Machine learning-based Cerebral Venous Thrombosis diagnosis with clinical data.

OBJECTIVES: Cerebral Venous Thrombosis (CVT) poses diagnostic challenges due to the variability in disease course and symptoms. The prognosis of CVT relies on early diagnosis. Our study focuses on developing a machine learning-based screening algorithm using clinical data from a large neurology referral center in southern Iran. METHODS: The Iran Cerebral Venous Thrombosis Registry (ICVTR code: 9001013381) provided data on 382 CVT cases from Namazi Hospital. The control group comprised of adult headache patients without CVT as confirmed by neuroimaging and was retrospectively selected from those admitted to the same hospital. We collected 60 clinical and demographic features for model development and validation. Our modeling pipeline involved imputing missing values and evaluating four machine learning algorithms: generalized linear model, random forest, support vector machine, and extreme gradient boosting. RESULTS: A total of 314 CVT cases and 575 controls were included. The highest AUROC was reached when imputation was used to estimate missing values for all the variables, combined with the support vector machine model (AUROC = 0.910, Recall = 0.73, Precision = 0.88). The best recall was achieved also by the support vector machine model when only variables with less than 50 % missing rate were included (AUROC = 0.887, Recall = 0.77, Precision = 0.86). The random forest model yielded the best precision by using variables with less than 50 % missing rate (AUROC = 0.882, Recall = 0.61, Precision = 0.94). CONCLUSION: The application of machine learning techniques using clinical data showed promising results in accurately diagnosing CVT within our study population. This approach offers a valuable complementary assistive tool or an alternative to resource-intensive imaging methods.

A deep learning approach for overall survival prediction in lung cancer with missing values.

BACKGROUND AND OBJECTIVE: In the field of lung cancer research, particularly in the analysis of overall survival (OS), artificial intelligence (AI) serves crucial roles with specific aims. Given the prevalent issue of missing data in the medical domain, our primary objective is to develop an AI model capable of dynamically handling this missing data. Additionally, we aim to leverage all accessible data, effectively analyzing both uncensored patients who have experienced the event of interest and censored patients who have not, by embedding a specialized technique within our AI model, not commonly utilized in other AI tasks. Through the realization of these objectives, our model aims to provide precise OS predictions for non-small cell lung cancer (NSCLC) patients, thus overcoming these significant challenges. METHODS: We present a novel approach to survival analysis with missing values in the context of NSCLC, which exploits the strengths of the transformer architecture to account only for available features without requiring any imputation strategy. More specifically, this model tailors the transformer architecture to tabular data by adapting its feature embedding and masked self-attention to mask missing data and fully exploit the available ones. By making use of ad-hoc designed losses for OS, it is able to account for both censored and uncensored patients, as well as changes in risks over time. RESULTS: We compared our method with state-of-the-art models for survival analysis coupled with different imputation strategies. We evaluated the results obtained over a period of 6 years using different time granularities obtaining a Ct-index, a time-dependent variant of the C-index, of 71.97, 77.58 and 80.72 for time units of 1 month, 1 year and 2 years, respectively, outperforming all state-of-the-art methods regardless of the imputation method used. CONCLUSIONS: The results show that our model not only outperforms the state-of-the-art's performance but also simplifies the analysis in the presence of missing data, by effectively eliminating the need to identify the most appropriate imputation strategy for predicting OS in NSCLC patients.

Revisions to the requirement of the Japanese clinical study data for biosimilar developments in Japan.

