Big data in digital healthcare: lessons learnt and recommendations for general practice

Natural language processing in drug discovery: bridging the gap between text and therapeutics with artificial intelligence

INTRODUCTION

The field of Natural Language Processing (NLP) within the life sciences has exploded in its capacity to aid the extraction and analysis of data from scientific texts in recent years through the advancement of Artificial Intelligence (AI). Drug discovery pipelines have been innovated and accelerated by the uptake of AI/Machine Learning (ML) techniques.

AREAS COVERED

The authors provide background on Named Entity Recognition (NER) in text - from tagging terms in text using ontologies to entity identification via ML models. They also explore the use of Knowledge Graphs (KGs) in biological data ingestion, manipulation, and extraction, leading into the modern age of Large Language Models (LLMs) and their ability to maneuver complex and abundant data. The authors also cover the main strengths and weaknesses of the many methods available when undertaking NLP tasks in drug discovery. Literature was derived from searches utilizing Europe PMC, ResearchRabbit and SciSpace.

EXPERT OPINION

The mass of scientific data that is now produced each year is both a huge positive for potential innovation in drug discovery and a new hurdle for researchers to overcome. Notably, methods should be selected to fit a use case and the data available, as each method performs optimally under different conditions.

Factors influencing the use of big data within healthcare services: a systematic review

Background: The emergence of big data holds the promise of aiding healthcare providers by identifying patterns and converting vast quantities of data into actionable insights facilitating the provision of precision medicine and decision-making. Objective: This study aimed to investigate the factors influencing use of big data within healthcare services to facilitate their use. Method: A systematic review was conducted in February 2024, adhering to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Database searches for articles published between 01 January 2020 and 18 February 2024 and included PubMed, Scopus, ProQuest and Cochrane Library. The Authority, Accuracy, Coverage, Objectivity, Date, Significance ( AACODS) checklist was used to evaluate the quality of the included articles. Subsequently, a thematic analysis was conducted on the findings of the review, using the Boyatzis approach. Results: A final selection of 46 studies were included in this systematic review. A significant proportion of these studies demonstrated acceptable quality, and the level of bias was deemed satisfactory. Thematic analysis identified seven major themes that influenced the use of big data in healthcare services. These themes were grouped into four primary categories: performance expectancy, effort expectancy, social influence, and facilitating conditions. Factors associated with "effort expectancy" were the most highly cited in the included studies (67%), while those related to "social influence" received the fewest citations (15%). Conclusion: This study underscored the critical role of "effort expectancy" factors, particularly those under the theme of "data complexity and management," in the process of using big data in healthcare services. Implications: Results of this study provide groundwork for future research to explore facilitators and barriers to using big data in health care, particularly in relation to data complexity and the efficient and effective management of big data, with significant implications for healthcare administrators and policymakers.

Leveraging large language models to mimic domain expert labeling in unstructured text-based electronic healthcare records in non-english languages

BACKGROUND

The integration of big data and artificial intelligence (AI) in healthcare, particularly through the analysis of electronic health records (EHR), presents significant opportunities for improving diagnostic accuracy and patient outcomes. However, the challenge of processing and accurately labeling vast amounts of unstructured data remains a critical bottleneck, necessitating efficient and reliable solutions. This study investigates the ability of domain specific, fine-tuned large language models (LLMs) to classify unstructured EHR texts with typographical errors through named entity recognition tasks, aiming to improve the efficiency and reliability of supervised learning AI models in healthcare.

METHODS

Turkish clinical notes from pediatric emergency room admissions at Hacettepe University İhsan Doğramacı Children's Hospital from 2018 to 2023 were analyzed. The data were preprocessed with open source Python libraries and categorized using a pretrained GPT-3 model, "text-davinci-003," before and after fine-tuning with domain-specific data on respiratory tract infections (RTI). The model's predictions were compared against ground truth labels established by pediatric specialists.

RESULTS

Out of 24,229 patient records classified as poorly labeled, 18,879 were identified without typographical errors and confirmed for RTI through filtering methods. The fine-tuned model achieved a 99.88% accuracy, significantly outperforming the pretrained model's 78.54% accuracy in identifying RTI cases among the remaining records. The fine-tuned model demonstrated superior performance metrics across all evaluated aspects compared to the pretrained model.

CONCLUSIONS

Fine-tuned LLMs can categorize unstructured EHR data with high accuracy, closely approximating the performance of domain experts. This approach significantly reduces the time and costs associated with manual data labeling, demonstrating the potential to streamline the processing of large-scale healthcare data for AI applications.

Dysphagia Rehabilitation Using Digital Technology: A Scoping Review

AIM

Digital health technology in swallowing rehabilitation offers personalized exercises, remote monitoring, and real-time feedback, enhancing accessibility and effectiveness of therapy. This scoping review was conducted to summarize what types and features of digital technology-based dysphagia rehabilitation interventions exist, how they are applied in patients with dysphagia, and what the effectiveness and facilitators and barriers to intervention application are.

METHODS

We searched Medline Complete, Embase, CINAHL, Scopus, and gray literature for articles published between January 2000 and June 2023. We used subheadings and terms related to digital health, dysphagia, and rehabilitation to search for articles. The included studies were mapped according to the types and features, effectiveness, enablers, barriers, and future improvements of swallowing rehabilitation using digital technologies.

RESULTS

Twenty-five studies met the inclusion criteria. Three types of digital swallowing rehabilitation interventions were identified: home-based rehabilitation using the mHealth app, synchronous telepractice and monitoring, as well as game-based biofeedback and tracking. The included studies reported positive results regarding physiological changes in swallowing function, swallowing performance, and quality of life. Digital unfamiliarity, resources for digital access, and technical issues related to the failure of the mobile device operating system were identified as barriers to the use of digital swallowing rehabilitation technology and future improvements.

CONCLUSIONS

Digital technology has potential value in dysphagia rehabilitation. In the future, developing various interventions utilizing the advantages of digital technology and conducting additional research to validate their effectiveness is necessary. Additionally, improved digital familiarity, better accessibility, better technology, and management practices will be needed.

Mini-review of clinical data service platforms in the era of artificial intelligence: A case study of the iHi data platform

In the past two decades, healthcare organizations have transitioned from the early stages of digitization and digitalization to a more comprehensive process of digital transformation, a shift significantly accelerated by the advent of artificial intelligence (AI). Consequently, the development of high-quality clinical data warehouses, derived from electronic health records (EHRs) and enriched with multidomain data, such as genomics, proteomics, and Internet of Things (IoT) information, has become essential for the creation of the modern patient digital twin (PDT). This approach is critical for leveraging AI in the evolving landscape of clinical practice. Leading medical centers and healthcare institutions have adopted this model, as summarized in this review. Since 2020, China Medical University Hospital (CMUH) has been constructing its data ecosystem by integrating EHRs with extensive genomic databases. This initiative has led to the development of a data service platform, the ignite Hyper-intelligence (iHi®) platform. The iHi platform serves as a case study exemplifying the workflow of the smart data chip, which facilitates the deep cleaning and reliable de-identification of clinical data while incorporating analytical platforms related to genomics and the microbiome to enhance insight extraction processes. The ability to predict complex interactions and disease trajectories among PDTs, digital counterparts of healthcare professionals, and virtual socioeconomic environments will be pivotal in advancing personalized healthcare and optimizing patient outcomes. Future challenges will involve the unification of cross-institutional data platforms and ensuring the interoperability of AI inferences-key factors that will define the next era of AI-driven healthcare.

Empowering cancer research in Europe: the EUCAIM cancer imaging infrastructure

Artificial intelligence (AI) is a powerful technology with the potential to disrupt cancer detection, diagnosis and treatment. However, the development of new AI algorithms requires access to large and complex real-world datasets. Although such datasets are constantly being generated, access to them is limited by data fragmentation across numerous repositories and sites, heterogeneity, lack of annotations, and potential privacy issues. The European Cancer Imaging Initiative is a flagship of Europe's Beating Cancer Plan, aiming to unlock the power of AI for cancer patients, clinicians, and researchers by establishing a federated European infrastructure for cancer images through the EU-funded EUropean Federation for CAncer IMages (EUCAIM) project. This infrastructure, called Cancer Image Europe, builds on the AI for Health Imaging network (AI4HI), established European Research Infrastructures (Euro-BioImaging, BBMRI-ERIC, EATRIS, ECRIN, and ELIXIR), and numerous related partners providing access to research tools, images, and related clinical, pathology and molecular data. The infrastructure targets clinicians, researchers, and innovators by providing the means to develop and validate data-intensive AI-based and other IT-enabled clinical decision-making systems supporting precision medicine. Common data models, including a linking hyperontology, quality standards, compliance with the FAIR (Findability, Accessibility, Interoperability and Reusability) principles, data annotation, curation and anonymization services are provided to ensure data quality and interoperability, consistency and privacy. In summer 2024, the EUCAIM project released the first prototype of an EU-wide infrastructure, with a comprehensive dashboard integrating applications for dataset discovery, federated search, data access request, metadata harvesting, annotation, secure processing environments and federated processing. CRITICAL RELEVANCE STATEMENT: EUCAIM's federated infrastructure for cancer image data advances medical research and related AI development in Europe. It addresses the current fragmentation and heterogeneity of data repositories is legally compliant, and facilitates collaboration among clinicians, researchers, and innovators. KEY POINTS: AI solutions to advance cancer care rely on large, high-quality real-world datasets. EUCAIM's federated infrastructure for cancer image data empowers cancer research in Europe. It provides access to research tools, images, and related clinical, pathology and molecular data.

Machine learning techniques for predicting neurodevelopmental impairments in premature infants: a systematic review

Background and objective

Very preterm infants are highly susceptible to Neurodevelopmental Impairments (NDIs), including cognitive, motor, and language deficits. This paper presents a systematic review of the application of Machine Learning (ML) techniques to predict NDIs in premature infants.

Methods

This review presents a comparative analysis of existing studies from January 2018 to December 2023, highlighting their strengths, limitations, and future research directions.

Results

We identified 26 studies that fulfilled the inclusion criteria. In addition, we explore the potential of ML algorithms and discuss commonly used data sources, including clinical and neuroimaging data. Furthermore, the inclusion of omics data as a contemporary approach employed, in other diagnostic contexts is proposed.

Conclusions

We identified limitations and emphasized the significance of employing multimodal data models and explored various alternatives to address the limitations identified in the reviewed studies. The insights derived from this review guide researchers and clinicians toward improving early identification and intervention strategies for NDIs in this vulnerable population.

Researching public health datasets in the era of deep learning: a systematic literature review

Objective: Explore deep learning applications in predictive analytics for public health data, identify challenges and trends, and then understand the current landscape. Materials and Methods: A systematic literature review was conducted in June 2023 to search articles on public health data in the context of deep learning, published from the inception of medical and computer science databases through June 2023. The review focused on diverse datasets, abstracting applications, challenges, and advancements in deep learning. Results: 2004 articles were reviewed, identifying 14 disease categories. Observed trends include explainable-AI, patient embedding learning, and integrating different data sources and employing deep learning models in health informatics. Noted challenges were technical reproducibility and handling sensitive data. Discussion: There has been a notable surge in deep learning applications on public health data publications since 2015. Consistent deep learning applications and models continue to be applied across public health data. Despite the wide applications, a standard approach still does not exist for addressing the outstanding challenges and issues in this field. Conclusion: Guidelines are needed for applying deep learning and models in public health data to improve FAIRness, efficiency, transparency, comparability, and interoperability of research. Interdisciplinary collaboration among data scientists, public health experts, and policymakers is needed to harness the full potential of deep learning.

Artificial intelligence and big data from digital health applications: publication trends and analysis

PURPOSE

The integration of big data with artificial intelligence in the field of digital health has brought a new dimension to healthcare service delivery. AI technologies that provide value by using big data obtained in the provision of health services are being added to each passing day. There are also some problems related to the use of AI technologies in health service delivery. In this respect, it is aimed to understand the use of digital health, AI and big data technologies in healthcare services and to analyze the developments and trends in the sector.

DESIGN/METHODOLOGY/APPROACH

In this research, 191 studies published between 2016 and 2023 on digital health, AI and its sub-branches and big data were analyzed using VOSviewer and Rstudio Bibliometrix programs for bibliometric analysis. We summarized the type, year, countries, journals and categories of publications; matched the most cited publications and authors; explored scientific collaborative relationships between authors and determined the evolution of research over the years through keyword analysis and factor analysis of publications. The content of the publications is briefly summarized.

FINDINGS

The data obtained showed that significant progress has been made in studies on the use of AI technologies and big data in the field of health, but research in the field is still ongoing and has not yet reached saturation.

RESEARCH LIMITATIONS/IMPLICATIONS

Although the bibliometric analysis study conducted has comprehensively covered the literature, a single database has been utilized and limited to some keywords in order to reach the most appropriate publications on the subject.

PRACTICAL IMPLICATIONS

The analysis has addressed important issues regarding the use of developing digital technologies in health services and is thought to form a basis for future researchers.

ORIGINALITY/VALUE

In today's world, where significant developments are taking place in the field of health, it is necessary to closely follow the development of digital technologies in the health sector and analyze the current situation in order to guide both stakeholders and those who will work in this field.

PheW2P2V: a phenome-wide prediction framework with weighted patient representations using electronic health records

Objective

Electronic health records (EHRs) provide opportunities for the development of computable predictive tools. Conventional machine learning methods and deep learning methods have been widely used for this task, with the approach of usually designing one tool for one clinical outcome. Here we developed PheW2P2V, a Phenome-Wide prediction framework using Weighted Patient Vectors. PheW2P2V conducts tailored predictions for phenome-wide phenotypes using numeric representations of patients' past medical records weighted based on their similarities with individual phenotypes.

Materials and Methods

PheW2P2V defines clinical disease phenotypes using Phecode mapping based on International Classification of Disease codes, which reduces redundancy and case-control misclassification in real-life EHR datasets. Through upweighting medical records of patients that are more relevant to a phenotype of interest in calculating patient vectors, PheW2P2V achieves tailored incidence risk prediction of a phenotype. The calculation of weighted patient vectors is computationally efficient, and the weighting mechanism ensures tailored predictions across the phenome. We evaluated prediction performance of PheW2P2V and baseline methods with simulation studies and clinical applications using the MIMIC-III database.

Results

Across 942 phenome-wide predictions using the MIMIC-III database, PheW2P2V has median area under the receiver operating characteristic curve (AUC-ROC) 0.74 (baseline methods have values ≤0.72), median max F1-score 0.20 (baseline methods have values ≤0.19), and median area under the precision-recall curve (AUC-PR) 0.10 (baseline methods have values ≤0.10).

Discussion

PheW2P2V can predict phenotypes efficiently by using medical concept embeddings and upweighting relevant past medical histories. By leveraging both labeled and unlabeled data, PheW2P2V reduces overfitting and improves predictions for rare phenotypes, making it a useful screening tool for early diagnosis of high-risk conditions, though further research is needed to assess the transferability of embeddings across different databases.

Conclusions

PheW2P2V is fast, flexible, and has superior prediction performance for many clinical disease phenotypes across the phenome of the MIMIC-III database compared to that of several popular baseline methods.

Advancing governance for digital transformation in health: insights from Georgia's experience

Enhancing digital health governance is critical to healthcare systems in low-income and middle-income countries. However, implementing governance-enhancing reforms in these countries is often challenging due to the multiplicity of external players and insufficient operational guidance that is accessible. Using data from desktop research, in-depth interviews, focus group discussions and three stakeholder workshops, this paper aims to provide insights into Georgia's experience in advancing digital health governance reforms. It reveals how Georgia has progressed on this path by unpacking the general term 'governance' into operational domains, where stakeholders and involved institutions could easily relate their institutional and personal roles and responsibilities with the specific function needed for digital health. Based on this work, the country delineated institutional responsibilities and passed the necessary regulations to establish better governance arrangements for digital health. The Georgia experience provides practical insights into the challenges faced and solutions found for advancing digital health governance in a middle-income country setting. The paper highlights the usefulness of operational definitions for the digital health governance domains that helped (a) increase awareness among stakeholders about the identified domains and their meaning, (b) discuss possible governance and institutional arrangements relevant to a country context, and (c) design the digital health governance architecture that the government decreed. Finally, the paper offers a broad description of domains in which the governance arrangements could be considered and used for other settings where relevant. The paper points to the need for a comprehensive taxonomy for governance domains to better guide digital health governance enhancements in low-middle-income country settings.

Deconstructing demographic bias in speech-based machine learning models for digital health

Introduction

Machine learning (ML) algorithms have been heralded as promising solutions to the realization of assistive systems in digital healthcare, due to their ability to detect fine-grain patterns that are not easily perceived by humans. Yet, ML algorithms have also been critiqued for treating individuals differently based on their demography, thus propagating existing disparities. This paper explores gender and race bias in speech-based ML algorithms that detect behavioral and mental health outcomes.

Methods

This paper examines potential sources of bias in the data used to train the ML, encompassing acoustic features extracted from speech signals and associated labels, as well as in the ML decisions. The paper further examines approaches to reduce existing bias via using the features that are the least informative of one's demographic information as the ML input, and transforming the feature space in an adversarial manner to diminish the evidence of the demographic information while retaining information about the focal behavioral and mental health state.

Results

Results are presented in two domains, the first pertaining to gender and race bias when estimating levels of anxiety, and the second pertaining to gender bias in detecting depression. Findings indicate the presence of statistically significant differences in both acoustic features and labels among demographic groups, as well as differential ML performance among groups. The statistically significant differences present in the label space are partially preserved in the ML decisions. Although variations in ML performance across demographic groups were noted, results are mixed regarding the models' ability to accurately estimate healthcare outcomes for the sensitive groups.

Discussion

These findings underscore the necessity for careful and thoughtful design in developing ML models that are capable of maintaining crucial aspects of the data and perform effectively across all populations in digital healthcare applications.

Electronic Health Record-Oriented Knowledge Graph System for Collaborative Clinical Decision Support Using Multicenter Fragmented Medical Data: Design and Application Study

BACKGROUND

The medical knowledge graph provides explainable decision support, helping clinicians with prompt diagnosis and treatment suggestions. However, in real-world clinical practice, patients visit different hospitals seeking various medical services, resulting in fragmented patient data across hospitals. With data security issues, data fragmentation limits the application of knowledge graphs because single-hospital data cannot provide complete evidence for generating precise decision support and comprehensive explanations. It is important to study new methods for knowledge graph systems to integrate into multicenter, information-sensitive medical environments, using fragmented patient records for decision support while maintaining data privacy and security.

OBJECTIVE

This study aims to propose an electronic health record (EHR)-oriented knowledge graph system for collaborative reasoning with multicenter fragmented patient medical data, all the while preserving data privacy.

METHODS

The study introduced an EHR knowledge graph framework and a novel collaborative reasoning process for utilizing multicenter fragmented information. The system was deployed in each hospital and used a unified semantic structure and Observational Medical Outcomes Partnership (OMOP) vocabulary to standardize the local EHR data set. The system transforms local EHR data into semantic formats and performs semantic reasoning to generate intermediate reasoning findings. The generated intermediate findings used hypernym concepts to isolate original medical data. The intermediate findings and hash-encrypted patient identities were synchronized through a blockchain network. The multicenter intermediate findings were collaborated for final reasoning and clinical decision support without gathering original EHR data.

RESULTS

The system underwent evaluation through an application study involving the utilization of multicenter fragmented EHR data to alert non-nephrology clinicians about overlooked patients with chronic kidney disease (CKD). The study covered 1185 patients in nonnephrology departments from 3 hospitals. The patients visited at least two of the hospitals. Of these, 124 patients were identified as meeting CKD diagnosis criteria through collaborative reasoning using multicenter EHR data, whereas the data from individual hospitals alone could not facilitate the identification of CKD in these patients. The assessment by clinicians indicated that 78/91 (86%) patients were CKD positive.

CONCLUSIONS

The proposed system was able to effectively utilize multicenter fragmented EHR data for clinical application. The application study showed the clinical benefits of the system with prompt and comprehensive decision support.

Performance Drift in Machine Learning Models for Cardiac Surgery Risk Prediction: Retrospective Analysis

Background

The Society of Thoracic Surgeons and European System for Cardiac Operative Risk Evaluation (EuroSCORE) II risk scores are the most commonly used risk prediction models for in-hospital mortality after adult cardiac surgery. However, they are prone to miscalibration over time and poor generalization across data sets; thus, their use remains controversial. Despite increased interest, a gap in understanding the effect of data set drift on the performance of machine learning (ML) over time remains a barrier to its wider use in clinical practice. Data set drift occurs when an ML system underperforms because of a mismatch between the data it was developed from and the data on which it is deployed.

Objective

In this study, we analyzed the extent of performance drift using models built on a large UK cardiac surgery database. The objectives were to (1) rank and assess the extent of performance drift in cardiac surgery risk ML models over time and (2) investigate any potential influence of data set drift and variable importance drift on performance drift.

Methods

We conducted a retrospective analysis of prospectively, routinely gathered data on adult patients undergoing cardiac surgery in the United Kingdom between 2012 and 2019. We temporally split the data 70:30 into a training and validation set and a holdout set. Five novel ML mortality prediction models were developed and assessed, along with EuroSCORE II, for relationships between and within variable importance drift, performance drift, and actual data set drift. Performance was assessed using a consensus metric.

Results

A total of 227,087 adults underwent cardiac surgery during the study period, with a mortality rate of 2.76% (n=6258). There was strong evidence of a decrease in overall performance across all models (P<.0001). Extreme gradient boosting (clinical effectiveness metric [CEM] 0.728, 95% CI 0.728-0.729) and random forest (CEM 0.727, 95% CI 0.727-0.728) were the overall best-performing models, both temporally and nontemporally. EuroSCORE II performed the worst across all comparisons. Sharp changes in variable importance and data set drift from October to December 2017, from June to July 2018, and from December 2018 to February 2019 mirrored the effects of performance decrease across models.

Conclusions

All models show a decrease in at least 3 of the 5 individual metrics. CEM and variable importance drift detection demonstrate the limitation of logistic regression methods used for cardiac surgery risk prediction and the effects of data set drift. Future work will be required to determine the interplay between ML models and whether ensemble models could improve on their respective performance advantages.

A review of big data technology and its application in cancer care

The development of modern medical devices and information technology has led to a rapid growth in the amount of data available for health protection information, with the concept of medical big data emerging globally, along with significant advances in cancer care relying on data-driven approaches. However, outstanding issues such as fragmented data governance, low-quality data specification, and data lock-in still make sharing challenging. Big data technology provides solutions for managing massive heterogeneous data while combining artificial intelligence (AI) techniques such as machine learning (ML) and deep learning (DL) to better mine the intrinsic connections between data. This paper surveys and organizes recent articles on big data technology and its applications in cancer, dividing them into three different types to outline their primary content and summarize their critical role in assisting cancer care. It then examines the latest research directions in big data technology in cancer and evaluates the current state of development of each type of application. Finally, current challenges and opportunities are discussed, and recommendations are made for the further integration of big data technology into the medical industry in the future.

