BackgroundAlzheimer’s Disease (AD) is a progressive memory disorder that causes irreversible cognitive decline. Given that there is currently no cure, it is critical to detect AD in its early stage during the disease progression. Recently, many statistical learning methods have been presented to identify cognitive decline with temporal data, but few of these methods integrate heterogeneous phenotype and genetic information together to improve the accuracy of prediction. In addition, many of these models are often unable to handle incomplete temporal data; this often manifests itself in the removal of records to ensure consistency in the number of records across participants.ResultsTo address these issues, in this work we propose a novel approach to integrate the genetic data and the longitudinal phenotype data to learn a fixed-length “enriched” biomarker representation derived from the temporal heterogeneous neuroimaging records. Armed with this enriched representation, as a fixed-length vector per participant, conventional machine learning models can be used to predict clinical outcomes associated with AD.ConclusionThe proposed method shows improved prediction performance when applied to data derived from Alzheimer’s Disease Neruoimaging Initiative cohort. In addition, our approach can be easily interpreted to allow for the identification and validation of biomarkers associated with cognitive decline.

BackgroundPost-ERCP pancreatitis is one of the most common adverse events in ERCP-related procedures. The purpose of this study is to construct an online model to predict the risk of post-ERCP pancreatitis in non-elderly patients with common bile duct stones through screening of relevant clinical parameters.MethodsA total of 919 cases were selected from 7154 cases from a major Chinese tertiary hospital. Multivariable logistic regression model was fitted using the variables selected by the LASSO regression from 28 potential predictor variables. The internal and external validation was assessed by evaluating the receiver operating characteristic curve and the area under curve. Restricted cubic spline modelling was used to explore non-linear associations. The interactive Web application developed for risk prediction was built using the R “shiny” package.ResultsThe incidence of post-ERCP pancreatitis was 5.22% (48/919) and significantly higher in non-elderly patients with female, high blood pressure, the history of pancreatitis, difficult intubation, endoscopic sphincterotomy, lower alkaline phosphatase and smaller diameter of common bile duct. The predictive performance in the test and external validation set was 0.915 (95% CI, 0.858–0.972) and 0.838 (95% CI, 0.689–0.986), respectively. The multivariate restricted cubic spline results showed that the incidence of pancreatitis was increased at 33–50 years old, neutrophil percentage > 58.90%, hemoglobin > 131 g/L, platelet < 203.04 or > 241.40 × 109/L, total bilirubin > 18.39 umol / L, aspartate amino transferase < 36.56 IU / L, alkaline phosphatase < 124.92 IU / L, Albumin < 42.21 g / L and common bile duct diameter between 7.25 and 10.02 mm. In addition, a web server was developed that supports query for immediate PEP risk.ConclusionThe visualized networked version of the above model is able to most accurately predict the risk of PEP in non-elderly patients with choledocholithiasis and allows clinicians to assess the risk of PEP in real time and provide preventive treatment measures as early as possible.

BackgroundImproving shared decision-making using a treat-to-target approach, including the use of clinical outcome measures, is important to providing high quality care for rheumatoid arthritis (RA). We developed an Electronic Health Record (EHR) integrated, patient-facing sidecar dashboard application that displays RA outcomes, medications, and lab results for use during clinical visits (“RA PRO dashboard”). The purpose of this study was to assess clinician perceptions and experiences using the dashboard in a university rheumatology clinic.MethodsWe conducted focus group (FG) discussions with clinicians who had access to the dashboard as part of a randomized, stepped-wedge pragmatic trial. FGs explored clinician perceptions towards the usability, acceptability, and usefulness of the dashboard. FG data were analyzed thematically using deductive and inductive techniques; generated themes were categorized into the domains of the Technology Acceptance Model (TAM).Results3 FG discussions were conducted with a total of 13 clinicians. Overall, clinicians were enthusiastic about the dashboard and expressed the usefulness of visualizing RA outcome trajectories in a graphical format for motivating patients, enhancing patient understanding of their RA outcomes, and improving communication about medications. Major themes that emerged from the FG analysis as barriers to using the dashboard included inconsistent collection of RA outcomes leading to sparse data in the dashboard and concerns about explaining RA outcomes, especially to patients with fibromyalgia. Other challenges included time constraints and technical difficulties refreshing the dashboard to display real-time data. Methods for integrating the dashboard into the visit varied: some clinicians used the dashboard at the beginning of the visit as they documented RA outcomes; others used it at the end to justify changes to therapy; and a few shared it only with stable patients.ConclusionsThe study provides valuable insights into clinicians’ perceptions and experiences with the RA PRO dashboard. The dashboard showed promise in enhancing patient-clinician communication, shared decision-making, and overall acceptance among clinicians. Addressing challenges related to data collection, education, and tailoring dashboard use to specific patient populations will be crucial for maximizing its potential impact on RA care. Further research and ongoing improvements in dashboard design and implementation are warranted to ensure its successful integration into routine clinical practice.