BACKGROUND: The 'Questions and Answers (Q&A)' document regarding Japanese biosimilar guideline elucidated that Japanese participant enrollment in at least one comparative clinical study was required for the marketing authorization application (MAA) of biosimilars in Japan. RESEARCH DESIGN AND METHODS: To discuss the requirement of Japanese clinical study data for biosimilar development, the trend in comparative clinical studies conducted for approved biosimilars of monoclonal antibodies and fusion proteins was analyzed, and the consistency of the results between the overall population and the Japanese population according to the publicly available information was reviewed. RESULTS: The number of comparative clinical studies enrolling Japanese participants was 25 cases, and the type and percentage were 13 (52%) and 12 (48%) cases of comparative pharmacokinetic study and comparative efficacy study, respectively. In all comparative clinical studies, consistent results between the overall population and the Japanese population were shown. CONCLUSIONS: Our study indicated that Japanese participant enrollment in comparative clinical studies may not always be necessary for biosimilar development when certain conditions are satisfied. This has been described in the revised Q&A document published by the Ministry of Health, Labour and Welfare in January 2024.

RNA-binding protein AZGP1 inhibits epithelial cell proliferation by regulating the genes of alternative splicing in COPD.

BACKGROUND: Chronic Obstructive Pulmonary Disease (COPD) is characterized by high morbidity, disability, and mortality rates worldwide. RNA-binding proteins (RBPs) might regulate genes involved in oxidative stress and inflammation in COPD patients. Single-cell transcriptome sequencing (scRNA-seq) offers an accurate tool for identifying intercellular heterogeneity and the diversity of immune cells. However, the role of RBPs in the regulation of various cells, especially AT2 cells, remains elusive. MATERIALS AND METHODS: A scRNA-seq dataset (GSE173896) and a bulk RNA-seq dataset acquired from airway tissues (GSE124180) were employed for data mining. Next, RNA-seq analysis was performed in both COPD and control patients. Differentially expressed genes (DEGs) were identified using criteria of fold change (FC ≥ 1.5 or ≤ 1.5) and P value ≤ 0.05. Lastly, Gene Ontology (GO), Kyoto Encyclopedia of Genes and Genomes (KEGG), and alternative splicing identification analyses were carried out. RESULTS: RBP genes exhibited specific expression patterns across different cell groups and participated in cell proliferation and mitochondrial dysfunction in AT2 cells. As an RBP, AZGP1 expression was upregulated in both the scRNA-seq and RNA-seq datasets. It might potentially be a candidate immune biomarker that regulates COPD progression by modulating AT2 cell proliferation and adhesion by regulating the expression of SAMD5, DNER, DPYSL3, GBP5, GBP3, and KCNJ2. Moreover, AZGP1 regulated alternative splicing events in COPD, particularly DDAH1 and SFRP1, holding significant implications in COPD. CONCLUSION: RBP gene AZGP1 inhibits epithelial cell proliferation by regulating genes participating in alternative splicing in COPD.

Direct oral anticoagulant use in hospitalized pediatric patients: Insights from nationwide data.

BACKGROUND: Direct oral anticoagulants (DOACs) have had significant impact on the management of venous thromboembolism (VTE) in adults, but these agents were not approved for use in pediatric patients until 2021. Our objective was to analyze the characteristics of pediatric patients treated with DOACs prior to and following U.S. Food and Drug Administration (FDA) approval for children and evaluate their impact on hospital outcomes. PROCEDURE: We utilized the Epic Cosmos dataset (Cosmos), a de-identified dataset of over 220 million patients, to identify patients aged 1-18 years admitted with a first-occurrence diagnosis of VTE between January 1, 2017 and June 30, 2023. Patients were grouped by anticoagulation received (unfractionated heparin, low molecular weight heparin, and/or DOACs). RESULTS: Among 5138 eligible patients, 18.1% received DOACs as all or part of their anticoagulation treatment, while 81.9% received heparin therapies alone. Patients treated with DOACs were older than patients treated with heparin monotherapy at 17.4 and 13.0 years, respectively. Non-DOAC patients were more likely to have chronic conditions and were less likely to have pulmonary embolism. Patients treated with DOACs demonstrated shorter overall length of stay and duration of intensive care unit (ICU) admission. CONCLUSIONS: DOACs remain infrequently utilized in pediatric patients, especially in those under 13 years old. Initiation on heparin therapy and transition to DOACs remains common, with 80.6% of DOAC patients receiving heparin during their hospitalization. While DOAC monotherapy is not currently endorsed as first-line therapy for DVT or PE in children, it is being used clinically. Further research is needed to clarify the impact of DOAC use on patient adherence, VTE recurrence, and healthcare cost.