Taipei Medical University Clinical Research Database: a collaborative hospital EHR database aligned with international common data standards

OBJECTIVE

The objective of this paper is to provide a comprehensive overview of the development and features of the Taipei Medical University Clinical Research Database (TMUCRD), a repository of real-world data (RWD) derived from electronic health records (EHRs) and other sources.

METHODS

TMUCRD was developed by integrating EHRs from three affiliated hospitals, including Taipei Medical University Hospital, Wan-Fang Hospital and Shuang-Ho Hospital. The data cover over 15 years and include diverse patient care information. The database was converted to the Observational Medical Outcomes Partnership Common Data Model (OMOP CDM) for standardisation.

RESULTS

TMUCRD comprises 89 tables (eg, 29 tables for each hospital and 2 linked tables), including demographics, diagnoses, medications, procedures and measurements, among others. It encompasses data from more than 4.15 million patients with various medical records, spanning from the year 2004 to 2021. The dataset offers insights into disease prevalence, medication usage, laboratory tests and patient characteristics.

DISCUSSION

TMUCRD stands out due to its unique advantages, including diverse data types, comprehensive patient information, linked mortality and cancer registry data, regular updates and a swift application process. Its compatibility with the OMOP CDM enhances its usability and interoperability.

CONCLUSION

TMUCRD serves as a valuable resource for researchers and scholars interested in leveraging RWD for clinical research. Its availability and integration of diverse healthcare data contribute to a collaborative and data-driven approach to advancing medical knowledge and practice.

An open source knowledge graph ecosystem for the life sciences

Translational research requires data at multiple scales of biological organization. Advancements in sequencing and multi-omics technologies have increased the availability of these data, but researchers face significant integration challenges. Knowledge graphs (KGs) are used to model complex phenomena, and methods exist to construct them automatically. However, tackling complex biomedical integration problems requires flexibility in the way knowledge is modeled. Moreover, existing KG construction methods provide robust tooling at the cost of fixed or limited choices among knowledge representation models. PheKnowLator (Phenotype Knowledge Translator) is a semantic ecosystem for automating the FAIR (Findable, Accessible, Interoperable, and Reusable) construction of ontologically grounded KGs with fully customizable knowledge representation. The ecosystem includes KG construction resources (e.g., data preparation APIs), analysis tools (e.g., SPARQL endpoint resources and abstraction algorithms), and benchmarks (e.g., prebuilt KGs). We evaluated the ecosystem by systematically comparing it to existing open-source KG construction methods and by analyzing its computational performance when used to construct 12 different large-scale KGs. With flexible knowledge representation, PheKnowLator enables fully customizable KGs without compromising performance or usability.

Lightweight federated learning for STIs/HIV prediction

This paper presents a solution that prioritises high privacy protection and improves communication throughput for predicting the risk of sexually transmissible infections/human immunodeficiency virus (STIs/HIV). The approach utilised Federated Learning (FL) to construct a model from multiple clinics and key stakeholders. FL ensured that only models were shared between clinics, minimising the risk of personal information leakage. Additionally, an algorithm was explored on the FL manager side to construct a global model that aligns with the communication status of the system. Our proposed method introduced Random Forest Federated Learning for assessing the risk of STIs/HIV, incorporating a flexible aggregation process that can be adjusted to accommodate the capacious communication system. Experimental results demonstrated the significant potential of a solution for estimating STIs/HIV risk. In comparison with recent studies, our approach yielded superior results in terms of AUC (0.97) and accuracy ( 93 % ). Despite these promising findings, a limitation of the study lies in the experiment for man's data, due to the self-reported nature of the data and sensitive content. which may be subject to participant bias. Future research could check the performance of the proposed framework in partnership with high-risk populations (e.g., men who have sex with men) to provide a more comprehensive understanding of the proposed framework's impact and ultimately aim to improve health outcomes/health service optimisation.

Building Flexible, Scalable, and Machine Learning-Ready Multimodal Oncology Datasets

The advancements in data acquisition, storage, and processing techniques have resulted in the rapid growth of heterogeneous medical data. Integrating radiological scans, histopathology images, and molecular information with clinical data is essential for developing a holistic understanding of the disease and optimizing treatment. The need for integrating data from multiple sources is further pronounced in complex diseases such as cancer for enabling precision medicine and personalized treatments. This work proposes Multimodal Integration of Oncology Data System (MINDS)-a flexible, scalable, and cost-effective metadata framework for efficiently fusing disparate data from public sources such as the Cancer Research Data Commons (CRDC) into an interconnected, patient-centric framework. MINDS consolidates over 41,000 cases from across repositories while achieving a high compression ratio relative to the 3.78 PB source data size. It offers sub-5-s query response times for interactive exploration. MINDS offers an interface for exploring relationships across data types and building cohorts for developing large-scale multimodal machine learning models. By harmonizing multimodal data, MINDS aims to potentially empower researchers with greater analytical ability to uncover diagnostic and prognostic insights and enable evidence-based personalized care. MINDS tracks granular end-to-end data provenance, ensuring reproducibility and transparency. The cloud-native architecture of MINDS can handle exponential data growth in a secure, cost-optimized manner while ensuring substantial storage optimization, replication avoidance, and dynamic access capabilities. Auto-scaling, access controls, and other mechanisms guarantee pipelines' scalability and security. MINDS overcomes the limitations of existing biomedical data silos via an interoperable metadata-driven approach that represents a pivotal step toward the future of oncology data integration.

Perspectives on Big Data and Big Data Analytics in Healthcare

Big data (BD) is of high interest for research and practice purposes because it has the potential to provide insights into the population served and healthcare practices. Much progress has been made in collecting BD and creating tools for big data analytics (BDA). However, healthcare organizations continue to experience challenges associated with BD characteristics and BDA tools. Utilization of BD impacts current decision-making, planning, and future use of artificial intelligence (AI) tools, which are trained on BD. This qualitative study focused on better understanding the reality of BD and BDA management and usage by healthcare organizations. Six structured interviews were conducted with individuals who work with healthcare BD and BDA. Findings confirmed the known challenges associated with BD/BDA and added rich insights into the structural, operational and utilization aspects, as well as future directions. Such perspectives are valuable for education and improvements in BD/BDA management and development.

Centralized healthcare database for ensuring better healthcare: Are we lagging behind?

doi: https://doi.org/10.12669/pjms.40.3.9084 How to cite this: Tariq S, Tariq S, Shoukat AA. Centralized healthcare database for ensuring better healthcare: Are we lagging behind? Pak J Med Sci. 2024;40(3):---------. doi: https://doi.org/10.12669/pjms.40.3.9084 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Identifying Existing Evidence to Potentially Develop a Machine Learning Diagnostic Algorithm for Cough in Primary Care Settings: Scoping Review

BACKGROUND

Primary care is known to be one of the most complex health care settings because of the high number of theoretically possible diagnoses. Therefore, the process of clinical decision-making in primary care includes complex analytical and nonanalytical factors such as gut feelings and dealing with uncertainties. Artificial intelligence is also mandated to offer support in finding valid diagnoses. Nevertheless, to translate some aspects of what occurs during a consultation into a machine-based diagnostic algorithm, the probabilities for the underlying diagnoses (odds ratios) need to be determined.

OBJECTIVE

Cough is one of the most common reasons for a consultation in general practice, the core discipline in primary care. The aim of this scoping review was to identify the available data on cough as a predictor of various diagnoses encountered in general practice. In the context of an ongoing project, we reflect on this database as a possible basis for a machine-based diagnostic algorithm. Furthermore, we discuss the applicability of such an algorithm against the background of the specifics of general practice.

