Key result
Machine learning models using joint pain attributes predict chronic Chikungunya progression with ~69% recall.
Why the study?
Chikungunya can progress to a debilitating chronic phase marked by arthralgia, and understanding the influence of pain points on disease progression using data science is needed.
Does the inclusion of specific joint pain points improve the performance of machine learning models in predicting the progression to chronic Chikungunya?
Observational (n=347)
Yes
Does the inclusion of specific joint pain points improve the performance of machine learning models in predicting the progression to chronic Chikungunya?
Machine learning models incorporating specific joint pain points can effectively estimate the likelihood of Chikungunya progressing to the chronic phase, potentially guiding early preventive measures.
Answers are grounded in this paper and cite their sources.
May guide early preventive measures in high-risk acute cases; extends ML prediction by confirming joint pain attributes' value.
Chikungunya is an arbovirus capable of affecting the musculoskeletal system of infected individuals. Furthermore, it has the potential to progress from the acute to the chronic phase, marked by the prevalence of symptoms of arthralgia. Joint pain compromises the performance of daily activities, including psychological, economic, and physical functioning. Through the use of data science techniques, such as data analysis, evaluation, and visualization, the aim is to understand the influence of pain points on disease progression. Furthermore, we also evaluate artificial intelligence models to calculate the likelihood of patients progressing to a chronic phase. The data analysis showed that arthralgia was reported by 97.70% of the sample (339 cases), followed by 74.06% edema (257 cases), 36.31% low back pain (126 cases) and 34.58% myalgia (120 cases), being factors that are related to chronicity. The artificial intelligence models have achieved metrics above 60%, demonstrating potential for estimating the likelihood of a patient’s progression to the chronic phase. Based on these estimates, healthcare professionals can adopt preventive measures capable of mitigating the disease’s impacts. Implementing these models in the decision-making process becomes an important ally in the fight against Chikungunya in Brazil, helping to mitigate the social and economic impacts caused by the chronic phase.
No takes yet. Share an insight, caveat, or question.
Masson et al. (2026) conducted an observational in Chikungunya (n=347). Machine learning models was evaluated on Progression to the chronic phase of Chikungunya (≥ 90 days). Machine learning models incorporating joint pain attributes achieved a median recall of 69% in predicting the progression of Chikungunya to the chronic phase.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: