Scoring systems, expert assessment, and identification of risk factors for the emergence of delirium in paediatric patients: Prospective cohort study.

INTRODUCTION: Emergence delirium (ED) is a transient irritative and dissociative state that arises after the cessation of anaesthesia in patients who do not respond to calming measures. There are many risk factors for ED, but the exact cause and underlying mechanism have not been determined because the definition of ED is still unclear in consensus. This study aims to determine ED incidence, identify ED risk factors and external validation of Watcha, Cravero and expert assessment to Pediatric Anesthesia Emergence Delirium (PAED) scoring system in ED prediction. MATERIALS AND METHODS: This study is a prospective cohort study on 79 paediatrics who underwent elective surgery with general anaesthesia. Parameter measures include the incidence of ED, ED risk factors, and the relationship between PAED, Watcha, Cravero score and expert assessment. The ED risk factor was analysed using univariate and multivariate analysis. The relationship between PAED, Watcha, Cravero score, and expert assessment was determined using Receiver Operating Characteristic (ROC) curve analysis. RESULTS: The incidence of ED was 22.8%. All parameters examined in this study showed p < 0.05. Watcha's scoring correlates with the PAED scoring and shows the highest discrimination ability with AUC 0.741 and p < 0.05. CONCLUSION: The incidence of ED in paediatrics is relatively high. Compared to others, Watcha score are more reliable for ED prediction. However, some demographic and perioperative factors are not the risk factor of ED.

Diagnosis of heart diseases: A fuzzy-logic-based approach.

Cardiovascular diseases (CVD) also known as heart disease are now the leading cause of death in the world. This paper presents research for the design and creation of a fuzzy logic-based expert system for the prognosis and diagnosis of heart disease that is precise, economical, and effective. This system entails a fuzzification module, knowledge base, inference engine, and defuzzification module where seven attributes such as chest pain type, HbA1c (Haemoglobin A1c), HDL (high-density lipoprotein), LDL (low-density lipoprotein), heart rate, age, and blood pressure are considered as input to the system. With the aid of the available literature and extensive consultation with medical experts in this field, an enriched knowledge database has been created with a sufficient number of IF-THEN rules for the diagnosis of heart disease. The inference engine then activates the appropriate IF-THEN rule from the knowledge base and determines the output value using the appropriate defuzzification technique after the fuzzification module fuzzifies each input depending on the appropriate membership function. Moreover, the fusion of web-based technology makes it suitable and cost-effective for the prognosis of heart disease for a patient and then he can take his decision for addressing the problem based on the status of his heart. On the other hand, it can also assist a medical practitioner to reach a more accurate conclusion regarding the treatment of heart disease for a patient. The Mamdani inference method has been used to evaluate the results. The system is tested with the Cleveland dataset and cross-checked with the in-field dataset. Compared with the other existing expert systems, the proposed method performs 98.08% accurately and can make accurate decisions for diagnosing heart diseases.

Designing, validation and evaluation of the expert system of "Healthy Menopause" and assessing its effect on the management of menopause symptoms: an exploratory mixed method study protocol.

BACKGROUND: Menopause is a period of women's life that has the especial physical, psychological and social challenges. So provision of an effective, practical and affordable way for meeting women's related needs is important. In addition, women should be able to incorporate such programs into their daily work. Considering the dearth of suitable services in this regard, this study will be conducted with the aim of designing, validating and evaluating the "Healthy Menopause" expert system on the management of menopausal symptoms. METHODS/DESIGN: A mixed methods exploratory design will be used to conduct this study in 3 phases. The first phase is a qualitative conventional content analysis study with purposes of exploring the women's experience of menopausal symptoms and extracting their needs, and collecting data about their expectations from a healthy menopause expert system.. The purposive sampling (In his phase data will be gathered through interviewing menopaused women aged 40 to 60 years old and other persons that have rich information in this regard and will be continued until data saturation. The second phase includes designing a healthy menopause expert system in this stage, the needs will be extracted from the qualitative findings along with a comprehensive literature review. The extracted needs will be again confirmed by the participants. Then, through a participatory approach (Participatory Design) using nominal group or Delphi technique the experts' opinion about the priority needs of menopaused women and related solutions will be explored based on the categories of identified needs. Such findings will be used to design a healthy menopause expert system at this stage. The third phase of study is a quantitative research in which the evaluation of the healthy menopause expert system will be done through a randomized controlled clinical trial with the aim of determining the effect of the healthy menopause expert system on the management of menopause symptoms by menopausal women themselves. DISCUSSION: This is the first study that uses a mixed method approach for designing, validating and evaluating of the expert system "Healthy Menopause". This study will fill the research gap in the field of improving menopausal symptoms and designing a healthy menopause expert system based on the needs of the large group of menopause women. We hope that by applying this expert system, the menopausal women be empowered to management and improving their health with an easy and affordable manner.

Menopause is a period of women's life that has the especial physical, psychological and social challenges. So provision of an effective, easy for use and affordable way for managing related problems and meeting related needs is important. Menopause is a period of women's life that has physical, psychological and social consequences. It is important to identify methods that are effective, practical and affordable. New technologies can increase women's ability to access educational information. This is the first study for designing, validating and evaluating of the expert system "Healthy Menopause". A mixed methods exploratory design will be used to conduct this study in 3 phases. The first phase (qualitative): The conventional content analysis method will be used. The second phase: Designing a healthy menopause expert system: It is based on the codes of women's challenges from the first phase, along with conducting interviews and literature review. The participatory approach (Participatory Design) through nominal group or if needed, Delphi method based on the categories of needs and solutions by considering the opinions of the participants, available experts related to this issue will be listed. It should be used to design a healthy menopause expert system at this stage. The third phase (quantitative): The evaluation of the healthy menopause expert system will be a randomized clinical trial that determine the effect of the healthy menopause expert system on the management of menopause symptoms. In the present study an expert system (ES) will be designed that can be installed on mobile phones and computers. This tool is not only educational but also interactively helps to adapt to continuous changes, so by asking questions about menopause the system will respond as if an expert (midwife or gynecologist) is giving advice.

Patient-Centered Clinical Decision Support-Where Are We and Where to Next?

Patient-centered clinical decision support (PC CDS) includes digital health tools that support patients, caregivers, and care teams in healthcare decisions that incorporate patient-centered factors related to four components: knowledge, data, delivery, and use. This paper explores the current state of each factor and how each promotes patient-centeredness in healthcare. We conducted a literature review, reviewing 175 peer-reviewed and grey literature, and eighteen key informant interviews. Findings show a need for more research on how to incorporate patient input into the guideline selection and prioritization for PC CDS, development and implementation of PC CDS tools, technical challenges for capturing patient contributed data, and optimizing PC CDS across various settings to meet patient and caregiver needs. While progress is being made in each of the four components of PC CDS, critical gaps remain.

Assessing the Safety of a New Clinical Decision Support System for a National Helpline.

We assessed the safety of a new clinical decision support system (CDSS) for nurses on Australia's national consumer helpline. Accuracy and safety of triage advice was assessed by testing the CDSS using 78 standardised patient vignettes (48 published and 30 proprietary). Testing was undertaken in two cycles using the CDSS vendor's online evaluation tool (Cycle 1: 47 vignettes; Cycle 2: 41 vignettes). Safety equivalence was examined by testing the existing CDSS with the 47 vignettes from Cycle 1. The new CDSS triaged 66% of vignettes correctly compared to 57% by the existing CDSS. 15% of vignettes were overtriaged by the new CDSS compared to 28% by the existing CDSS. 19% of vignettes were undertriaged by the new CDSS compared to 15% by the existing CDSS. Overall performance of the new CDSS appears consistent and comparable with current studies. The new CDSS is at least as safe as the old CDSS.

An expert-based system to predict population survival rate from health data.

Timely detection and understanding of causes for population decline are essential for effective wildlife management and conservation. Assessing trends in population size has been the standard approach, but we propose that monitoring population health could prove more effective. We collated data from 7 bottlenose dolphin (Tursiops truncatus) populations in the southeastern United States to develop a method for estimating survival probability based on a suite of health measures identified by experts as indices for inflammatory, metabolic, pulmonary, and neuroendocrine systems. We used logistic regression to implement the veterinary expert system for outcome prediction (VESOP) within a Bayesian analysis framework. We fitted parameters with records from 5 of the sites that had a robust network of responders to marine mammal strandings and frequent photographic identification surveys that documented definitive survival outcomes. We also conducted capture-mark-recapture (CMR) analyses of photographic identification data to obtain separate estimates of population survival rates for comparison with VESOP survival estimates. The VESOP analyses showed that multiple measures of health, particularly markers of inflammation, were predictive of 1- and 2-year individual survival. The highest mortality risk 1 year following health assessment related to low alkaline phosphatase (odds ratio [OR] = 10.2 [95% CI: 3.41-26.8]), whereas 2-year mortality was most influenced by elevated globulin (OR = 9.60 [95% CI: 3.88-22.4]); both are markers of inflammation. The VESOP model predicted population-level survival rates that correlated with estimated survival rates from CMR analyses for the same populations (1-year Pearson's r = 0.99, p = 1.52 × 10-5 ; 2-year r = 0.94, p = 0.001). Although our proposed approach will not detect acute mortality threats that are largely independent of animal health, such as harmful algal blooms, it can be used to detect chronic health conditions that increase mortality risk. Random sampling of the population is important and advancement in remote sampling methods could facilitate more random selection of subjects, obtainment of larger sample sizes, and extension of the approach to other wildlife species.

Un sistema basado en conocimiento experto para predecir la tasa de supervivencia a partir de datos de salud Resumen La detección y el entendimiento oportunos de la declinación poblacional son esenciales para que el manejo y la conservación de fauna tengan efectividad. La evaluación de las tendencias en el tamaño poblacional ha sido la estrategia estándar, pero proponemos que el monitoreo de la salud poblacional podría ser más efectivo. Recopilamos datos de siete poblaciones de delfines (Tursiops truncatus) en el sureste de Estados Unidos para desarrollar un método de estimación de la probabilidad de supervivencia con base en un conjunto de medidas sanitarias identificadas por expertos como índices para los sistemas inflamatorio, metabólico, pulmonar y neuroendocrino. Usamos la regresión logística para implementar el sistema de expertos veterinarios para la predicción de resultados (SEVPR) en un análisis bayesiano. Ajustamos los parámetros con los registros de cinco sitios que contaban con una buena red de respondientes a los varamientos de mamíferos marinos y censos de identificación fotográfica (foto-ID) que documentaron los resultados de supervivencia definitivos. También realizamos análisis de marcaje-recaptura (MR) en los datos de identificación fotográfica para obtener estimados separados de las tasas de supervivencia poblacional para compararlos con los estimados del SEVPR. Los análisis del SEVPR mostraron que varias medidas sanitarias, particularmente los marcadores de inflamación son buenos predictores de la supervivencia individual para uno y dos años. El riesgo de mortalidad más alto un año después de la valoración sanitaria se relacionó con una fosfatasa alcalina baja (cociente de probabilidades de 10.2 [95% CI 3.41-26.8]), mientras que la mortalidad a los dos años estuvo más influenciada por una globulina elevada (9.60 [95% CI 3.88-22.4]); ambas son marcadores de la inflamación. El modelo del SEVPR predijo las tasas de supervivencia a nivel poblacional en correlación con las tasas estimadas de supervivencia de los análisis de MR para las mismas poblaciones (Pearson de un año r = 0.99, p = 1.52e-05; dos años r = 0.94, p = 0.001). Aunque nuestra propuesta no detecta las amenazas agudas de mortalidad que en su mayoría son independientes de la salud animal, como la proliferación de algas nocivas, puede usarse para detectar las condiciones crónicas de salud que incrementan el riesgo de mortalidad. Es importante el muestreo aleatorio de la población y los avances en los métodos de muestreo remoto podrían facilitar una selección más aleatoria de los sujetos, la obtención de muestras de mayor tamaño y la expansión de la estrategia a otras especies de fauna.