METHODS

The PubMed, Scopus, Web of Science, and Cochrane Library databases were searched with defined search terms, supplemented by the search for gray literature via the German Journal of Family Medicine until April 20, 2023. The inclusion criterion was the explicit analysis of cough as a predictor of any conceivable disease. Exclusion criteria were articles that did not provide original study results, articles in languages other than English or German, and articles that did not mention cough as a diagnostic predictor.

RESULTS

In total, 1458 records were identified for screening, of which 35 articles met our inclusion criteria. Most of the results (11/35, 31%) were found for chronic obstructive pulmonary disease. The others were distributed among the diagnoses of asthma or unspecified obstructive airway disease, various infectious diseases, bronchogenic carcinoma, dyspepsia or gastroesophageal reflux disease, and adverse effects of angiotensin-converting enzyme inhibitors. Positive odds ratios were found for cough as a predictor of chronic obstructive pulmonary disease, influenza, COVID-19 infections, and bronchial carcinoma, whereas the results for cough as a predictor of asthma and other nonspecified obstructive airway diseases were inconsistent.

CONCLUSIONS

Reliable data on cough as a predictor of various diagnoses encountered in general practice are scarce. The example of cough does not provide a sufficient database to contribute odds to a machine learning-based diagnostic algorithm in a meaningful way.

AI in Rehabilitation Medicine: Opportunities and Challenges

Artificial intelligence (AI) tools are increasingly able to learn from larger and more complex data, thus allowing clinicians and scientists to gain new insights from the information they collect about their patients every day. In rehabilitation medicine, AI can be used to find patterns in huge amounts of healthcare data. These patterns can then be leveraged at the individual level, to design personalized care strategies and interventions to optimize each patient's outcomes. However, building effective AI tools requires many careful considerations about how we collect and handle data, how we train the models, and how we interpret results. In this perspective, we discuss some of the current opportunities and challenges for AI in rehabilitation. We first review recent trends in AI for the screening, diagnosis, treatment, and continuous monitoring of disease or injury, with a special focus on the different types of healthcare data used for these applications. We then examine potential barriers to designing and integrating AI into the clinical workflow, and we propose an end-to-end framework to address these barriers and guide the development of effective AI for rehabilitation. Finally, we present ideas for future work to pave the way for AI implementation in real-world rehabilitation practices.

Innovations in genomic antimicrobial resistance surveillance

Whole-genome sequencing of antimicrobial-resistant pathogens is increasingly being used for antimicrobial resistance (AMR) surveillance, particularly in high-income countries. Innovations in genome sequencing and analysis technologies promise to revolutionise AMR surveillance and epidemiology; however, routine adoption of these technologies is challenging, particularly in low-income and middle-income countries. As part of a wider series of workshops and online consultations, a group of experts in AMR pathogen genomics and computational tool development conducted a situational analysis, identifying the following under-used innovations in genomic AMR surveillance: clinical metagenomics, environmental metagenomics, gene or plasmid tracking, and machine learning. The group recommended developing cost-effective use cases for each approach and mapping data outputs to clinical outcomes of interest to justify additional investment in capacity, training, and staff required to implement these technologies. Harmonisation and standardisation of methods, and the creation of equitable data sharing and governance frameworks, will facilitate successful implementation of these innovations.

Digital health technologies and major depressive disorder

There is an urgent need to improve the clinical management of major depressive disorder (MDD), which has become increasingly prevalent over the past two decades. Several gaps and challenges in the awareness, detection, treatment, and monitoring of MDD remain to be addressed. Digital health technologies have demonstrated utility in relation to various health conditions, including MDD. Factors related to the COVID-19 pandemic have accelerated the development of telemedicine, mobile medical apps, and virtual reality apps and have continued to introduce new possibilities across mental health care. Growing access to and acceptance of digital health technologies present opportunities to expand the scope of care and to close gaps in the management of MDD. Digital health technology is rapidly evolving the options for nonclinical support and clinical care for patients with MDD. Iterative efforts to validate and optimize such digital health technologies, including digital therapeutics and digital biomarkers, continue to improve access to and quality of personalized detection, treatment, and monitoring of MDD. The aim of this review is to highlight the existing gaps and challenges in depression management and discuss the current and future landscape of digital health technology as it applies to the challenges faced by patients with MDD and their healthcare providers.

Using machine learning approach for screening metastatic biomarkers in colorectal cancer and predictive modeling with experimental validation

Colorectal cancer (CRC) liver metastasis accounts for the majority of fatalities associated with CRC. Early detection of metastasis is crucial for improving patient outcomes but can be delayed due to a lack of symptoms. In this research, we aimed to investigate CRC metastasis-related biomarkers by employing a machine learning (ML) approach and experimental validation. The gene expression profile of CRC patients with liver metastasis was obtained using the GSE41568 dataset, and the differentially expressed genes between primary and metastatic samples were screened. Subsequently, we carried out feature selection to identify the most relevant DEGs using LASSO and Penalized-SVM methods. DEGs commonly selected by these methods were selected for further analysis. Finally, the experimental validation was done through qRT-PCR. 11 genes were commonly selected by LASSO and P-SVM algorithms, among which seven had prognostic value in colorectal cancer. It was found that the expression of the MMP3 gene decreases in stage IV of colorectal cancer compared to other stages (P value < 0.01). Also, the expression level of the WNT11 gene was observed to increase significantly in this stage (P value < 0.001). It was also found that the expression of WNT5a, TNFSF11, and MMP3 is significantly lower, and the expression level of WNT11 is significantly higher in liver metastasis samples compared to primary tumors. In summary, this study has identified a set of potential biomarkers for CRC metastasis using ML algorithms. The findings of this research may provide new insights into identifying biomarkers for CRC metastasis and may potentially lay the groundwork for innovative therapeutic strategies for treatment of this disease.

Navigating data governance associated with real-world data for public benefit: an overview in the UK and future considerations

Real-world data encompass data primarily captured for the provision or operation of services, for example, electronic health records for direct care purposes, but which may have secondary uses for informing research or commissioning. Public benefit is potentially forfeited by the underutilisation of real-world data for secondary uses, in part due to risk aversion when faced with the prospect of navigating necessary and important data governance processes. Such processes can be perceived as complex, daunting, time-consuming and exposing organisations to risk. By providing an overview description and discussion around the role of six key legal and information governance frameworks and their role regarding responsible data access, linkage and sharing, our intention is to make data governance a less daunting prospect and reduce the perception that it is a barrier to secondary uses, thus enabling public benefit.

Electronic health record interoperability using FHIR and blockchain: A bibliometric analysis and future perspective

Electronic health records (EHRs) constitute vital statistics, current health condition, ongoing therapies, and patient data; hence, their interoperability could be useful for epidemiologic and clinical research. Fast Healthcare Interoperability Resources (FHIR) and blockchain are currently "in-use" and tested for exchange of such data. The annual scientific production of publications for both FHIR and blockchain shows steady growth. The data interoperability and electronic data interchange have been introduced in the field of EHR in 2020, hence inferring that data interoperability is relatively a new domain. The thematic mapping suggested "interoperability" of EHR is well-developed and important for the structure of the research field.

Paucity of Health Data in Africa: An Obstacle to Digital Health Implementation and Evidence-Based Practice

Background: Among the numerous challenges that Africa faces in improving its healthcare systems, the paucity of health data stands out as paramount. This study aims to examine the challenges related to the paucity of health data in Africa and its impact on the implementation of digital health and evidence-based practice. The findings of the study reveal that health data availability in Africa is both limited and frequently of poor quality. Several factors contribute to this concerning situation, encompassing inadequate infrastructure, a shortage of resources, and cultural barriers. Furthermore, the available data, despite its limitations, is often underutilized due to a lack of capacity and expertise in data analysis and interpretation. Policy Options and Recommendations: To improve healthcare delivery in Africa, we recommend implementing novel strategies for data collection. It's important to recognize that effective information technology service is crucial for enhancing healthcare delivery, and a holistic approach is necessary to achieve this. Conclusion: This brief presents information to help policymakers develop long-term solutions to Africa's health data poverty. Taking action based on this evidence can assist in addressing the problem.