Lung cancer remains a leading cause of cancer-related mortality globally, with prognosis significantly dependent on early-stage detection. Traditional diagnostic methods, though effective, often face challenges regarding accuracy, early detection, and scalability, being invasive, time-consuming, and prone to ambiguous interpretations. This study proposes an advanced machine learning model designed to enhance lung cancer stage classification using CT scan images, aiming to overcome these limitations by offering a faster, non-invasive, and reliable diagnostic tool. Utilizing the IQ-OTHNCCD lung cancer dataset, comprising CT scans from various stages of lung cancer and healthy individuals, we performed extensive preprocessing including resizing, normalization, and Gaussian blurring. A Convolutional Neural Network (CNN) was then trained on this preprocessed data, and class imbalance was addressed using Synthetic Minority Over-sampling Technique (SMOTE). The model's performance was evaluated through metrics such as accuracy, precision, recall, F1-score, and ROC curve analysis. The results demonstrated a classification accuracy of 99.64%, with precision, recall, and F1-score values exceeding 98% across all categories. SMOTE significantly enhanced the model's ability to classify underrepresented classes, contributing to the robustness of the diagnostic tool. These findings underscore the potential of machine learning in transforming lung cancer diagnostics, providing high accuracy in stage classification, which could facilitate early detection and tailored treatment strategies, ultimately improving patient outcomes.

ObjectiveSuicide is a complex and multifactorial public health problem. Understanding and addressing the various factors associated with suicide is crucial for prevention and intervention efforts. Machine learning (ML) could enhance the prediction of suicide attempts.MethodA systematic review was performed using PubMed, Scopus, Web of Science and SID databases. We aim to evaluate the performance of ML algorithms and summarize their effects, gather relevant and reliable information to synthesize existing evidence, identify knowledge gaps, and provide a comprehensive list of the suicide risk factors using mixed method approach.ResultsForty-one studies published between 2011 and 2022, which matched inclusion criteria, were chosen as suitable. We included studies aimed at predicting the suicide risk by machine learning algorithms except natural language processing (NLP) and image processing.The neural network (NN) algorithm exhibited the lowest accuracy at 0.70, whereas the random forest demonstrated the highest accuracy, reaching 0.94. The study assessed the COX and random forest models and observed a minimum area under the curve (AUC) value of 0.54. In contrast, the XGBoost classifier yielded the highest AUC value, reaching 0.97. These specific AUC values emphasize the algorithm-specific performance in capturing the trade-off between sensitivity and specificity for suicide risk prediction.Furthermore, our investigation identified several common suicide risk factors, including age, gender, substance abuse, depression, anxiety, alcohol consumption, marital status, income, education, and occupation. This comprehensive analysis contributes valuable insights into the multifaceted nature of suicide risk, providing a foundation for targeted preventive strategies and intervention efforts.ConclusionsThe effectiveness of ML algorithms and their application in predicting suicide risk has been controversial. There is a need for more studies on these algorithms in clinical settings, and the related ethical concerns require further clarification.

