Integrating Chatbot Functionality in a Patient Summary Based Healthcare System.

The integration of chatbots in healthcare has gained attention due to their potential to enhance patient engagement and satisfaction. This paper presents a healthcare chatbot providing comprehensive access to patient summaries, aligned with the European Patient Summary. Leveraging Natural Language Processing (NLP) capabilities, our chatbot employs intent classification using the fine-tuned bioBERT model to categorize user queries effectively and extract relevant information from the patient summary stored in a database. We detail our methodology, which involves dataset creation, hyperparameter tuning, and model evaluation. Results demonstrate the effectiveness of our approach, with the trained model achieving high precision, recall, and F1 score across intent classes. Our study underscores the potential of emerging NLP techniques in patient interaction and healthcare delivery, covering the way for smarter, user-friendly companions.

Empowering Citizens Through Translated Patient Summary Access and Sharing in Digital Health Ecosystems.

This paper introduces a mobile framework designed to enhance citizen access to and sharing of health data, aiming to empower individuals with greater control over their personal health information. Accessing and sharing health-related data is essential in everyday scenarios, from routine doctor visits or viewing your health on your own to emergencies where swift access can save lives. It addresses the challenges posed by the fragmented nature of healthcare services and the barriers of language differences in patient records. The framework utilizes the EU eHealth Digital Service Infrastructure (eHDSI) OpenNCP for translating patient summaries and the FHIR Smart Health Links Protocol for secure sharing. A pilot study with 40 participants was conducted to assess the usability and effectiveness of the app, revealing a strong demand among citizens for such innovative health services.

Emergency Department Length of Stay Classification Based on Ensemble Methods and Rule Extraction.

This study employs machine learning techniques to identify factors that influence extended Emergency Department (ED) length of stay (LOS) and derives transparent decision rules to complement the results. Leveraging a comprehensive dataset, Gradient Boosting exhibited marginally superior predictive performance compared to Random Forest for LOS classification. Notably, variables like triage acuity and the Elixhauser Comorbidity Index (ECI) emerged as robust predictors. The extracted rules optimize LOS stratification and resource allocation, demonstrating the critical role of data-driven methodologies in improving ED workflow efficiency and patient care delivery.

An Overview of Explainable AI Studies in the Prediction of Sepsis Onset and Sepsis Mortality.

Explainable artificial intelligence (AI) focuses on developing models and algorithms that provide transparent and interpretable insights into decision-making processes. By elucidating the reasoning behind AI-driven diagnoses and treatment recommendations, explainability can gain the trust of healthcare experts and assist them in difficult diagnostic tasks. Sepsis is characterized as a serious condition that happens when the immune system of the body has an extreme response to an infection, causing tissue and organ damage and leading to death. Physicians face challenges in diagnosing and treating sepsis due to its complex pathogenesis. This work aims to provide an overview of the recent studies that propose explainable AI models in the prediction of sepsis onset and sepsis mortality using intensive care data. The general findings showed that explainable AI can provide the most significant features guiding the decision-making process of the model. Future research will investigate explainability through argumentation theory using intensive care data focused on sepsis patients.

Explainable AI Modeling in the Prediction of Cardiovascular Disease Risk.

The objective of this study was to develop explainable AI modeling in the prediction of cardiovascular disease. The XGBoost algorithm was used followed by rule extraction and argumentation theory that provides interpretability, explainability and accuracy in scenarios with low confidence results or dilemmas. Our findings are in agreement with previous research utilizing the XGBoost machine learning algorithm for prediction of cardiovascular risk, however it is supported by rule based explainability, offering significant advantages in terms of providing both global and local explainability. Further work is needed to enhance the argumentation-based rule interpretability, explainability and accuracy in scenarios with low confidence results or dilemmas.

Virtual Reality for Pulmonary Rehabilitation: Comprehensive Review.