How Can China's New Health Care Reform Promote the Balance of Interest Game?-Based on Game Evolution and Simulation Analysis

Purpose

The new round of medical reform is a significant exploration of reform in the public service sector in China. Health insurance regulatory departments, medical institutions, and patients, as critical stakeholders in China's medical reform, play a crucial role in the success of the reform through their strategic interactions.

Patients and Methods

Starting from the perspective of bounded rationality, applies evolutionary game theory to establish an evolutionary game model for the collaborative governance of health insurance regulatory departments, medical institutions, and patients and analyzes the stability of each party's strategy and the sensitivity of parameters in the tripartite game system.

Results

The study shows that an equilibrium point will be formed when medical institutions provide reasonable treatment, patients choose to accept treatment, and health insurance regulatory departments adopt a lenient regulatory strategy, maximizing the interests of all parties involved in the game. Factors such as the benefits of unreasonable treatment by medical institutions, fines, and regulatory costs impact the decision-making of health insurance regulatory departments. To maximize social welfare, health insurance regulatory departments should reform payment methods, adjust medical service behaviors of medical institutions, and guide the rational allocation of medical resources; the government should increase subsidies for the operation of medical institutions and the intensity of penalties; regulatory departments should reduce regulatory costs and introduce third-party forces to strengthen health insurance supervision further.

Conclusion

The research findings of this paper will provide valuable insights into some countries' medical and health reform.

Multi-Omics and Management of Follicular Carcinoma of the Thyroid

Follicular thyroid carcinoma (FTC) is the second most common cancer of the thyroid gland, accounting for up to 20% of all primary malignant tumors in iodine-replete areas. The diagnostic work-up, staging, risk stratification, management, and follow-up strategies in patients who have FTC are modeled after those of papillary thyroid carcinoma (PTC), even though FTC is more aggressive. FTC has a greater propensity for haematogenous metastasis than PTC. Furthermore, FTC is a phenotypically and genotypically heterogeneous disease. The diagnosis and identification of markers of an aggressive FTC depend on the expertise and thoroughness of pathologists during histopathological analysis. An untreated or metastatic FTC is likely to de-differentiate and become poorly differentiated or undifferentiated and resistant to standard treatment. While thyroid lobectomy is adequate for the treatment of selected patients who have low-risk FTC, it is not advisable for patients whose tumor is larger than 4 cm in diameter or has extensive extra-thyroidal extension. Lobectomy is also not adequate for tumors that have aggressive mutations. Although the prognosis for over 80% of PTC and FTC is good, nearly 20% of the tumors behave aggressively. The introduction of radiomics, pathomics, genomics, transcriptomics, metabolomics, and liquid biopsy have led to improvements in the understanding of tumorigenesis, progression, treatment response, and prognostication of thyroid cancer. The article reviews the challenges that are encountered during the diagnostic work-up, staging, risk stratification, management, and follow-up of patients who have FTC. How the application of multi-omics can strengthen decision-making during the management of follicular carcinoma is also discussed.

Adopting an electronic medication administration system in long-term care facilities: a key stakeholder interview study in Macao

To improve medication safety for residents in long-term care facilities (LTCFs), electronic medication administration records (eMARs) are widely adopted in Macao. This study aimed to (1) develop a logic model for adopting eMAR in LTCFs and (2) explore the contextual factors relevant to the implementation. Semi-structured interviews were conducted with key stakeholders (managers, doctors, nurses, pharmacy staff and other frontline workers) experienced with eMAR in LTCFs in Macao between February and March 2021. Purposive sampling was used for recruitment and thematic analysis followed the theoretical framework of the logic model. All 57 participants were positive about eMAR. Financial and nonfinancial resources were critical to adopting eMAR. eMAR was mostly used for its functions in documentation, e-prescribing and monitoring. Immediate output included simplified working process, reduced errors, closer monitoring of residents' conditions, and timely communication among staff. The outcomes mainly related to efficiency, safety and quality of care, workload redundancy, and data unification. Key influencing factors included eMAR flexibility, stability, and technical support. Adopting eMARs is highly consuming and the benefits in improving quality of care can only be realized with appropriate implementation, precise execution, regular evaluation and responsive adjustment. The proposed logic model framework serves as a roadmap for LTCFs, both current and future users of eMAR.

A digital health ecosystem ontology from the perspective of Australian consumers: a mixed-method literature analysis

This study presents an ontology that scopes the digital health ecosystem from a consumer-centered perspective. We used a mixed-method analysis on a set of papers collected for a comprehensive review to identify common themes, components, and patterns that repeatedly emerge within Australian-based digital health studies. Three major and four child themes were identified as the foundational aspects of the proposed ontology. The child themes have more precise concept definitions, inherited and distinguishing attributes. Out of 179 recognized concepts, 33 were related to the Healthcare theme; 23 concepts formed a cluster of employed devices under the Technology theme; 40 concepts were associated with Use and Usability factors. 60 other concepts formed the cluster of the consumer-user theme. The theme of Digital Health was seen as being connected to 2 independent clusters. The main cluster embodied 21 extracted concepts, semantically related to "data, information, and knowledge," whilst the second cluster embodied concepts related to "healthcare." Different stakeholders can utilize this ontology to define their landscape of digitally enabled healthcare. The novelty of this work resides in capturing a consumer-centered perspective and the method we used in deriving the ontology - formalizing the results of a systematic review based on data-driven analysis methods.

Public perceptions and attitudes of the national project of bio-big data: A nationwide survey in the Republic of Korea

Background: The National Project of Bio-Big Data (NPBBD) is a South Korean bio-big data collection project, expected to include health, genomic, and lifelog data of one million Koreans. The Ethical, Legal, and Social Implications study is a parallel study active since 2020. As part of the study, a public survey was conducted to evaluate public attitudes towards engagement schemes, such as public committees and web portals for communication between the public and researchers. Methods: An online survey was conducted from March 3-9, 2021, using structured questionnaires addressed to 1,000 adults aged 20-59 years. Results: Several respondents reported a positive attitude towards participation (43.6% "somewhat," 14.3% "definitely"), whereas approximately one-third (36.5%) reported a neutral attitude. Positive factors that may affect the willingness of the respondents to participate included receiving health information (25.1%), contributing to research on cancer and rare diseases (21.9%), and advancing personalized medicine (21.5%). Conversely, negative factors were mainly associated with concerns regarding the risk of data leakage (22.8%), discrimination (21.1%), lack of information (13.5%), possibility of knowing the risk of being diagnosed with an incurable diseases (12.5%), and possibility of using data in industry (11.3%). In terms of project governance, respondents tended to recognize the importance of public participation in incorporating public opinion into the project design. Conclusion: These results have implications for the participant recruitment process, public engagement strategies, and the scope of user (academics/industry, domestic/overseas) accessibility to the database.

Blockchain for Patient Safety: Use Cases, Opportunities and Open Challenges

Medical errors are recognized as major threats to patient safety worldwide. Lack of streamlined communication and an inability to share and exchange data are among the contributory factors affecting patient safety. To address these challenges, blockchain can be utilized to ensure a secure, transparent and decentralized data exchange among stakeholders. In this study, we discuss six use cases that can benefit from blockchain to gain operational effectiveness and efficiency in the patient safety context. The role of stakeholders, system requirements, opportunities and challenges are discussed in each use case in detail. Connecting stakeholders and data in complex healthcare systems, blockchain has the potential to provide an accountable and collaborative milieu for the delivery of safe care. By reviewing the potential of blockchain in six use cases, we suggest that blockchain provides several benefits, such as an immutable and transparent structure and decentralized architecture, which may help transform health care and enhance patient safety. While blockchain offers remarkable opportunities, it also presents open challenges in the form of trust, privacy, scalability and governance. Future research may benefit from including additional use cases and developing smart contracts to present a more comprehensive view on potential contributions and challenges to explore the feasibility of blockchain-based solutions in the patient safety context.

