Predicting Infections Using Computational Intelligence – A Systematic Review

Abstract

Infections encompass a set of medical conditions of very diverse kinds that can pose a significant risk to health, and even death. As with many other diseases, early diagnosis can help to provide patients with proper care to minimize the damage produced by the disease, or to isolate them to avoid the risk of spread. In this context, computational intelligence can be useful to predict the risk of infection in patients, raising early alarms that can aid medical teams to respond as quick as possible. In this paper, we survey the state of the art on infection prediction using computer science by means of a systematic literature review. The objective is to find papers where computational intelligence is used to predict infections in patients using physiological data as features. We have posed one major research question along with nine specific subquestions. The whole review process is thoroughly described, and eight databases are considered which index most of the literature published in different scholarly formats. A total of 101 relevant documents have been found in the period comprised between 2003 and 2019, and a detailed study of these documents is carried out to classify the works and answer the research questions posed, resulting to our best knowledge in the most comprehensive study of its kind. We conclude that the most widely addressed infection is by far sepsis, followed by Clostridium difficile infection and surgical site infections. Most works use machine learning techniques, from which logistic regression, support vector machines, random forest and naive Bayes are the most common. Some machine learning works provide some ideas on the problems of small data and class imbalance, which can be of interest. The current systematic literature review shows that automatic diagnosis of infectious diseases using computational intelligence is well documented in the medical literature.

A Comparative Performance Analysis of Data Resampling Methods on Imbalance Medical Data

“…Compared with other types of cancer, there is less study on class imbalance methods for lung cancer. Few research es als o classified the Lung nodules [83,84], chest-related diseases [85,86], identification of thoracic diseases [87], forecasting of COVID-19 [84,88,89].…”

Applications of Technological Solutions in Primary Ways of Preventing Transmission of Respiratory Infectious Diseases—A Systematic Literature Review

“…Regarding Computational Intelligence applications, Baldominos et al [1] performed a systematic literature review aiming to find studies that adopted computational intelligence to predict infections in patients using physiological data as features. The study analyzed 101 relevant documents between the period of 2003 and 2019, showed that automatic diagnosis of these diseases is well documented in medical literature and concluded that sepsis, Clostridium difficile infection and surgical site infections were the most addressed.…”

“…According to Baldominus et al [1], infectious diseases are the result of the invasive action of microscopic organisms (e.g., bacteria or viruses) in the body, and may be presented in many different types with different effect ranges. For example, while some infected bodies can remain asymptomatic, others can reach high risks of death.…”

“…Given the importance of the issue and its impact on human life, medicine has developed a variety of mechanisms for the prevention, prediction, diagnosing and treatment of infections [1]. However, over the years, new microorganisms have emerged, generating constant challenges for science in combating the action of these organisms towards humanity.…”

Telemonitoring System for Infectious Disease Prediction in Elderly People Based on a Novel Microservice Architecture

“…It is becoming increasingly difficult to ignore the growth of an aging population in Europe, since a 74% rise in the population aged over 65 is expected by 2060 [1], [2]. This group of people have high rates of comorbidity [3], causing a very high consumption of resources in terms of both primary and specialised care [4].…”