Semi-supervised breast cancer pathology image segmentation based on fine-grained classification guidance.

Breast cancer pathological image segmentation (BCPIS) holds significant value in assisting physicians with quantifying tumor regions and providing treatment guidance. However, achieving fine-grained semantic segmentation remains a major challenge for this technology. The complex and diverse morphologies of breast cancer tissue structures result in high costs for manual annotation, thereby limiting the sample size and annotation quality of the dataset. These practical issues have a significant impact on the segmentation performance. To overcome these challenges, this study proposes a semi-supervised learning model based on classification-guided segmentation. The model first utilizes a multi-scale convolutional network to extract rich semantic information and then employs a multi-expert cross-layer joint learning strategy, integrating a small number of labeled samples to iteratively provide the model with class-generated multi-cue pseudo-labels and real labels. Given the complexity of the breast cancer samples and the limited sample quantity, an innovative approach of augmenting additional unlabeled data was adopted to overcome this limitation. Experimental results demonstrate that, although the proposed model falls slightly behind supervised segmentation models, it still exhibits significant progress and innovation. The semi-supervised model in this study achieves outstanding performance, with an IoU (Intersection over Union) value of 71.53%. Compared to other semi-supervised methods, the model developed in this study demonstrates a performance advantage of approximately 3%. Furthermore, the research findings indicate a significant correlation between the classification and segmentation tasks in breast cancer pathological images, and the guidance of a multi-expert system can significantly enhance the fine-grained effects of semi-supervised semantic segmentation.

Assessment and personalised advice for fatigue in systemic lupus erythematosus using an innovative digital tool: the Lupus Expert system for the Assessment of Fatigue (LEAF) study.

BACKGROUND: Fatigue is reported as the most prevalent symptom by patients with systemic lupus erythematosus (SLE). Fatigue management is complex due to its multifactorial nature. The aim of the study was to assess the usefulness of an innovative digital tool to manage fatigue in SLE, in a completely automated manner. METHODS: The «Lupus Expert System for Assessment of Fatigue¼ (LEAF) is free digital tool which measures the intensity and characteristics of fatigue and assesses disease activity, pain, insomnia, anxiety, depression, stress, fibromyalgia and physical activity using validated patient-reported instruments. Then, LEAF automatically provides personalised feedback and recommendations to cope with fatigue. RESULTS: Between May and November 2022, 1250 participants with SLE were included (95.2% women, median age 43yo (IQR: 34-51)). Significant fatigue (Functional Assessment of Chronic Illness Therapy-Fatigue <34) was reported by 78.9% of patients. In univariate analysis, SLE participants with fatigue were more likely to be women (p=0.01), perceived their disease as more active (p<0.0001), had higher levels of pain (p<0.0001), anxiety (p<0.0001), depression (p<0.0001), insomnia (p<0.0001), stress (p<0.0001) and were more likely to screen for fibromyalgia (p<0.0001), compared with patients without significant fatigue. In multivariable analysis, parameters independently associated with fatigue were insomnia (p=0.0003), pain (p=0.002), fibromyalgia (p=0.008), self-reported active SLE (p=0.02) and stress (p=0.045). 93.2% of the participants found LEAF helpful and 92.3% would recommend it to another patient with SLE. CONCLUSION: Fatigue is commonly severe in SLE, and associated with insomnia, pain, fibromyalgia and active disease according to patients' perspective. Our study shows the usefulness of an automated digital tool to manage fatigue in SLE.

