Machine learning for predicting chronic diseases: a systematic review

Delpino, Felipe Mendes; Costa, Ândria Krolow; Farias, S R; Filho, Alexandre Dias Porto Chiavegatto; Arcêncio, Ricardo Alexandre; Nunes, Bruno Pereira

doi:10.1016/j.puhe.2022.01.007

Cited by 35 publications

(18 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the present study, individuals' baseline characteristics will be used to train popular ML algorithms such as Support Vector Machine (SVM), Neural Networks (ANNs), Random Forests, Penalized Regressions, Gradient Boosted Trees, and Extreme Gradient Boosting (XGBoost). These models were chosen based on a previous review in which the authors identified the most used models in healthcare studies 25 . We will use the Python programming language to perform the analyzes.…”

Section: Discussionmentioning

confidence: 99%

Emergency department use and Artificial Intelligence in Pelotas: design and baseline results

Delpino

Figueiredo

Costa

et al. 2023

Rev. bras. epidemiol.

Self Cite

View full text Add to dashboard Cite

RESUMO Objetivo: To describe the initial baseline results of a population-based study, as well as a protocol in order to evaluate the performance of different machine learning algorithms with the objective of predicting the demand for urgent and emergency services in a representative sample of adults from the urban area of Pelotas, Southern Brazil. Methods: The study is entitled “Emergency department use and Artificial Intelligence in PELOTAS (RS) (EAI PELOTAS)” (https://wp.ufpel.edu.br/eaipelotas/). Between September and December 2021, a baseline was carried out with participants. A follow-up was planned to be conducted after 12 months in order to assess the use of urgent and emergency services in the last year. Afterwards, machine learning algorithms will be tested to predict the use of urgent and emergency services over one year. Results: In total, 5,722 participants answered the survey, mostly females (66.8%), with an average age of 50.3 years. The mean number of household people was 2.6. Most of the sample has white skin color and incomplete elementary school or less. Around 30% of the sample has obesity, 14% diabetes, and 39% hypertension. Conclusion: The present paper presented a protocol describing the steps that were and will be taken to produce a model capable of predicting the demand for urgent and emergency services in one year among residents of Pelotas, in Rio Grande do Sul state.

show abstract

Section: Discussionmentioning

confidence: 99%

Emergency department use and Artificial Intelligence in Pelotas: design and baseline results

Delpino

Figueiredo

Costa

et al. 2023

Rev. bras. epidemiol.

Self Cite

View full text Add to dashboard Cite

show abstract

“…For real-time healthcare analytic applications, one study [7] proposed pruned Random Forest for detecting three different diseases using different medical datasets. The study described in [8] proposed a prediction model for the classification of diabetes mellitus using the synthetic minority oversampling technique, genetic algorithm, and decision tree, with an accuracy of 82.12%. In [9], the authors compared the accuracy of the decision tree with other classification algorithms to examine a thyroid disease dataset.…”

Section: Related Workmentioning

confidence: 99%

“…Trained weights are utilized for clustering new examples, where a new example is in the cluster of winning vectors [31,33]. Over time, both the radius and learning rate undergo exponential decay that is similar in nature, along with the neighborhood function influence β i (t) (6), (7), (8).…”

Section: Decision Tree Random Forest and Som Neural Networkmentioning

confidence: 99%

“…This algorithm is useful for identifying the presence or absence of chronic diseases based on a dataset, such as individual health data and diagnostic data. Using the random forest algorithm, we can build a model that predicts the presence or absence of specific chronic diseases such as hypertension, diabetes, heart disease, and others [7,8]. Additionally, the algorithm allows us to identify key variables that have the most significant impact on the development of a particular disease, such as age, gender, body mass index, blood pressure, and other factors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Unveiling the Comorbidities of Chronic Diseases in Serbia Using ML Algorithms and Kohonen Self-Organizing Maps for Personalized Healthcare Frameworks