BACKGROUND: Pulmonary rehabilitation is a vital component of comprehensive care for patients with respiratory conditions, such as lung cancer, chronic obstructive pulmonary disease, and asthma, and those recovering from respiratory diseases like COVID-19. It aims to enhance patients' functional ability and quality of life, and reduce symptoms, such as stress, anxiety, and chronic pain. Virtual reality is a novel technology that offers new opportunities for customized implementation and self-control of pulmonary rehabilitation through patient engagement. OBJECTIVE: This review focused on all types of virtual reality technologies (nonimmersive, semi-immersive, and fully immersive) that witnessed significant development and were released in the field of pulmonary rehabilitation, including breathing exercises, biofeedback systems, virtual environments for exercise, and educational models. METHODS: The review screened 7 electronic libraries from 2010 to 2023. The libraries were ACM Digital Library, Google Scholar, IEEE Xplore, MEDLINE, PubMed, Sage, and ScienceDirect. Thematic analysis was used as an additional methodology to classify our findings based on themes. The themes were virtual reality training, interaction, types of virtual environments, effectiveness, feasibility, design strategies, limitations, and future directions. RESULTS: A total of 2319 articles were identified, and after a detailed screening process, 32 studies were reviewed. Based on the findings of all the studies that were reviewed (29 with a positive label and 3 with a neutral label), virtual reality can be an effective solution for pulmonary rehabilitation in patients with lung cancer, chronic obstructive pulmonary disease, and asthma, and in individuals and children who are dealing with mental health-related disorders, such as anxiety. The outcomes indicated that virtual reality is a reliable and feasible solution for pulmonary rehabilitation. Interventions can provide immersive experiences to patients and offer tailored and engaging rehabilitation that promotes improved functional outcomes of pulmonary rehabilitation, breathing body awareness, and relaxation breathing techniques. CONCLUSIONS: The identified studies on virtual reality in pulmonary rehabilitation showed that virtual reality holds great promise for improving the outcomes and experiences of patients. The immersive and interactive nature of virtual reality interventions offers a new dimension to traditional rehabilitation approaches, providing personalized exercises and addressing psychological well-being. However, additional research is needed to establish standardized protocols, identify the most effective strategies, and evaluate long-term benefits. As virtual reality technology continues to advance, it has the potential to revolutionize pulmonary rehabilitation and significantly improve the lives of patients with chronic lung diseases.

Offering Outworld Experiences to In-Patients With Dementia Through Virtual Reality: Mixed Methods Study.

Background: Research has suggested that institutionalization can increase the behavioral and psychological symptoms of dementia. To date, recent studies have reported a growing number of successful deployments of virtual reality for people with dementia to alleviate behavioral and psychological symptoms of dementia and improve quality of life. However, virtual reality has yet to be rigorously evaluated, since the findings are still in their infancy, with nonstatistically significant and inconclusive results. Objective: Unlike prior works, to overcome limitations in the current literature, our virtual reality system was co-designed with people with dementia and experts in dementia care and was evaluated with a larger population of patients with mild to severe cases of dementia. Methods: Working with 44 patients with dementia and 51 medical experts, we co-designed a virtual reality system to enhance the symptom management of in-patients with dementia residing in long-term care. We evaluated the system with 16 medical experts and 20 people with dementia. Results: This paper explains the screening process and analysis we used to identify which environments patients would like to receive as an intervention. We also present the system's evaluation results by discussing their impact in depth. According to our findings, virtual reality contributes significantly to the reduction of behavioral and psychological symptoms of dementia, especially for aggressive, agitated, anxious, apathetic, depressive, and fearful behaviors. Conclusions: Ultimately, we hope that the results from this study will offer insight into how virtual reality technology can be designed, deployed, and used in dementia care.

Toward objective monitoring of Parkinson's disease motor symptoms using a wearable device: wearability and performance evaluation of PDMonitor®.