Hybrid approach combining deep learning and a rule based expert system for concept extraction from prescriptions.

Concept extraction from prescriptions is a very important task that provides a foundation for many of the downstream healthcare applications in decision making across the areas of pharmacovigilance, medication adherence, inventory management, and other matters of value-based care. Although short, these directions can sometimes be complex. With the increase in complexity of direction, it becomes harder to extract various concepts by only rule based expert system. It identifies major concepts like frequency, dosage, duration, etc. from the natural text direction using a combination of rules and deep learning (DL) based methods on a large real world data of a pharmacy chain. The DL module includes a fine-tuned BERT transformer and Gram CNN (Convolutional Neural Network) based NER (Named Entity Recognition) architecture. The proposed method utilizes the domain heuristics along with intelligent labelling and bootstrapping to help DL models extract concepts with high evaluation scores and thus provides a way for carrying out concept extraction using targeted methods instead of one single method. To the best of our knowledge, this is the best performance reported in the literature for concept extraction from doctor's prescription.

Development of a read-across-derived classification model for the predictions of mutagenicity data and its comparison with traditional QSAR models and expert systems.

Mutagenicity is considered an important endpoint from the regulatory, environmental and medical points of view. Due to the wide number of compounds that may be of concern and the enormous expenses (in terms of time, money, and animals) associated with rodent mutagenicity bioassays, this endpoint is a major target for the development of alternative approaches for screening and prediction. The majority of old-aged expert systems and quantitative structure-activity relationship (QSAR) models may show reduced performance over time for their application on newer chemical candidates; thus, researchers constantly try to improve the modeling strategies. In our report, we initially performed traditional classification-based linear discriminant analysis (LDA) QSAR modeling using the benchmark Ames dataset of diverse chemicals (6512 compounds) to recognize the relationship between the molecules and their potential mutagenic behavior. The classical LDA QSAR model is developed from a selected set of 2D descriptors. The LDA QSAR model was developed by using a total of 31 descriptors identified from the analysis of the most discriminating features. Additionally, we have used similarity-derived features obtained from the read-across (RA) to develop an RA-based QSAR model. The developed RA-based LDA QSAR model has better predictivity, transferability, and interpretability compared to the LDA QSAR model, and it uses a very small number of descriptors compared to the classical QSAR model. Different machine learning (ML) models were also developed using the descriptors appearing in the read-across-based LDA QSAR model for comparative studies. We have checked the prediction quality of 216 true external set compounds using the novel similarity-derived RA model. The performance of the OECD toolbox is also compared with the RA-derived LDA QSAR model for a true external set. The current study aimed to explore the significance of the read-across-based algorithm and its application to the most current experimental mutagenicity data to complement already available expert systems.

Paediatric orthopaedic expert system.

The paediatric orthopaedic expert system analyses and predicts the healing time of limb fractures in children using machine learning. As far we know, no published research on the paediatric orthopaedic expert system that predicts paediatric fracture healing time using machine learning has been published. The University Malaya Medical Centre (UMMC) offers paediatric orthopaedic data, comprises children under the age of 12 radiographs limb fractures with ages recorded from the date and time of initial trauma. SVR algorithms are used to predict and discover variables associated with fracture healing time. This study developed an expert system capable of predicting healing time, which can assist general practitioners and healthcare practitioners during treatment and follow-up. The system is available online at https://kidsfractureexpert.com/.

Proposal of neural network model for neurocognitive rehabilitation and its comparison with fuzzy expert system model.

