ECG-based data-driven solutions for diagnosis and prognosis of cardiovascular diseases: A systematic review.

Cardiovascular diseases (CVD) are a leading cause of death globally, and result in significant morbidity and reduced quality of life. The electrocardiogram (ECG) plays a crucial role in CVD diagnosis, prognosis, and prevention; however, different challenges still remain, such as an increasing unmet demand for skilled cardiologists capable of accurately interpreting ECG. This leads to higher workload and potential diagnostic inaccuracies. Data-driven approaches, such as machine learning (ML) and deep learning (DL) have emerged to improve existing computer-assisted solutions and enhance physicians' ECG interpretation of the complex mechanisms underlying CVD. However, many ML and DL models used to detect ECG-based CVD suffer from a lack of explainability, bias, as well as ethical, legal, and societal implications (ELSI). Despite the critical importance of these Trustworthy Artificial Intelligence (AI) aspects, there is a lack of comprehensive literature reviews that examine the current trends in ECG-based solutions for CVD diagnosis or prognosis that use ML and DL models and address the Trustworthy AI requirements. This review aims to bridge this knowledge gap by providing a systematic review to undertake a holistic analysis across multiple dimensions of these data-driven models such as type of CVD addressed, dataset characteristics, data input modalities, ML and DL algorithms (with a focus on DL), and aspects of Trustworthy AI like explainability, bias and ethical considerations. Additionally, within the analyzed dimensions, various challenges are identified. To these, we provide concrete recommendations, equipping other researchers with valuable insights to understand the current state of the field comprehensively.

Assessing the relevance of mental health factors in fibromyalgia severity: A data-driven case study using explainable AI.

BACKGROUND AND OBJECTIVE: Fibromyalgia is a chronic disease that causes pain and affects patients' quality of life. Current treatments focus on pharmacological therapies for pain reduction. However, patients' psychological well-being is also affected, with depression and pain catastrophizing being common. This research addresses the clinicians' need to assess the influence of mental health factors on FM severity compared to pain factors. METHODS: A co-development study between FM clinicians and data scientists analyzed data from 166 FM-diagnosed patients to assess the influence of mental health factors on FM severity in comparison to pain factors. The study used the Polysymptomatic Distress Scale (PDS) and Fibromyalgia Impact Questionnaire (FIQ) as FM severity indicators and collected 15 variables including regarding demographics, pain intensity perceived, and mental health factors. The team used an author's developed framework to identify the optimal FM severity classifier and explainability by selecting a number of features that lead to obtaining the best classification result. Machine learning classifiers employed in the framework were: decision trees, logistic regression, support vector machines, random forests, AdaBoost, extra trees, and RUSBoost. Explainability analyses were conducted using the following explainable AI techniques: SHapley Additive exPlanations (SHAP), Partial Dependence Plot (PDP), and Mean Decrease Impurity (MDI). RESULTS: A balanced random forest with 6 features achieved the best performance with PDS (AUC_ROC, mean = 0.81, std = 0.07). Being FIQ the target variable, due to the imbalance in FM severity levels, a binary and a multiclass classification approaches were considered achieving the optimal performance, respectively, a logistic regression classifier (AUC_ROC, mean = 0.83, std = 0.08) with 6 selected features, and a random forest (AUC_ROC, mean = 0.91, std = 0.04) with 8 selected features. Next, the explainability analysis determined mental health factors were found to be more relevant than pain perceived factors for FM severity. CONCLUSIONS: This study's findings, validated by clinicians, are potentially aligned with FM international guidelines that promote non-pharmacological interventions such as promoting mental well-being of FM patients.

Improvement of a prediction model for heart failure survival through explainable artificial intelligence.