Parkinson's disease (PD) is characterized by a variety of motor and non-motor symptoms. As disease progresses, fluctuations in the response to levodopa treatment may develop, along with emergence of freezing of gait (FoG) and levodopa induced dyskinesia (LiD). The optimal management of the motor symptoms and their complications, depends, principally, on the consistent detection of their course, leading to improved treatment decisions. During the last few years, wearable devices have started to be used in the clinical practice for monitoring patients' PD-related motor symptoms, during their daily activities. This work describes the results of 2 multi-site clinical studies (PDNST001 and PDNST002) designed to validate the performance and the wearability of a new wearable monitoring device, the PDMonitor®, in the detection of PD-related motor symptoms. For the studies, 65 patients with Parkinson's disease and 28 healthy individuals (controls) were recruited. Specifically, during the Phase I of the first study, participants used the monitoring device for 2-6 h in a clinic while neurologists assessed the exhibited parkinsonian symptoms every half hour using the Unified Parkinson's Disease Rating Scale (UPDRS) Part III, as well as the Abnormal Involuntary Movement Scale (AIMS) for dyskinesia severity assessment. The goal of Phase I was data gathering. On the other hand, during the Phase II of the first study, as well as during the second study (PDNST002), day-to-day variability was evaluated, with patients in the former and with control subjects in the latter. In both cases, the device was used for a number of days, with the subjects being unsupervised and free to perform any kind of daily activities. The monitoring device produced estimations of the severity of the majority of PD-related motor symptoms and their fluctuations. Statistical analysis demonstrated that the accuracy in the detection of symptoms and the correlation between their severity and the expert evaluations were high. As a result, the studies confirmed the effectiveness of the system as a continuous telemonitoring solution, easy to be used to facilitate decision-making for the treatment of patients with Parkinson's disease.

A cross-sectional study of explainable machine learning in Alzheimer's disease: diagnostic classification using MR radiomic features.

Introduction: Alzheimer's disease (AD) even nowadays remains a complex neurodegenerative disease and its diagnosis relies mainly on cognitive tests which have many limitations. On the other hand, qualitative imaging will not provide an early diagnosis because the radiologist will perceive brain atrophy on a late disease stage. Therefore, the main objective of this study is to investigate the necessity of quantitative imaging in the assessment of AD by using machine learning (ML) methods. Nowadays, ML methods are used to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers in the assessment of AD. Methods: In this study radiomic features from both entorhinal cortex and hippocampus were extracted from 194 normal controls (NC), 284 mild cognitive impairment (MCI) and 130 AD subjects. Texture analysis evaluates statistical properties of the image intensities which might represent changes in MRI image pixel intensity due to the pathophysiology of a disease. Therefore, this quantitative method could detect smaller-scale changes of neurodegeneration. Then the radiomics signatures extracted by texture analysis and baseline neuropsychological scales, were used to build an XGBoost integrated model which has been trained and integrated. Results: The model was explained by using the Shapley values produced by the SHAP (SHapley Additive exPlanations) method. XGBoost produced a f1-score of 0.949, 0.818, and 0.810 between NC vs. AD, MC vs. MCI, and MCI vs. AD, respectively. Discussion: These directions have the potential to help to the earlier diagnosis and to a better manage of the disease progression and therefore, develop novel treatment strategies. This study clearly showed the importance of explainable ML approach in the assessment of AD.

MYeHealthAppCY: A Healthcare Mobile Application in Cyprus.

This paper presents MYeHealthAppCY, an mHealth solution designed to provide patients and healthcare providers in Cyprus with access to medical data. The application includes features such as an at-a-glance view of patient summary, comprehensive prescription management, teleconsultation, and the ability to store and access European Digital COVID Certificates (EUDCC). The application is an integral part of the eHealth4U platform targeting to implement a prototype EHR platform for national use. The application developed is based on FHIR and follows a strict adherence to widely used coding standards. The application was evaluated receiving satisfactory scores; however, significant work is still needed to deploy the application in production.

eHealth4U: A DEMO of a Prototype National Electronic Health Record for Cyprus.

In this paper we present a demonstration of a prototype national Electronic Health Record platform for Cyprus. This prototype is developed using the HL7 FHIR interoperability standard in combination with terminologies widely adopted by the clinical community such as the SNOMED CT and the LOINC. The system is organized in such a way to be user-friendly for its users, being the doctors and the citizens. The health-related data of this EHR are separated into three main sections, being the "Medical History", the "Clinical Examination" and the "Laboratory results". Business requirements include the Patient Summary as defined by the guidelines of the eHealth network and the International Patient Summary which are used as the base for all the sections of our EHR, together with additional medical information and functionality such as the organization of medical teams or the history of medical visits and episodes of care. From the doctor's point of view, one can search for patients who have granted the doctor with a consent and read or add/edit their EHR data by initiating a new visit as defined in the Cyprus National Law for eHealth. At the same time, doctors can organize their medical teams by managing the locations of each team and the members that belong to each team.