Applications of Artificial Intelligence to Obesity Research: Scoping Review of Methodologies

BACKGROUND

Obesity is a leading cause of preventable death worldwide. Artificial intelligence (AI), characterized by machine learning (ML) and deep learning (DL), has become an indispensable tool in obesity research.

OBJECTIVE

This scoping review aimed to provide researchers and practitioners with an overview of the AI applications to obesity research, familiarize them with popular ML and DL models, and facilitate the adoption of AI applications.

METHODS

We conducted a scoping review in PubMed and Web of Science on the applications of AI to measure, predict, and treat obesity. We summarized and categorized the AI methodologies used in the hope of identifying synergies, patterns, and trends to inform future investigations. We also provided a high-level, beginner-friendly introduction to the core methodologies to facilitate the dissemination and adoption of various AI techniques.

RESULTS

We identified 46 studies that used diverse ML and DL models to assess obesity-related outcomes. The studies found AI models helpful in detecting clinically meaningful patterns of obesity or relationships between specific covariates and weight outcomes. The majority (18/22, 82%) of the studies comparing AI models with conventional statistical approaches found that the AI models achieved higher prediction accuracy on test data. Some (5/46, 11%) of the studies comparing the performances of different AI models revealed mixed results, indicating the high contingency of model performance on the data set and task it was applied to. An accelerating trend of adopting state-of-the-art DL models over standard ML models was observed to address challenging computer vision and natural language processing tasks. We concisely introduced the popular ML and DL models and summarized their specific applications in the studies included in the review.

CONCLUSIONS

This study reviewed AI-related methodologies adopted in the obesity literature, particularly ML and DL models applied to tabular, image, and text data. The review also discussed emerging trends such as multimodal or multitask AI models, synthetic data generation, and human-in-the-loop that may witness increasing applications in obesity research.

Introducing AI to the molecular tumor board: one direction toward the establishment of precision medicine using large-scale cancer clinical and biological information

Since U.S. President Barack Obama announced the Precision Medicine Initiative in his New Year's State of the Union address in 2015, the establishment of a precision medicine system has been emphasized worldwide, particularly in the field of oncology. With the advent of next-generation sequencers specifically, genome analysis technology has made remarkable progress, and there are active efforts to apply genome information to diagnosis and treatment. Generally, in the process of feeding back the results of next-generation sequencing analysis to patients, a molecular tumor board (MTB), consisting of experts in clinical oncology, genetic medicine, etc., is established to discuss the results. On the other hand, an MTB currently involves a large amount of work, with humans searching through vast databases and literature, selecting the best drug candidates, and manually confirming the status of available clinical trials. In addition, as personalized medicine advances, the burden on MTB members is expected to increase in the future. Under these circumstances, introducing cutting-edge artificial intelligence (AI) technology and information and communication technology to MTBs while reducing the burden on MTB members and building a platform that enables more accurate and personalized medical care would be of great benefit to patients. In this review, we introduced the latest status of elemental technologies that have potential for AI utilization in MTB, and discussed issues that may arise in the future as we progress with AI implementation.

Data consistency in the English Hospital Episodes Statistics database

BACKGROUND

To gain maximum insight from large administrative healthcare datasets it is important to understand their data quality. Although a gold standard against which to assess criterion validity rarely exists for such datasets, internal consistency can be evaluated. We aimed to identify inconsistencies in the recording of mandatory International Statistical Classification of Diseases and Related Health Problems, tenth revision (ICD-10) codes within the Hospital Episodes Statistics dataset in England.

METHODS

Three exemplar medical conditions where recording is mandatory once diagnosed were chosen: autism, type II diabetes mellitus and Parkinson's disease dementia. We identified the first occurrence of the condition ICD-10 code for a patient during the period April 2013 to March 2021 and in subsequent hospital spells. We designed and trained random forest classifiers to identify variables strongly associated with recording inconsistencies.

RESULTS

For autism, diabetes and Parkinson's disease dementia respectively, 43.7%, 8.6% and 31.2% of subsequent spells had inconsistencies. Coding inconsistencies were highly correlated with non-coding of an underlying condition, a change in hospital trust and greater time between the spell with the first coded diagnosis and the subsequent spell. For patients with diabetes or Parkinson's disease dementia, the code recording for spells without an overnight stay were found to have a higher rate of inconsistencies.

CONCLUSIONS

Data inconsistencies are relatively common for the three conditions considered. Where these mandatory diagnoses are not recorded in administrative datasets, and where clinical decisions are made based on such data, there is potential for this to impact patient care.

Resource integration capabilities to enable platform complementarity in healthcare service ecosystem co-creation

Purpose

Covid has increased the usage of multisided digital platforms. For companies, this has become a business opportunity. Data usage on platforms requires that platform companies co-create services for common customers. In this case, the target is not to make the same value proposition but rather to use the resources such as data, knowledge, technology, or institutions in a complementary manner. Platforms are characterized as a combination of hardware and software including standards, interfaces, and rules making it possible for different ecosystem players to complement and interact in the ecosystem. Current ecosystems include several platforms that do not work without resource integration. The purpose of this study is to increase understanding what do we mean by resource complementarity in service ecosystems.

Design/methodology/approach

This study was done via an in-depth qualitative case study in which a health service ecosystem co-creating technological surgery innovation was used as a unit of analysis.

Findings

The authors’ findings suggest that key resource capabilities, to enable complementarity in service ecosystems, are motivation, knowledge, skills, data and complementary designed technology components.

Research limitations/implications

The authors’ study increases theoretical understanding of what does one mean by construct of resource complementarity.

Practical implications

From a managerial perspective, it is shown that organizations need to develop adaptive capabilities to utilize internal and external competencies and resources and enable co-creative processes within the service ecosystem.

Originality/value

Very few empirical studies in the marketing literature have focused on multi-sided digital platforms and their resource complementarity in the data-driven healthcare ecosystem settings.

Using real world data to advance the provision of supportive cancer care: mucositis as a case study

PURPOSE OF REVIEW

For decades, clinical decision making and practice has been largely informed by data generated through randomized clinical trials (RCTs). By design, RCTs are highly restricted in both scope and scale, resulting in narrow indications and iterative advances in clinical practice. With the transition to electronic health records, there are now endless opportunities to utilize these 'real world' data (RWD) to make more substantive advances in our understanding that are, by nature, more applicable to reality. This review discusses the current paradigm of using big data to advance and inform the provision of supportive cancer care, using mucositis as a case study.

RECENT FINDINGS

Global efforts to synthesize RWD in cancer have almost exclusively focused on tumor classification and treatment efficacy, leveraging on routine tumor pathology and binary response outcomes. In contrast, clinical notes and billing codes are not as applicable to treatment side effects which require integration of both clinical and biological data, as well as patient-reported outcomes.

SUMMARY

Cancer treatment-induced toxicities are heterogeneous and complex, and as such, the use of RWD to better understand their etiology and interaction is challenging. Multidisciplinary cooperation and leadership are needed to improve data collection and governance to ensure the right data is accessible and reliable.

Data silos undermine efforts to characterize, predict, and mitigate dementia-related missing person incidents

It is estimated that up to 60% of people living with dementia go missing at least once during the course of their disease. Databases on missing incidents involving people living with dementia are managed in silos with minimal or incomplete data. A national strategy for the collection of data on missing incidents of people living with dementia would optimize time and resources spent on police and search and rescue and enhance chances of saving lives of those who go missing. Such a strategy would be a first step toward developing strategies to prevent future missing person incidents among this population. The objectives of this manuscript are to: (1) describe the issues and challenges related to the lack of integrated data on people living with dementia at risk of going missing, and (2) propose directions to create a national database.