Cardiovascular diseases and their associated disorder of heart failure (HF) are major causes of death globally, making it a priority for doctors to detect and predict their onset and medical consequences. Artificial Intelligence (AI) allows doctors to discover clinical indicators and enhance their diagnoses and treatments. Specifically, "eXplainable AI" (XAI) offers tools to improve the clinical prediction models that experience poor interpretability of their results. This work presents an explainability analysis and evaluation of two HF survival prediction models using a dataset that includes 299 patients who have experienced HF. The first model utilizes survival analysis, considering death events and time as target features, while the second model approaches the problem as a classification task to predict death. The model employs an optimization data workflow pipeline capable of selecting the best machine learning algorithm as well as the optimal collection of features. Moreover, different post hoc techniques have been used for the explainability analysis of the model. The main contribution of this paper is an explainability-driven approach to select the best HF survival prediction model balancing prediction performance and explainability. Therefore, the most balanced explainable prediction models are Survival Gradient Boosting model for the survival analysis and Random Forest for the classification approach with a c-index of 0.714 and balanced accuracy of 0.74 (std 0.03) respectively. The selection of features by the SCI-XAI in the two models is similar where "serum_creatinine", "ejection_fraction", and "sex" are selected in both approaches, with the addition of "diabetes" for the survival analysis model. Moreover, the application of post hoc XAI techniques also confirm common findings from both approaches by placing the "serum_creatinine" as the most relevant feature for the predicted outcome, followed by "ejection_fraction". The explainable prediction models for HF survival presented in this paper would improve the further adoption of clinical prediction models by providing doctors with insights to better understand the reasoning behind usually "black-box" AI clinical solutions and make more reasonable and data-driven decisions.

Assessing Trustworthy AI in Times of COVID-19: Deep Learning for Predicting a Multiregional Score Conveying the Degree of Lung Compromise in COVID-19 Patients.

This article's main contributions are twofold: 1) to demonstrate how to apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice for the domain of healthcare and 2) to investigate the research question of what does "trustworthy AI" mean at the time of the COVID-19 pandemic. To this end, we present the results of a post-hoc self-assessment to evaluate the trustworthiness of an AI system for predicting a multiregional score conveying the degree of lung compromise in COVID-19 patients, developed and verified by an interdisciplinary team with members from academia, public hospitals, and industry in time of pandemic. The AI system aims to help radiologists to estimate and communicate the severity of damage in a patient's lung from Chest X-rays. It has been experimentally deployed in the radiology department of the ASST Spedali Civili clinic in Brescia, Italy, since December 2020 during pandemic time. The methodology we have applied for our post-hoc assessment, called Z-Inspection®, uses sociotechnical scenarios to identify ethical, technical, and domain-specific issues in the use of the AI system in the context of the pandemic.

Evaluation of Machine Learning Algorithms and Explainability Techniques to Detect Hearing Loss From a Speech-in-Noise Screening Test.

PURPOSE: The aim of this study was to analyze the performance of multivariate machine learning (ML) models applied to a speech-in-noise hearing screening test and investigate the contribution of the measured features toward hearing loss detection using explainability techniques. METHOD: Seven different ML techniques, including transparent (i.e., decision tree and logistic regression) and opaque (e.g., random forest) models, were trained and evaluated on a data set including 215 tested ears (99 with hearing loss of mild degree or higher and 116 with no hearing loss). Post hoc explainability techniques were applied to highlight the role of each feature in predicting hearing loss. RESULTS: Random forest (accuracy = .85, sensitivity = .86, specificity = .85, precision = .84) performed, on average, better than decision tree (accuracy = .82, sensitivity = .84, specificity = .80, precision = .79). Support vector machine, logistic regression, and gradient boosting had similar performance as random forest. According to post hoc explainability analysis on models generated using random forest, the features with the highest relevance in predicting hearing loss were age, number and percentage of correct responses, and average reaction time, whereas the total test time had the lowest relevance. CONCLUSIONS: This study demonstrates that a multivariate approach can help detect hearing loss with satisfactory performance. Further research on a bigger sample and using more complex ML algorithms and explainability techniques is needed to fully investigate the role of input features (including additional features such as risk factors and individual responses to low-/high-frequency stimuli) in predicting hearing loss.

A Social Network Analysis of Tweets Related to Masks during the COVID-19 Pandemic.