Affective Out-World Experience via Virtual Reality for Older Adults Living with Mild Cognitive Impairments or Mild Dementia.

Older adults with cognitive impairments may face barriers to accessing experiences beyond their physical premises. Previous research has suggested that missing out on emotional experiences may affect mental health and impact cognitive abilities. In recent years, there has been growing research interest in designing non-pharmacological interventions to improve the health-related quality of life of older adults. With virtual reality offering endless opportunities for health support, we must consider how virtual reality can be sensitively designed to provide comfortable, enriching out-world experiences to older adults to enhance their emotional regulation. Thirty older adults living with mild cognitive impairment or mild dementia participated in the study. Affect and emotional behavior were measured. The usability and the sense of presence were also assessed. Finally, we assessed the virtual reality experiences based on physiological responses and eye-tracking data. The results indicated that virtual reality can positively enhance the mental health of this population by eliciting a positive affective state and enhancing their emotional regulation. Overall, this paper raises awareness of the role of virtual reality in emotion elicitation, regulation, and expression and enhances our understanding of the use of virtual reality by older adults living with mild cognitive impairments or mild dementia.

Computer-Aided Diagnosis by Tissue Image Analysis as an Optical Biopsy in Hysteroscopy.

This review of our experience in computer-assisted tissue image analysis (CATIA) research shows that significant information can be extracted and used to diagnose and distinguish normal from abnormal endometrium. CATIA enabled the evaluation and differentiation between the benign and malignant endometrium during diagnostic hysteroscopy. The efficacy of texture analysis in the endometrium image during hysteroscopy was examined in 40 women, where 209 normal and 209 abnormal regions of interest (ROIs) were extracted. There was a significant difference between normal and abnormal endometrium for the statistical features (SF) features mean, variance, median, energy and entropy; for the spatial grey-level difference matrix (SGLDM) features contrast, correlation, variance, homogeneity and entropy; and for the gray-level difference statistics (GLDS) features homogeneity, contrast, energy, entropy and mean. We further evaluated 52 hysteroscopic images of 258 normal and 258 abnormal endometrium ROIs, and tissue diagnosis was verified by histopathology after biopsy. The YCrCb color system with SF, SGLDM and GLDS color texture features based on support vector machine (SVM) modeling correctly classified 81% of the cases with a sensitivity and a specificity of 78% and 81%, respectively, for normal and hyperplastic endometrium. New technical and computational advances may improve optical biopsy accuracy and assist in the precision of lesion excision during hysteroscopy. The exchange of knowledge, collaboration, identification of tasks and CATIA method selection strategy will further improve computer-aided diagnosis implementation in the daily practice of hysteroscopy.

Carotid Ultrasound Boundary Study (CUBS): Technical considerations on an open multi-center analysis of computerized measurement systems for intima-media thickness measurement on common carotid artery longitudinal B-mode ultrasound scans.

After publishing an in-depth study that analyzed the ability of computerized methods to assist or replace human experts in obtaining carotid intima-media thickness (CIMT) measurements leading to correct therapeutic decisions, here the same consortium joined to present technical outlooks on computerized CIMT measurement systems and provide considerations for the community regarding the development and comparison of these methods, including considerations to encourage the standardization of computerized CIMT measurements and results presentation. A multi-center database of 500 images was collected, upon which three manual segmentations and seven computerized methods were employed to measure the CIMT, including traditional methods based on dynamic programming, deformable models, the first order absolute moment, anisotropic Gaussian derivative filters and deep learning-based image processing approaches based on U-Net convolutional neural networks. An inter- and intra-analyst variability analysis was conducted and segmentation results were analyzed by dividing the database based on carotid morphology, image signal-to-noise ratio, and research center. The computerized methods obtained CIMT absolute bias results that were comparable with studies in literature and they generally were similar and often better than the observed inter- and intra-analyst variability. Several computerized methods showed promising segmentation results, including one deep learning method (CIMT absolute bias = 106 ± 89 µm vs. 160 ± 140 µm intra-analyst variability) and three other traditional image processing methods (CIMT absolute bias = 139 ± 119 µm, 143 ± 118 µm and 139 ± 136 µm). The entire database used has been made publicly available for the community to facilitate future studies and to encourage an open comparison and technical analysis (https://doi.org/10.17632/m7ndn58sv6.1).

A fast supervised density-based discretization algorithm for classification tasks in the medical domain.

Discretization is a preprocessing technique used for converting continuous features into categorical. This step is essential for processing algorithms that cannot handle continuous data as input. In addition, in the big data era, it is important for a discretizer to be able to efficiently discretize data. In this paper, a new supervised density-based discretization (DBAD) algorithm is proposed, which satisfies these requirements. For the evaluation of the algorithm, 11 datasets that cover a wide range of datasets in the medical domain were used. The proposed algorithm was tested against three state-of-the art discretizers using three classifiers with different characteristics. A parallel version of the algorithm was evaluated using two synthetic big datasets. In the majority of the performed tests, the algorithm was found performing statistically similar or better than the other three discretization algorithms it was compared to. Additionally, the algorithm was faster than the other discretizers in all of the performed tests. Finally, the parallel version of DBAD shows almost linear speedup for a Message Passing Interface (MPI) implementation (9.64× for 10 nodes), while a hybrid MPI/OpenMP implementation improves execution time by 35.3× for 10 nodes and 6 threads per node.

Is Computer-Assisted Tissue Image Analysis the Future in Minimally Invasive Surgery? A Review on the Current Status of Its Applications.

PURPOSE: Computer-assisted tissue image analysis (CATIA) enables an optical biopsy of human tissue during minimally invasive surgery and endoscopy. Thus far, it has been implemented in gastrointestinal, endometrial, and dermatologic examinations that use computational analysis and image texture feature systems. We review and evaluate the impact of in vivo optical biopsies performed by tissue image analysis on the surgeon's diagnostic ability and sampling precision and investigate how operation complications could be minimized. METHODS: We performed a literature search in PubMed, IEEE, Xplore, Elsevier, and Google Scholar, which yielded 28 relevant articles. Our literature review summarizes the available data on CATIA of human tissues and explores the possibilities of computer-assisted early disease diagnoses, including cancer. RESULTS: Hysteroscopic image texture analysis of the endometrium successfully distinguished benign from malignant conditions up to 91% of the time. In dermatologic studies, the accuracy of distinguishing nevi melanoma from benign disease fluctuated from 73% to 81%. Skin biopsies of basal cell carcinoma and melanoma exhibited an accuracy of 92.4%, sensitivity of 99.1%, and specificity of 93.3% and distinguished nonmelanoma and normal lesions from benign precancerous lesions with 91.9% and 82.8% accuracy, respectively. Gastrointestinal and endometrial examinations are still at the experimental phase. CONCLUSIONS: CATIA is a promising application for distinguishing normal from abnormal tissues during endoscopic procedures and minimally invasive surgeries. However, the efficacy of computer-assisted diagnostics in distinguishing benign from malignant states is still not well documented. Prospective and randomized studies are needed before CATIA is implemented in clinical practice.

A Prototype of the National EHR system for Cyprus.

The aim of this paper is to present Cyprus' initiative for the design and the implementation of the prototype of the integrated electronic health record at a national level that will establish the foundations of the country's broader eHealth ecosystem. The latter, requires an interdisciplinary approach and scientific collaboration among various fields, including medicine, information and communication technologies, management, and finance, among others. The objective, is to design the system architecture, specify the requirements in terms of clinical content as well as the hardware infrastructure, but also implement European and national legislation with respect to privacy and security that govern sensitive medical data manipulation. The present study summarizes the outcomes of the 1st phase of this initiative, which comprises of the healthcare as well as the administrative requirements, user stories, data-flows and associated functionality. Moreover, leveraging the HL7 Fast Healthcare Interoperability Resources (FHIR) standard we highlight the concluded interoperability framework that allows genuine cross-system communication and defines third-party systems connectivity.Clinical Relevance- This work is strongly correlated with medicine since it describes the system requirements and the architecture of a national integrated electronic health records system.

The Effects of Specific Omega-3 and Omega-6 Polyunsaturated Fatty Acids and Antioxidant Vitamins on Gait and Functional Capacity Parameters in Patients with Relapsing-Remitting Multiple Sclerosis.