This article focuses on the development of algorithms for a smart neurorehabilitation system, whose core is made up of artificial neural networks. The authors of the article have proposed a completely unique transfer of ACE-R results to the CHC model. This unique approach allows for the saturation of the CHC model domains according to modified ACE-R factor analysis. The outputs of the proposed algorithm thus enable the automatic creation of a personalized and optimized neurorehabilitation plan for individual patients to train their cognitive functions. A set of tasks in 6 levels of difficulty (level 1 to level 6) was designed for each of the nine CHC model domains. For each patient, the results of the ACE-R screening helped deter-mine the specific CHC domains to be rehabilitated, as well as the initial gaming level for rehabilitation in each domain. The proposed artificial neural network algorithm was adapted to real data from 703 patients. Experimental outputs were compared to the outputs of the initially designed fuzzy expert system, which was trained on the same real data, and all outputs from both systems were statistically evaluated against expert conclusions that were available. It is evident from the conducted experimental study that the smart neurorehabilitation system using artificial neural networks achieved significantly better results than the neurorehabilitation system whose core is a fuzzy expert system. Both algorithms are implemented into a comprehensive neurorehabilitation portal (Eddie), which was supported by a research project from the Technology Agency of the Czech Republic.

Common knowledge processing patterns in networks of different systems.

Knowledge processing has patterns which can be found in biological neuron activity and artificial neural networks. The work explores whether an underlying structure exists for knowledge which crosses domains. The results show common data processing patterns in biological systems and human-made knowledge-based systems, present examples of human-generated knowledge processing systems, such as artificial neural networks and research topic knowledge networks, and explore change of system patterns over time. The work analyzes nature-based systems, which are animal connectomes, and observes neuron circuitry of knowledge processing based on complexity of the knowledge processing system. The variety of domains and similarity in processing mechanisms raise the question: if it is common in natural and artificial systems to see this pattern-based knowledge processing, how unique is knowledge processing in humans.

Therapy-based expert system on function and postural stability after anterior cruciate ligament reconstruction: a pilot study.

PURPOSE: Wii Fit exergames have been less commonly used for the rehabilitation of athletes after Anterior Cruciate Ligament Reconstruction (ACLR). This study aims to investigate the effects of an expert system using Wii Fit exergames compared to conventional rehabilitation following ACLR. A forward-chaining rule-based expert system was developed which proposed a rehabilitation program that included the number and type of exercise in terms of difficulty and ease and the duration of each exercise in a progressive manner according to the patient's physical condition. MATERIALS AND METHODS: Twenty eligible athletes aged 20-30 who underwent ACLR were enrolled in this study and randomly assigned to two groups; and received 12 sessions of either Wii Fit exergames as Wii group (n = 10) or conventional rehabilitation as CL group (n = 10). RESULTS: The main outcomes consisted of pain (Visual Analogue Scale (VAS)), knee effusion, knee flexion range (KFR), thigh girth (TG), single-leg hop for distance (SLHD), and for time (SLHT), static and dynamic balance tests. Both groups had considerable improvement in all outcomes, also there were significantly differences between Wii and CL groups as follows; VAS (P < 0.001), knee effusion (P < 0.001), TG (P = 0.001), KFR (P = 0.012), static balance in stable position (P < 0.001) and in unstable position (P = 0.001), dynamic balance in the anterior (P < 0.001), posteromedial (P < 0.001), posterolateral (P = 0.004) directions, symmetry index of SLHD (P < 0.001) and symmetry index of SLHT (P = 0.013). CONCLUSIONS: The findings showed that using Wii Fit exergames in post-ACLR patients reduced pain and effusion while also improving function and balance significantly. Iranian Registry of Clinical Trials registration number is IRCT20191013045090N1, and the registration date is 03-03-2020.

The Application of Knowledge-Based Clinical Decision Support Systems to Enhance Adherence to Evidence-Based Medicine in Chronic Disease.