The Feasibility and Utility of Harnessing Digital Health to Understand Clinical Trajectories in Medication Treatment for Opioid Use Disorder: D-TECT Study Design and Methodological Considerations

Introduction

Across the U.S., the prevalence of opioid use disorder (OUD) and the rates of opioid overdoses have risen precipitously in recent years. Several effective medications for OUD (MOUD) exist and have been shown to be life-saving. A large volume of research has identified a confluence of factors that predict attrition and continued substance use during substance use disorder treatment. However, much of this literature has examined a small set of potential moderators or mediators of outcomes in MOUD treatment and may lead to over-simplified accounts of treatment non-adherence. Digital health methodologies offer great promise for capturing intensive, longitudinal ecologically-valid data from individuals in MOUD treatment to extend our understanding of factors that impact treatment engagement and outcomes.

Methods

This paper describes the protocol (including the study design and methodological considerations) from a novel study supported by the National Drug Abuse Treatment Clinical Trials Network at the National Institute on Drug Abuse (NIDA). This study (D-TECT) primarily seeks to evaluate the feasibility of collecting ecological momentary assessment (EMA), smartphone and smartwatch sensor data, and social media data among patients in outpatient MOUD treatment. It secondarily seeks to examine the utility of EMA, digital sensing, and social media data (separately and compared to one another) in predicting MOUD treatment retention, opioid use events, and medication adherence [as captured in electronic health records (EHR) and EMA data]. To our knowledge, this is the first project to include all three sources of digitally derived data (EMA, digital sensing, and social media) in understanding the clinical trajectories of patients in MOUD treatment. These multiple data streams will allow us to understand the relative and combined utility of collecting digital data from these diverse data sources. The inclusion of EHR data allows us to focus on the utility of digital health data in predicting objectively measured clinical outcomes.

Discussion

Results may be useful in elucidating novel relations between digital data sources and OUD treatment outcomes. It may also inform approaches to enhancing outcomes measurement in clinical trials by allowing for the assessment of dynamic interactions between individuals' daily lives and their MOUD treatment response.

Clinical Trial Registration

Identifier: NCT04535583.

Innovations in Genomics and Big Data Analytics for Personalized Medicine and Health Care: A Review

Big data in health care is a fast-growing field and a new paradigm that is transforming case-based studies to large-scale, data-driven research. As big data is dependent on the advancement of new data standards, technology, and relevant research, the future development of big data applications holds foreseeable promise in the modern day health care revolution. Enormously large, rapidly growing collections of biomedical omics-data (genomics, proteomics, transcriptomics, metabolomics, glycomics, etc.) and clinical data create major challenges and opportunities for their analysis and interpretation and open new computational gateways to address these issues. The design of new robust algorithms that are most suitable to properly analyze this big data by taking into account individual variability in genes has enabled the creation of precision (personalized) medicine. We reviewed and highlighted the significance of big data analytics for personalized medicine and health care by focusing mostly on machine learning perspectives on personalized medicine, genomic data models with respect to personalized medicine, the application of data mining algorithms for personalized medicine as well as the challenges we are facing right now in big data analytics.

Machine learning, artificial intelligence and the prediction of dementia

PURPOSE OF REVIEW

Artificial intelligence and its division machine learning are emerging technologies that are increasingly applied in medicine. Artificial intelligence facilitates automatization of analytical modelling and contributes to prediction, diagnostics and treatment of diseases. This article presents an overview of the application of artificial intelligence in dementia research.

RECENT FINDINGS

Machine learning and its branch Deep Learning are widely used in research to support in diagnosis and prediction of dementia. Deep Learning models in certain tasks often result in better accuracy of detection and prediction of dementia than traditional machine learning methods, but they are more costly in terms of run times and hardware requirements. Both machine learning and Deep Learning models have their own strengths and limitations. Currently, there are few datasets with limited data available to train machine learning models. There are very few commercial applications of machine learning in medical practice to date, mostly represented by mobile applications, which include questionnaires and psychometric assessments with limited machine learning data processing.

SUMMARY

Application of machine learning technologies in detection and prediction of dementia may provide an advantage to psychiatry and neurology by promoting a better understanding of the nature of the disease and more accurate evidence-based processes that are reproducible and standardized.

Medical-Blocks: A Platform for Exploration, Management, Analysis, and Sharing of Data in Biomedical Research

BACKGROUND

Biomedical research requires healthcare institutions to provide sensitive clinical data to leverage data science and artificial intelligence technologies. However, providing healthcare data to researchers simple and secure, proves to be challenging for healthcare institutions.

OBJECTIVE

We describe and introduce Medical-Blocks, a platform for data exploration, data management, data analysis, and data sharing in biomedical research.

METHODS

The specification requirements for Medical-Blocks included: i) Connection to data sources of healthcare institutions with an interface for data exploration, ii) management of data in an internal file storage system, iii) data analysis through visualization and classification of data, and iv) data sharing via a file hosting service for collaboration. Medical-Blocks should be simple to use via a web-based user interface and extensible with new functionalities by a modular design via microservices ("blocks"). The scalability of the platform should be ensured by containerization. Security and legal regulations were considered during the development.

RESULTS

Medical-Blocks is a web application that runs in the cloud or as a local instance at a healthcare institution. Local instances of Medical-Blocks access data sources such as electronic health records and picture archiving and communications system (PACS) at healthcare institutions. Researchers and clinicians can explore, manage, and analyze the available data through Medical-Blocks. The data analysis involves classification of data for metadata extraction and the formation of cohorts. In collaborations, metadata (e.g., number of patients per cohort) and/or the data itself can be shared through Medical-Blocks locally or via a cloud instance to other researchers and clinicians.

CONCLUSIONS

Medical-Blocks facilitates biomedical research by providing a centralized platform to interact with medical data in collaborative research projects. The access to and management of medical data is simplified. Data can be swiftly analyzed to form cohorts for research and be shared among researchers. The modularity of Medical-Blocks makes the platform feasible for biomedical research where heterogenous medical data is needed.

CLINICALTRIAL

Artificial intelligence in liver diseases: improving diagnostics, prognostics and response prediction

Clinical routine in hepatology involves the diagnosis and treatment of a wide spectrum of metabolic, infectious, autoimmune and neoplastic diseases. Clinicians integrate qualitative and quantitative information from multiple data sources to make a diagnosis, prognosticate the disease course, and recommend a treatment. In the last 5 years, advances in artificial intelligence (AI), particularly in deep learning, have made it possible to extract clinically relevant information from complex and diverse clinical datasets. In particular, histopathology and radiology image data contain diagnostic, prognostic and predictive information which AI can extract. Ultimately, such AI systems could be implemented in clinical routine as decision support tools. However, in the context of hepatology, this requires further large-scale clinical validation and regulatory approval. Herein, we summarise the state of the art in AI in hepatology with a particular focus on histopathology and radiology data. We present a roadmap for the further development of novel biomarkers in hepatology and outline critical obstacles which need to be overcome.

Database Supported Long-term Management of Chronic Diseases - Data from the German Disease Management Programmes as a Source for Continuing Medical Education

Disease Management Programmes (DMPs) have been introduced by German Federal Government in 2002 to improve long-term care for patients with specific chronic diseases. Digitisation has been a requirement to reliably document patient data in DMPs. This report presents data from six DMPs in the German federal state of North Rhine-Westphalia. It demonstrates that high level long-term quality of care can be achieved and maintained. But beyond clinical purposes DMP data are also an invaluable source to supply content in CME.