Patients with multiple sclerosis (MS) are characterized by, among other symptoms, impaired functional capacity and walking difficulties. Polyunsaturated fatty acids (PUFAs) have been found to improve MS patients' clinical outcomes; however, their effect on other parameters associated with daily living activities need further investigation. The current study aimed to examine the effect of a 24-month supplementation with a cocktail dietary supplement formula, the NeuroaspisTM PLP10, containing specific omega-3 and omega-6 PUFAs and specific antioxidant vitamins on gait and functional capacity parameters of patients with MS. Fifty-one relapsing-remitting MS (RRMS) patients with low disability scores (age: 38.4 ± 7.1 years; 30 female) were randomized 1:1 to receive either a 20 mL daily dose of the dietary formula containing a mixture of omega-3 and omega-6 PUFAs (12,150 mg), vitamin A (0.6 mg), vitamin E (22 mg), and γ-tocopherol (760 mg), the OMEGA group (n = 27; age: 39 ± 8.3 years), or 20 mL placebo containing virgin olive oil, the placebo group (n = 24; age: 37.8 ± 5.3 years). The mean ± SD (standard deviation) Expanded Disability Status Scale (EDSS) score for the placebo group was 2.36 and for the OMEGA group 2.22. All enrolled patients in the study were on Interferon-ß treatment. Spatiotemporal gait parameters and gait deviation index (GDI) were assessed using a motion capture system. Functional capacity was examined using various functional tests such as the six-minute walk test (6MWT), two sit-to-stand tests (STS-5 and STS-60), and the Timed Up and Go test (TUG). Isometric handgrip strength was assessed by a dynamometer. Leg strength was assessed using an isokinetic dynamometer. All assessments were performed at baseline and at 12 and 24 months of supplementation. A total of 36 patients completed the study (18 from each group). Six patients from the placebo group and 9 patients from the OMEGA group dropped out from the study or were lost to follow-up. The dietary supplement significantly improved the single support time and the step and stride time (p < 0.05), both spatiotemporal gait parameters. In addition, while GDI of the placebo group decreased by about 10% at 24 months, it increased by about 4% in the OMEGA group (p < 0.05). Moreover, performance in the STS-60 test improved in the OMEGA group (p < 0.05) and there was a tendency for improvement in the 6MWT and TUG tests. Long-term supplementation with high dosages of omega-3 and omega-6 PUFAs (compared to previous published clinical studies using PUFAs) and specific antioxidant vitamins improved some functional capacity and gait parameters in RRMS patients.

Association of Intima-Media Texture With Prevalence of Clinical Cardiovascular Disease.

Recent studies have suggested that textural characteristics of the intima-media complex (IMC) may be more useful than the intima-media thickness (IMT) in evaluating cardiovascular risk. The primary aim of our study was to investigate the association between texture features of the common carotid IMC and prevalent clinical cardiovascular disease (CVD). The secondary aim was to determine whether IMT and IMC texture features vary between the left and right carotid arteries. The study was performed on 2208 longitudinal-section ultrasound images of the left (L) and right (R) common carotid artery (CCA), acquired from 569 men and 535 women out of which 125 had clinical CVD. L and R sides of the IMC were intensity normalized and despeckled. The IMC was semiautomatically delineated for all images using a semiautomated segmentation system, and 61 different texture features were extracted. The corresponding IMT semiautomated measurements (mean±SD) of the L and R sides were 0.73±0.21 mm/0.69±0.19 mm for the normal population and 0.83±0.17 mm/0.79±0.18 mm for those with CVD. IMC texture features did not differ between the right- and left-hand sides. Several texture features were independent predictors of the presence of CVD. The multivariate logistic regression analysis combining age, IMT, and texture features produced a receiver operating characteristic curve with an area under the curve of 89%. A correct classification rate of 77% for separating the normal subject (NOR) versus CVD subjects was achieved using the support vector machine classifier with a combination of clinical features, IMT, and extracted texture features. Texture features provide additional information on the presence of clinical CVD, which is over and above that provided by conventional risk factors or IMT alone. The value of IMC texture features in the prediction of future cardiovascular events should be tested in prospective studies.