Among the technology-based solutions, clinical decision support systems (CDSSs) have the ability to keep up with clinicians with the latest evidence in a smart way. Hence, the main objective of our study was to investigate the applicability and characteristics of CDSSs regarding chronic disease. The Web of Science, Scopus, OVID, and PubMed databases were searched using keywords from January 2000 to February 2023. The review was completed according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses checklist. Then, an analysis was done to determine the characteristics and applicability of CDSSs. The quality of the appraisal was assessed using the Mixed Methods Appraisal Tool checklist (MMAT). A systematic database search yielded 206 citations. Eventually, 38 articles from sixteen countries met the inclusion criteria and were accepted for final analysis. The main approaches of all studies can be classified into adherence to evidence-based medicine (84.2%), early and accurate diagnosis (81.6%), identifying high-risk patients (50%), preventing medical errors (47.4%), providing up-to-date information to healthcare providers (36.8%), providing patient care remotely (21.1%), and standardizing care (71.1%). The most common features among the knowledge-based CDSSs included providing guidance and advice for physicians (92.11%), generating patient-specific recommendations (84.21%), integrating into electronic medical records (60.53%), and using alerts or reminders (60.53%). Among thirteen different methods to translate the knowledge of evidence into machine-interpretable knowledge, 34.21% of studies utilized the rule-based logic technique while 26.32% of studies used rule-based decision tree modeling. For CDSS development and translating knowledge, diverse methods and techniques were applied. Therefore, the development of a standard framework for the development of knowledge-based decision support systems should be considered by informaticians.

Prototype Expert System for Gout Diagnosis on an Outpatient Basis.

Gout is a systemic disease that is caused by the deposition of monosodium urate crystals in various tissues which leads to inflammation in them. This disease is often misdiagnosed. It leads to the lack of adequate medical care and development of serious complications, such as urate nephropathy and disability. The current situation can be improved by optimizing the medical care provided to patients, which requires searching for new strategies in terms of diagnosis. One of these strategies is the development of an expert system for providing information assistance to medical specialists which was a purpose of this study. The developed prototype expert system for gout diagnosis has knowledge base including 1144 medical concepts and 5 640 522 links, intelligent knowledge base editor and software which helps practitioner make the final decision. It has sensitivity of 91,3% [95% CI, 89,1%-93,1%], specificity of 85,4% [95% CI, 82,9%-87,6%] and AUROC 0,954 [95% CI, 0,944-0,963].

Initial study on an expert system for spine diseases screening using inertial measurement unit.

In recent times, widely understood spine diseases have advanced to one of the most urgetn problems where quick diagnosis and treatment are needed. To diagnose its specifics (e.g. to decide whether this is a scoliosis or sagittal imbalance) and assess its extend, various kind of imaging diagnostic methods (such as X-Ray, CT, MRI scan or ST) are used. However, despite their common use, some may be regarded as (to a level) invasive methods and there are cases where there are contraindications to using them. Besides, which is even more of a problem, these are very expensive methods and whilst their use for pure diagnostic purposes is absolutely valid, then due to their cost, they cannot rather be considered as tools which would be equally valid for bad posture screening programs purposes. This paper provides an initial evaluation of the alternative approach to the spine diseases diagnostic/screening using inertial measurement unit and we propose policy-based computing as the core for the inference systems. Although the methodology presented herein is potentially applicable to a variety of spine diseases, in the nearest future we will focus specifically on sagittal imbalance detection.

Secur-e-Health Project: Towards Federated Learning for Smart Pediatric Care.

The application of machine learning (ML) algorithms to electronic health records (EHR) data allows the achievement of data-driven insights on various clinical problems and the development of clinical decision support (CDS) systems to improve patient care. However, data governance and privacy barriers hinder the use of data from multiple sources, especially in the medical field due to the sensitivity of data. Federated learning (FL) is an attractive data privacy-preserving solution in this context by enabling the training of ML models with data from multiple sources without any data sharing, using distributed remotely hosted datasets. The Secur-e-Health project aims at developing a solution in terms of CDS tools encompassing FL predictive models and recommendation systems. This tool may be especially useful in Pediatrics due to the increasing demands on Pediatric services, and the current scarcity of ML applications in this field compared to adult care. Herein we provide a description of the technical solution proposed in this project for three specific pediatric clinical problems: childhood obesity management, pilonidal cyst post-surgical care and retinography imaging analysis.