Ranković

Lukić

et al. 2023

JPM

View full text Add to dashboard Cite

In previous years, significant attempts have been made to enhance computer-aided diagnosis and prediction applications. This paper presents the results obtained using different machine learning (ML) algorithms and a special type of a neural network map to uncover previously unknown comorbidities associated with chronic diseases, allowing for fast, accurate, and precise predictions. Furthermore, we are presenting a comparative study on different artificial intelligence (AI) tools like the Kohonen self-organizing map (SOM) neural network, random forest, and decision tree for predicting 17 different chronic non-communicable diseases such as asthma, chronic lung diseases, myocardial infarction, coronary heart disease, hypertension, stroke, arthrosis, lower back diseases, cervical spine diseases, diabetes mellitus, allergies, liver cirrhosis, urinary tract diseases, kidney diseases, depression, high cholesterol, and cancer. The research was developed as an observational cross-sectional study through the support of the European Union project, with the data collected from the largest Institute of Public Health “Dr. Milan Jovanovic Batut” in Serbia. The study found that hypertension is the most prevalent disease in Sumadija and western Serbia region, affecting 9.8% of the population, and it is particularly prominent in the age group of 65 to 74 years, with a prevalence rate of 33.2%. The use of Random Forest algorithms can also aid in identifying comorbidities associated with hypertension, with the highest number of comorbidities established as 11. These findings highlight the potential for ML algorithms to provide accurate and personalized diagnoses, identify risk factors and interventions, and ultimately improve patient outcomes while reducing healthcare costs. Moreover, they will be utilized to develop targeted public health interventions and policies for future healthcare frameworks to reduce the burden of chronic diseases in Serbia.

show abstract

“…Several existing studies have employed ML to predict an extensive range of chronic health conditions, such as autoimmune, cardiovascular, cerebrovascular, hepatic, metabolic, neurodegenerative, pulmonary, renal, and rheumatic diseases, as well as cancers ( 56–61 ). Most of these studies used K-nearest neighbors (KNN), support vector machines (SVM), Naïve Bayes (NB), deep neural networks, random forest (RF), and logistic regression (LR) ( 58 , 60 , 62–64 ). Existing classical ML models in the literature have predicted health outcomes based on SDoH with accuracies between 61 and 74% ( 65 ).…”

Section: Introductionmentioning

confidence: 99%

Can adverse childhood experiences predict chronic health conditions? Development of trauma-informed, explainable machine learning models

Afzal,

Jahangir,

Mei

et al. 2024

Front. Public Health

View full text Add to dashboard Cite

IntroductionDecades of research have established the association between adverse childhood experiences (ACEs) and adult onset of chronic diseases, influenced by health behaviors and social determinants of health (SDoH). Machine Learning (ML) is a powerful tool for computing these complex associations and accurately predicting chronic health conditions.MethodsUsing the 2021 Behavioral Risk Factor Surveillance Survey, we developed several ML models—random forest, logistic regression, support vector machine, Naïve Bayes, and K-Nearest Neighbor—over data from a sample of 52,268 respondents. We predicted 13 chronic health conditions based on ACE history, health behaviors, SDoH, and demographics. We further assessed each variable’s importance in outcome prediction for model interpretability. We evaluated model performance via the Area Under the Curve (AUC) score.ResultsWith the inclusion of data on ACEs, our models outperformed or demonstrated similar accuracies to existing models in the literature that used SDoH to predict health outcomes. The most accurate models predicted diabetes, pulmonary diseases, and heart attacks. The random forest model was the most effective for diabetes (AUC = 0.784) and heart attacks (AUC = 0.732), and the logistic regression model most accurately predicted pulmonary diseases (AUC = 0.753). The strongest predictors across models were age, ever monitored blood sugar or blood pressure, count of the monitoring behaviors for blood sugar or blood pressure, BMI, time of last cholesterol check, employment status, income, count of vaccines received, health insurance status, and total ACEs. A cumulative measure of ACEs was a stronger predictor than individual ACEs.DiscussionOur models can provide an interpretable, trauma-informed framework to identify and intervene with at-risk individuals early to prevent chronic health conditions and address their inequalities in the U.S.

show abstract

Machine learning for predicting chronic diseases: a systematic review

Cited by 35 publications

References 35 publications

Emergency department use and Artificial Intelligence in Pelotas: design and baseline results

Emergency department use and Artificial Intelligence in Pelotas: design and baseline results

Unveiling the Comorbidities of Chronic Diseases in Serbia Using ML Algorithms and Kohonen Self-Organizing Maps for Personalized Healthcare Frameworks

Can adverse childhood experiences predict chronic health conditions? Development of trauma-informed, explainable machine learning models

Contact Info

Product

Resources

About