AI-Rehab: A Framework for AI Driven Neurorehabilitation Training - The Profiling Challenge

Abstract

One of the health clinic challenges is rehabilitation therapy cognitive impairment that can happen after brain injury, dementia and in normal cognitive decline due to aging. Current cognitive rehabilitation therapy has been shown to be the most effective way to address this problem. However, a) it is not adaptive for every patient, b) it has a high cost, and c) it is usually implemented in clinical environments. The Task Generator (TG) is a free tool for the generation of cognitive training tasks. However, TG is not designed to adapt and monitor the cognitive progress of the patient. Hence, we propose in the BRaNT project an enhancement of TG with belief revision and machine learning techniques, gamification and remote monitoring capabilities to enable health professionals to provide a long-term personalized cognitive rehabilitation therapy at home. The BRaNT is an interdisciplinary effort that addresses scientific limitations of current practices as well as provides solutions towards the sustainability of health systems and contributes towards the improvement of quality of life of patients. This paper proposes the AI-Rehab framework for the BRaNT, explains profiling challenge in the situation of insufficient data and presents an alternate AI solutions which might be applicable once enough data is available.

Nuevas tecnologías e inteligencia artificial en neurorrehabilitación

“…En el plano diagnóstico, su aplicación en estudios de neuroimagen y pruebas neurofisiológicas facilitaría establecer un pronóstico funcional y temporal en escenarios complejos, como por ejemplo los estados alterados de consciencia 25 . Además, puede ayudar a definir subtipos y perfiles clínicos concretos que optimicen las indicaciones farmacológicas y neurorrehabilitadoras de cada paciente y su efectividad 26 .…”

“…Se dispone de modelos computacionales basados en IA capaces de registrar resultados y su evolución en el tiempo en los juegos terapéuticos indicados al paciente, parametrizando dichos datos y, a partir de estos, seleccionando nuevos ejercicios, posibilitando así un entrenamiento adaptativo. Esto genera una terapia individualizada con monitorización continua que libera de tareas al terapeuta, especialmente cuando este interviene a distancia 20,26,27 .…”

Enhancing accuracy in brain stroke detection: Multi-layer perceptron with Adadelta, RMSProp and AdaMax optimizers

“…Stroke, as per the American Heart Association, is a significant health concern due to its high fatality rate ( Benjamin et al, 2018 ). Moreover, the expenses associated with stroke-related hospitalizations are on the rise and there is demand of advanced technologies ( Di Carlo, 2009 ; Fermé et al, 2020 ). Stroke ranks as the 2nd leading cause of death, accounting for around 11% of all deaths.…”

Transfer Learning-Based Classification Comparison of Stroke

“…Additionally, there is an increased demand for improved technology that can aid in clinical diagnosis, treatment, forecasts of clinical events, recommendations of potential therapeutic approaches, rehabilitation programmers , etc. (Almeida, Y.;Bermúdez i Badia, S. and Fermé., 2020) due to the rising costs of stroke hospitalization (Di Carlo, 2009). For a stroke to be effectively treated, early diagnosis is essential, and ML and deep learning (DL) can be very helpful in this process.…”