BackgroundFew studies have been conducted on the usage of telehealth focusing on consultations between patients’ families and physicians. This study aimed to identify the usage and limitations of online medical consultations with patients’ families compared to the traditional in-person consultations.MethodsWe conducted a prospective cohort study from April 1, 2020, to September 30, 2021, at an educational acute-care hospital in Japan. The study included hospitalized patients aged 20 years or older and their family members for whom an online or in-person medical consultation between the family member and physician was conducted during the hospitalization period. The primary endpoints assessed were three topics pertaining to medical consultation: medical conditions and treatment plans, policies for life-threatening events, and post-discharge support. The secondary endpoint was the number of consultations required.ResultsOnline consultations and traditional in-person consultations were provided to 58 and 53 patients’ families, respectively. Of the patients in the online consultation group who underwent multiple consultations, 46 (79%) also underwent in-person consultations. Regarding the topics, all the patients’ families in both consultation groups had consultations on medical conditions and treatment plans; regarding the policy for life-threatening events, 47% of patient families in the online consultation group were consulted compared to 53% of those in the in-person group. Regarding post-discharge support, 59% of patient families in the online group were consulted compared to 40% in the in-person group. In the online consultation group of 58 patients’ families, 188 consultations were conducted, including 95 online and 93 in-person consultations. Consultations on policy for life-threatening events were significantly more frequent in in-person consultations than in online consultations (p < 0.05). Regarding post-discharge support, online consultations were significantly more frequent than in-person consultations (p < 0.05). The number of family members who attended online consultations was significantly higher than those who attended in-person consultations (p < 0.05).ConclusionsOnline consultation between the physician and patient’s family may be an alternative to in-person consultation for explaining medical conditions and treatment plans. However, in-person consultation still plays an important role in sensitive topics, such as policy consultation for life-threatening events.

BackgroundModeling causality through graphs, referred to as causal graph learning, offers an appropriate description of the dynamics of causality. The majority of current machine learning models in clinical decision support systems only predict associations between variables, whereas causal graph learning models causality dynamics through graphs. However, building personalized causal graphs for each individual is challenging due to the limited amount of data available for each patient.MethodIn this study, we present a new algorithmic framework using meta-learning for learning personalized causal graphs in biomedicine. Our framework extracts common patterns from multiple patient graphs and applies this information to develop individualized graphs. In multi-task causal graph learning, the proposed optimized initial guess of shared commonality enables the rapid adoption of knowledge to new tasks for efficient causal graph learning.ResultsExperiments on one real-world biomedical causal graph learning benchmark data and four synthetic benchmarks show that our algorithm outperformed the baseline methods. Our algorithm can better understand the underlying patterns in the data, leading to more accurate predictions of the causal graph. Specifically, we reduce the structural hamming distance by 50-75%, indicating an improvement in graph prediction accuracy. Additionally, the false discovery rate is decreased by 20-30%, demonstrating that our algorithm made fewer incorrect predictions compared to the baseline algorithms.ConclusionTo the best of our knowledge, this is the first study to demonstrate the effectiveness of meta-learning in personalized causal graph learning and cause inference modeling for biomedicine. In addition, the proposed algorithm can also be generalized to transnational research areas where integrated analysis is necessary for various distributions of datasets, including different clinical institutions.

The selection of data elements is a decisive task within the development of a health registry. Having the right metadata is crucial for answering the particular research questions. Furthermore, the set of data elements determines the registries' readiness of interoperability and data reusability to a major extent. Six health registries shared and published their metadata within a German funding initiative. As one step in the direction of a common set of data elements, a selection of those metadata was evaluated with regard to their appropriateness for a broader usage. Each registry was asked to contribute a 10%-selection of their data elements to an evaluation sample. The survey was set up with the online survey tool "LimeSurvey Cloud". The registries and an accompanying project participated in the survey with one vote for each project. The data elements were offered in content groups along with the question of whether the data element is appropriate for health registries on a broader scale. The question could be answered using a Likert scale with five options. Furthermore, "no answer" was allowed. The level of agreement was assessed using weighted Cohen's kappa and Kendall's coefficient of concordance. The evaluation sample consisted of 269 data elements. With a grade of "perhaps recommendable" or higher in the mean, 169 data elements were selected. These data elements belong preferably to groups' demography, education/occupation, medication, and nutrition. Half of the registries lost significance compared with their percentage of data elements in the evaluation sample, one remained stable. The level of concordance was adequate. The survey revealed a set of 169 data elements recommended for health registries. When developing a registry, this set could be valuable help in selecting the metadata appropriate to answer the registry's research questions. However, due to the high specificity of research questions, data elements beyond this set will be needed to cover the whole range of interests of a register. A broader discussion and subsequent surveys are needed to establish a common set of data elements on an international scale.