BACKGROUND: High compliance in wearing a mask is a crucial factor for stopping the transmission of COVID-19. Since the beginning of the pandemic, social media has been a key communication channel for citizens. This study focused on analyzing content from Twitter related to masks during the COVID-19 pandemic. METHODS: Twitter data were collected using the keyword "mask" from 27 June 2020 to 4 July 2020. The total number of tweets gathered were n = 452,430. A systematic random sample of 1% (n = 4525) of tweets was analyzed using social network analysis. NodeXL (Social Media Research Foundation, California, CA, USA) was used to identify users ranked influential by betweenness centrality and was used to identify key hashtags and content. RESULTS: The overall shape of the network resembled a community network because there was a range of users conversing amongst each other in different clusters. It was found that a range of accounts were influential and/or mentioned within the network. These ranged from ordinary citizens, politicians, and popular culture figures. The most common theme and popular hashtags to emerge from the data encouraged the public to wear masks. CONCLUSION: Towards the end of June 2020, Twitter was utilized by the public to encourage others to wear masks and discussions around masks included a wide range of users.

Monitoring and Intervention Technologies to Manage Diabetic Older Persons: The CAPACITY Case-A Pilot Study.

Diabetes Mellitus is a chronic disease with a high prevalence among older people, and it is related to an increased risk of functional and cognitive decline, in addition to classic micro and macrovascular disease and a moderate increase in the risk of death. Technology aimed to improve elder care and quality of life needs to focus in the early detection of decline, monitoring the functional evolution of the individuals and providing ways to foster physical activity, to recommend adequate nutritional habits and to control polypharmacy. But apart from all these core features, some other elements or modules covering disease-specific needs should be added to complement care. In the case of diabetes these functionalities could include control mechanisms for blood glucose and cardiovascular risk factors, specific nutritional recommendations, suited physical activity programs, diabetes-specific educational contents, and self-care recommendations. This research work focuses on those core aspects of the technology, leaving out disease-specific modules. These central technological components have been developed within the scope of two research and innovation projects (FACET and POSITIVE, funded by the EIT-Health), that revolve around the provision of integrated, continuous and coordinated care to frail older population, who are at a high risk of functional decline. Obtained results indicate that a geriatric multimodal intervention is effective for preventing functional decline and for reducing the use of healthcare resources if administered to diabetic pre-frail and frail older persons. And if such intervention is supported by the CAPACITY technological ecosystem, it becomes more efficient.

FriWalk robotic walker: usability, acceptance and UX evaluation after a pilot study in a real environment.

Background: Scientific evidence supports that prevention strategies like multicomponent physical exercise help avoiding functional decline, falls and frailty. The robotic walker FriWalk, developed within the ACANTO project, supports the execution of controlled physical activities during hospital admission to prevent functional deterioration associated to prolonged bedrest. FriWalk shows in a clinical validation study a positive relationship with improvement in physical performance, basic activities of daily living execution and frailty status. Usability, acceptance and user experience (UX) are key aspects to ease the adoption of assistive technologies in the elderly.Objective: This work pursues the evaluation of the usability, acceptance and UX of the FriWalk from the patients and clinical professionals' perspectives.Methods: Data collected during the validation of FriWalk in a real environment have been used. Forty-two patients recruited at Getafe University Hospital (Acute Care and Orthogeriatric Units) and one clinical professional participated. SUS, TAM, UX and ad hoc questionnaires were administered.Results: Patients provided an average SUS of 52.86 and provided valuable information in the qualitative acceptance interviews. The clinical professional provided an averaged SUS and TAM of 67 and 46.6, respectively, and evaluated all UX categories as above average.Conclusions: Usability results do not qualify FriWalk as above average; the reasons explaining this have been identified and point out to the prototypical stage of the hardware. Acceptance and UX were positively evaluated and allowed the research team to propose a new organizational model to deliver the FriWalk-based prevention program. FriWalk will be soon evolved.Implications for rehabilitationFriWalk showed in a randomized clinical trial a positive relationship with improvement in physical performance, basic activities of daily living execution and frailty status.In terms of usability, user experience (UX) and acceptance, participants of the study have valued the FriWalk robotic walker as a promising help, considering that the device that has been under evaluation was still in a prototype stage.Clinical professional reported FriWalk and its corresponding exercise program description software regarding usability, acceptance and UX as satisfactory tool to prescribe and assess a rehabilitation program for hospitalized patients.