Periodic Reporting for period 1 - MAESTRO (Novel machine learning techniques to improve the forecasting of stroke post-interventive outcomes)
Periodo di rendicontazione: 2022-03-01 al 2024-02-29
Strokes are acute medical conditions in which poor blood flow to a part of the brain results in neuronal death. According to the stroke alliance for Europe (SAFE), there were over 600,000 strokes in the EU in 2015. The same study indicates that strokes, as well as their associated medical costs, will significantly increase in the future. Without action, this will immensely exacerbate an existing problem. Worldwide, stroke is the second most common cause of death, and the leading cause of physical disability.
There are long-term risks associated with stroke: Inability to move, or feel, one side of the body, problems in verbal expression, or loss of vision, among others. Two lines of action must be applied in order to minimize these long-term risks. Firstly, an urgent intervention in the first hours after the stroke is critical. Secondly, the continuous monitoring during the rehabilitation phase is also critical, to ensure a positive outcome and minimize risks. According to the same SAFE report, only 30% of the survivors receive unit care, and despite its importance, access to rehabilitation and long-term support is a known problem.
The goal of MAESTRO is to explore wearable sensors and deep learning technologies to improve the effectiveness of monitoring during the rehabilitation phase after stroke. Among others, Deep Learning with Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN), Natural Language Processing (NLP), Outlier Detection (OD) and Distributed Parallel Computing (DPC) techniques will be used to improve the monitorization of rehabilitation effectiveness and adherence, and determine the predicted outcome of the patient after said rehabilitation process.
The expected result of MAESTRO is an algorithm, combined with sensors, that predicts the response to rehabilitation of stroke patients. Its novelty lies in the use of deep learning techniques and off-the-shelf hardware to predict rehabilitation effectiveness and monitor patient adherence.
The target of MAESTRO is to explore data acquisition and classification procedures and provide meaningful information that could then be sent to neurologists with minimal-to-no intervention on the part of the patient, and no direct intervention by the software developer. This will be used to predict post-stroke outcomes by using novel machine learning algorithms which allow a classification of patients based on their rehabilitation adherence and effectiveness. This goal is divided into three objectives:
1. Determine the suitability of an array of IoT sensors, wearables, biosignals, and/or other data sources, to determine the long-term outcomes of stroke.
2. Develop novel classification algorithms to predict the post-interventive outcome of stroke based on the conclusions of Objective 1, including a gamified application for data collection.
3. Implement and validate a prototypical system of post-interventive stroke outcome prediction based on the results of Objectives 1 and 2.
There are long-term risks associated with stroke: Inability to move, or feel, one side of the body, problems in verbal expression, or loss of vision, among others. Two lines of action must be applied in order to minimize these long-term risks. Firstly, an urgent intervention in the first hours after the stroke is critical. Secondly, the continuous monitoring during the rehabilitation phase is also critical, to ensure a positive outcome and minimize risks. According to the same SAFE report, only 30% of the survivors receive unit care, and despite its importance, access to rehabilitation and long-term support is a known problem.
The goal of MAESTRO is to explore wearable sensors and deep learning technologies to improve the effectiveness of monitoring during the rehabilitation phase after stroke. Among others, Deep Learning with Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN), Natural Language Processing (NLP), Outlier Detection (OD) and Distributed Parallel Computing (DPC) techniques will be used to improve the monitorization of rehabilitation effectiveness and adherence, and determine the predicted outcome of the patient after said rehabilitation process.
The expected result of MAESTRO is an algorithm, combined with sensors, that predicts the response to rehabilitation of stroke patients. Its novelty lies in the use of deep learning techniques and off-the-shelf hardware to predict rehabilitation effectiveness and monitor patient adherence.
The target of MAESTRO is to explore data acquisition and classification procedures and provide meaningful information that could then be sent to neurologists with minimal-to-no intervention on the part of the patient, and no direct intervention by the software developer. This will be used to predict post-stroke outcomes by using novel machine learning algorithms which allow a classification of patients based on their rehabilitation adherence and effectiveness. This goal is divided into three objectives:
1. Determine the suitability of an array of IoT sensors, wearables, biosignals, and/or other data sources, to determine the long-term outcomes of stroke.
2. Develop novel classification algorithms to predict the post-interventive outcome of stroke based on the conclusions of Objective 1, including a gamified application for data collection.
3. Implement and validate a prototypical system of post-interventive stroke outcome prediction based on the results of Objectives 1 and 2.
In MAESTRO, we explored data sources and sensor methods to monitor stroke patients in order to improve quality of care and outcome prediction accuracy. To do so, we conducted a systematic review of methods and data sources in 3- and 6-month stroke outcome prediction based on the modified Rankin scale (mRS). We observed that free-text notes, processed through pretrained large language models such as ClinicalBERT, show great promise in improving outcome prediction quality with minimal invasiveness. We conducted an early study on the limitations of ClinicalBERT leveraging ICU notes from the publicly available MIMIC-III dataset, and found key limitations that should be addressed in the future to make the output for this task clinically actionable. Separately, we acquired a corpus of actigraph data from stroke inpatients that were experiencing delirium. Using extreme gradient boosting classifiers and dynamic time warping, we observed an increase in delirium detection prediction accuracy compared to using other forms of clinical structured data exclusively.
The project was concluded early due to the ER receiving an employment offer. As a result, the latter project objectives were not fully accomplished. Nevertheless, we strongly believe the work conducted in MAESTRO will lead to key advances in clinical decision support for acute and chronic stroke management.
The project was concluded early due to the ER receiving an employment offer. As a result, the latter project objectives were not fully accomplished. Nevertheless, we strongly believe the work conducted in MAESTRO will lead to key advances in clinical decision support for acute and chronic stroke management.
The MAESTRO project has advanced beyond the state of the art in two key areas:
Firstly, we have proven that actigraph sensors, combined with extreme gradient boosting classifiers and dynamic time warping combined with other signal preprocessing methods, significantly increases classification accuracy when monitoring delirium in stroke inpatients.
Secondly, we have identified large language models (LLMs) as a key element of improving post-rehabilitative stroke outcome prediction.
These two advances show great promise to increase quality of care for stroke patients during both the acute and chronic phase of the disease. In the future, we will aim to train large language models across international datasets, leveraging methods such as federated learning and multilingual modeling, to produce highly functional LLMs that will enhance clinical decision support and reduce healthcare spending and documentation burden.
Firstly, we have proven that actigraph sensors, combined with extreme gradient boosting classifiers and dynamic time warping combined with other signal preprocessing methods, significantly increases classification accuracy when monitoring delirium in stroke inpatients.
Secondly, we have identified large language models (LLMs) as a key element of improving post-rehabilitative stroke outcome prediction.
These two advances show great promise to increase quality of care for stroke patients during both the acute and chronic phase of the disease. In the future, we will aim to train large language models across international datasets, leveraging methods such as federated learning and multilingual modeling, to produce highly functional LLMs that will enhance clinical decision support and reduce healthcare spending and documentation burden.