European survey: citizens' attitudes on personalized medicine, genetic testing and health data sharing - design and delivery.

In the transformative landscape of healthcare, personalized medicine emerges as a pivotal shift, harnessing genetic, environmental and lifestyle data to tailor medical treatments for enhanced outcomes and cost efficiency. Central to its success is public engagement and consent to share health data amidst rising data privacy concerns. To investigate European public opinion on this paradigm, we executed a comprehensive cross-sectional survey to capture the general public's views on personalized medicine and data-sharing modalities, including digital tools and electronic records. The survey was distributed in eight major European Union countries and the results aim at guiding future policymaking and trust-building measures for secure health data exchange. This article delineates our methodological approach, whereby survey findings will be expounded in subsequent publications.

[Box: see text].

RWE ready for reimbursement? A round up of developments in real-world evidence relating to health technology assessment: part 16.

In this update, we discuss recent US FDA guidance offering more specific guidelines on appropriate study design and analysis to support causal inference for non-interventional studies and the launch of the European Medicines Agency (EMA) and the Heads of Medicines Agencies (HMA) public electronic catalogues. We also highlight an article recommending assessing data quality and suitability prior to protocol finalization and a Journal of the American Medical Association-endorsed framework for using causal language when publishing real-world evidence studies. Finally, we explore the potential of large language models to automate the development of health economic models.

Determining an Appropriate Sample Size for Qualitative Interviews to Achieve True and Near Code Saturation: Secondary Analysis of Data.

BACKGROUND: In-depth interviews are a common method of qualitative data collection, providing rich data on individuals' perceptions and behaviors that would be challenging to collect with quantitative methods. Researchers typically need to decide on sample size a priori. Although studies have assessed when saturation has been achieved, there is no agreement on the minimum number of interviews needed to achieve saturation. To date, most research on saturation has been based on in-person data collection. During the COVID-19 pandemic, web-based data collection became increasingly common, as traditional in-person data collection was possible. Researchers continue to use web-based data collection methods post the COVID-19 emergency, making it important to assess whether findings around saturation differ for in-person versus web-based interviews. OBJECTIVE: We aimed to identify the number of web-based interviews needed to achieve true code saturation or near code saturation. METHODS: The analyses for this study were based on data from 5 Food and Drug Administration-funded studies conducted through web-based platforms with patients with underlying medical conditions or with health care providers who provide primary or specialty care to patients. We extracted code- and interview-specific data and examined the data summaries to determine when true saturation or near saturation was reached. RESULTS: The sample size used in the 5 studies ranged from 30 to 70 interviews. True saturation was reached after 91% to 100% (n=30-67) of planned interviews, whereas near saturation was reached after 33% to 60% (n=15-23) of planned interviews. Studies that relied heavily on deductive coding and studies that had a more structured interview guide reached both true saturation and near saturation sooner. We also examined the types of codes applied after near saturation had been reached. In 4 of the 5 studies, most of these codes represented previously established core concepts or themes. Codes representing newly identified concepts, other or miscellaneous responses (eg, "in general"), uncertainty or confusion (eg, "don't know"), or categorization for analysis (eg, correct as compared with incorrect) were less commonly applied after near saturation had been reached. CONCLUSIONS: This study provides support that near saturation may be a sufficient measure to target and that conducting additional interviews after that point may result in diminishing returns. Factors to consider in determining how many interviews to conduct include the structure and type of questions included in the interview guide, the coding structure, and the population under study. Studies with less structured interview guides, studies that rely heavily on inductive coding and analytic techniques, and studies that include populations that may be less knowledgeable about the topics discussed may require a larger sample size to reach an acceptable level of saturation. Our findings also build on previous studies looking at saturation for in-person data collection conducted at a small number of sites.

