journal credibility, open access to full-text publications and the most recent papers. In order to focus on only the most recent research, only the papers published in the last 5 years were evaluated. The search through PubMed, ScienceDirect and Google Scholar has yielded 81, 205, and 520 papers respectively. Out of this number of papers, 26 of them have met all of the inclusion criteria and were included in the research. The observed accuracies of the models and the overall rising interest in the topic denote that this field is rapidly growing and has a great potential to be applied in daily medical practice in the future.

Abstract Pneumonia is a leading cause of mortality in limited resource settings (LRS), which are common in low- and middle-income countries (LMICs). Accurate referrals can reduce the devastating impact of pneumonia, especially in LRS. Discriminating pneumonia from other respiratory conditions based only on symptoms is a major challenge. Machine learning has shown promise in overcoming the diagnostic difficulties of pneumonia (i.e., low specificity of symptoms, lack of accessible diagnostic tests and varied clinical presentation). Many scientific papers are now focusing on deep-learning methods applied to clinical images, which is unaffordable for initial patient referral in LMICs. The current study used a dataset of 4500 patients (1500 patients affected by bronchitis, 3000 by pneumonia) from a middle-income country, containing information on subject population characteristics, symptoms and laboratory test results. Manual feature selection was performed, focusing on clinical symptoms that are easily measurable in LRS and in community settings. Three common machine learning methods were tested and compared: logistic regression; decision tree and support vector machine. Models were developed through a holdout process of training-validation and testing. We focused on six clinically relevant, easily interpreted patient symptoms as best indicators for pneumonia. Our final model was a decision tree, achieving an AUC of 93%, with the advantage of being fully intelligible and easily interpreted. The performance achieved suggested that intelligible machine learning models can enhance symptom-based referral of pneumonia in LRS and in community settings.