BackgroundThere are approximately 8,000 different rare diseases that affect roughly 400 million people worldwide. Many of them suffer from delayed diagnosis. Ciliopathies are rare monogenic disorders characterized by a significant phenotypic and genetic heterogeneity that raises an important challenge for clinical diagnosis. Diagnosis support systems (DSS) applied to electronic health record (EHR) data may help identify undiagnosed patients, which is of paramount importance to improve patients’ care. Our objective was to evaluate three online-accessible rare disease DSSs using phenotypes derived from EHRs for the diagnosis of ciliopathies.MethodsTwo datasets of ciliopathy cases, either proven or suspected, and two datasets of controls were used to evaluate the DSSs. Patient phenotypes were automatically extracted from their EHRs and converted to Human Phenotype Ontology terms. We tested the ability of the DSSs to diagnose cases in contrast to controls based on Orphanet ontology.ResultsA total of 79 cases and 38 controls were selected. Performances of the DSSs on ciliopathy real world data (best DSS with area under the ROC curve = 0.72) were not as good as published performances on the test set used in the DSS development phase. None of these systems obtained results which could be described as “expert-level”. Patients with multisystemic symptoms were generally easier to diagnose than patients with isolated symptoms. Diseases easily confused with ciliopathy generally affected multiple organs and had overlapping phenotypes. Four challenges need to be considered to improve the performances: to make the DSSs interoperable with EHR systems, to validate the performances in real-life settings, to deal with data quality, and to leverage methods and resources for rare and complex diseases.ConclusionOur study provides insights into the complexities of diagnosing highly heterogenous rare diseases and offers lessons derived from evaluation existing DSSs in real-world settings. These insights are not only beneficial for ciliopathy diagnosis but also hold relevance for the enhancement of DSS for various complex rare disorders, by guiding the development of more clinically relevant rare disease DSSs, that could support early diagnosis and finally make more patients eligible for treatment.

BackgroundStroke frequently gives rise to incapacitating motor impairments in the upper limb. Virtual reality (VR) rehabilitation has exhibited potential for augmenting upper extremity recovery; nonetheless, the optimal techniques for such interventions remain a topic of uncertainty. The present systematic review and meta-analysis were undertaken to comprehensively compare VR-based rehabilitation with conventional occupational therapy across a spectrum of immersion levels and outcome domains.MethodsA systematic search was conducted in PubMed, IEEE, Scopus, Web of Science, and PsycNET databases to identify randomized controlled trials about upper limb rehabilitation in stroke patients utilizing VR interventions. The search encompassed studies published in the English language up to March 2023. The identified studies were stratified into different categories based on the degree of immersion employed: non-immersive, semi-immersive, and fully-immersive settings. Subsequent meta-analyses were executed to assess the impact of VR interventions on various outcome measures.ResultsOf the 11,834 studies screened, 55 studies with 2142 patients met the predefined inclusion criteria. VR conferred benefits over conventional therapy for upper limb motor function, functional independence, Quality of life, Spasticity, and dexterity. Fully immersive VR showed the greatest gains in gross motor function, while non-immersive approaches enhanced fine dexterity. Interventions exceeding six weeks elicited superior results, and initiating VR within six months post-stroke optimized outcomes.ConclusionsThis systematic review and meta-analysis demonstrates that adjunctive VR-based rehabilitation enhances upper limb motor recovery across multiple functional domains compared to conventional occupational therapy alone after stroke. Optimal paradigms likely integrate VR’s immersive capacity with conventional techniques.Trial registrationThis systematic review and meta-analysis retrospectively registered in the OSF registry under the identifier [https://doi.org/10.17605/OSF.IO/YK2RJ].