Dados do Trabalho

Título

Clinical Decision Support System Applied to Amyotrophic Lateral Sclerosis Prognosis

Resumo

Introduction:
Amyotrophic Lateral Sclerosis (ALS) is a rare and incurable disease that affects the neurons of the human motor system. The communication between the brain and muscles is gradually interrupted, leading patients to paralysis and death. The average life expectancy is 3-5 years after symptoms onset, and the worldwide incidence is about 1.9 cases per 100,000 individuals per year. ALS is clinically heterogeneous, with different symptoms and disease progression among its patients, making it challenging to perform prognoses (e.g., survival time and disease progression).
Research using Machine Learning (ML) algorithms has been applied to improve the prognosis of diseases.
ML could extract information from the training data, transform it into knowledge, and use it to solve different categories of problems. Thus, it is crucial to collect patient data to perform relevant studies and create ML solutions to help physicians in their daily work, e.g., developing a Clinical Decision Support System (CDSS).

Objectives:
The primary objective is to develop a CDSS to assist Brazilian health workers in their tasks related to ALS prognosis.
The proposed CDSS should provide helpful information about prognosis prediction, including the survival time, the disease stage, and the moment when respiratory or nutritional support will be needed. Consequently, we intend to create a Brazilian ALS Prognosis Database to support future research in this field.

Methodology:
This study is clinical, prospective, observational, and longitudinal.
Data will be collected from patients followed by Brazilian Research Centers, which include demographics, clinical, laboratory, functional, and respiratory biomarkers. The data collected will be processed by ML algorithms to learn and create models to provide the target predictions defined. A CDSS will be developed to allow the health workers to register information and obtain the prognosis predictions about their patients. The system will comprise the Electronic Medical Record and the Prognosis Dashboard modules.

Conclusions:
This research aims to develop a CDSS to help physicians in their ALS clinical practice. This system will allow health workers to register and monitor their ALS patients. We expect that the proposed CDSS can provide valuable information to the health workers about prognosis predictions and that it could represent a valuable tool for knowledge dissemination among all interested health workers and researchers in this area.

Palavras Chave

amyotrophic lateral sclerosis, prognosis, machine learning, health informatics