A Simple and Systematic Approach to Qualitative Data Extraction From Social Media for Novice Health Care Researchers: Tutorial.

Social media analyses have become increasingly popular among health care researchers. Social media continues to grow its user base and, when analyzed, offers unique insight into health problems. The process of obtaining data for social media analyses varies greatly and involves ethical considerations. Data extraction is often facilitated by software tools, some of which are open source, while others are costly and therefore not accessible to all researchers. The use of software for data extraction is accompanied by additional challenges related to the uniqueness of social media data. Thus, this paper serves as a tutorial for a simple method of extracting social media data that is accessible to novice health care researchers and public health professionals who are interested in pursuing social media research. The discussed methods were used to extract data from Facebook for a study of maternal perspectives on sudden unexpected infant death.

Evaluation of a Remote Patient Monitoring Program During the COVID-19 Pandemic: Retrospective Case Study With a Mixed Methods Explanatory Sequential Design.

BACKGROUND: Community health center (CHC) patients experience a disproportionately high prevalence of chronic conditions and barriers to accessing technologies that might support the management of these conditions. One such technology includes tools used for remote patient monitoring (RPM), the use of which surged during the COVID-19 pandemic. OBJECTIVE: The aim of this study was to assess how a CHC implemented an RPM program during the COVID-19 pandemic. METHODS: This retrospective case study used a mixed methods explanatory sequential design to evaluate a CHC's implementation of a suite of RPM tools during the COVID-19 pandemic. Analyses used electronic health record-extracted health outcomes data and semistructured interviews with the CHC's staff and patients participating in the RPM program. RESULTS: The CHC enrolled 147 patients in a hypertension RPM program. After 6 months of RPM use, mean systolic blood pressure (BP) was 13.4 mm Hg lower and mean diastolic BP 6.4 mm Hg lower, corresponding with an increase in hypertension control (BP<140/90 mm Hg) from 33.3% of patients to 81.5%. Considerable effort was dedicated to standing up the program, reinforced by organizational prioritization of chronic disease management, and by a clinician who championed program implementation. Noted barriers to implementation of the RPM program were limited initial training, lack of sustained support, and complexities related to the RPM device technology. CONCLUSIONS: While RPM technology holds promise for addressing chronic disease management, successful RPM program requires substantial investment in implementation support and technical assistance.

Data Lake, Data Warehouse, Datamart, and Feature Store: Their Contributions to the Complete Data Reuse Pipeline.

Unlabelled: The growing adoption and use of health information technology has generated a wealth of clinical data in electronic format, offering opportunities for data reuse beyond direct patient care. However, as data are distributed across multiple software, it becomes challenging to cross-reference information between sources due to differences in formats, vocabularies, and technologies and the absence of common identifiers among software. To address these challenges, hospitals have adopted data warehouses to consolidate and standardize these data for research. Additionally, as a complement or alternative, data lakes store both source data and metadata in a detailed and unprocessed format, empowering exploration, manipulation, and adaptation of the data to meet specific analytical needs. Subsequently, datamarts are used to further refine data into usable information tailored to specific research questions. However, for efficient analysis, a feature store is essential to pivot and denormalize the data, simplifying queries. In conclusion, while data warehouses are crucial, data lakes, datamarts, and feature stores play essential and complementary roles in facilitating data reuse for research and analysis in health care.

Cloud-based introduction to BASH programming for biologists.

This manuscript describes the development of a resource module that is part of a learning platform named 'NIGMS Sandbox for Cloud-based Learning', https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial authored by National Institute of General Medical Sciences: NIGMS Sandbox: A Learning Platform toward Democratizing Cloud Computing for Biomedical Research at the beginning of this supplement. This module delivers learning materials introducing the utility of the BASH (Bourne Again Shell) programming language for genomic data analysis in an interactive format that uses appropriate cloud resources for data access and analyses. The next-generation sequencing revolution has generated massive amounts of novel biological data from a multitude of platforms that survey an ever-growing list of genomic modalities. These data require significant downstream computational and statistical analyses to glean meaningful biological insights. However, the skill sets required to generate these data are vastly different from the skills required to analyze these data. Bench scientists that generate next-generation data often lack the training required to perform analysis of these datasets and require support from bioinformatics specialists. Dedicated computational training is required to empower biologists in the area of genomic data analysis, however, learning to efficiently leverage a command line interface is a significant barrier in learning how to leverage common analytical tools. Cloud platforms have the potential to democratize access to the technical tools and computational resources necessary to work with modern sequencing data, providing an effective framework for bioinformatics education. This module aims to provide an interactive platform that slowly builds technical skills and knowledge needed to interact with genomics data on the command line in the Cloud. The sandbox format of this module enables users to move through the material at their own pace and test their grasp of the material with knowledge self-checks before building on that material in the next sub-module. This manuscript describes the development of a resource module that is part of a learning platform named ``NIGMS Sandbox for Cloud-based Learning'' https://github.com/NIGMS/NIGMS-Sandbox. The overall genesis of the Sandbox is described in the editorial NIGMS Sandbox [1] at the beginning of this Supplement. This module delivers learning materials on the analysis of bulk and single-cell ATAC-seq data in an interactive format that uses appropriate cloud resources for data access and analyses.

Dupilumab induces hair regrowth in pediatric alopecia areata: a real-world, single-center observational study.

Alopecia areata (AA) is nonscarring hair loss characterized by Th1 and concomitant Th2 skewing, particularly in atopic patients. Despite novel developments for adult AA, safe and effective treatments for pediatric patients remain limited. Dupilumab, with a well-studied safety profile, may have therapeutic potential for atopic pediatric AA. To evaluate the ability of dupilumab to regrow hair in pediatric AA patients. We conducted a single-center, retrospective, observational study to evaluate hair regrowth [using Severity of Alopecia Tool (SALT)] with dupilumab in 20 children with both AD and AA (age range 5-16 years, mean 10.8 years; baseline SALT range 3-100, mean 54.4). Patient demographics, atopic history, IgE and SALT scores were collected at 12wk follow-up visits, up to > 72wks, to evaluate hair regrowth. Spearman correlations with clinical data were performed. Patients showed clinical improvement over the follow-up period (range 24 to > 72wks, mean 67.6wks) with significant mean(± SD) reduction in SALT at 48wks versus baseline [20.4(± 35.1) vs 54.4(± 37.6), respectively; p < 0.01] and continued improvement up to > 72wks [2.2(± 4.9), p < 0.01]. Baseline SALT positively correlated with disease duration (r = 0.54, p < 0.01), and negatively correlated with improvement in SALT at weeks 24, 36, and 48 (|r|≥ 0.65, p < 0.01 for all comparisons). Baseline IgE positively correlated with improvement in SALT at week 36 (r > 0.60, p < 0.05). Dupilumab was well-tolerated, with no new safety concerns. These real-world data support the utility of dupilumab to safely treat pediatric AA patients, corroborating the role of Th2 skewing in children with AA and associated atopy, warranting larger clinical trials.

Electrical neuromodulation for the treatment of chronic pain: derivation of the intrinsic barriers, outcomes and considerations of the sustainability of implantable spinal cord stimulation therapies.

INTRODUCTION: For over 60 years, spinal cord stimulation has endured as a therapy through innovation and novel developments. Current practice of neuromodulation requires proper patient selection, risk mitigation and use of innovation. However, there are tangible and intangible challenges in physiology, clinical science and within society. AREAS COVERED: We provide a narrative discussion regarding novel topics in the field especially over the last decade. We highlight the challenges in the patient care setting including selection, as well as economic and socioeconomic challenges. Physician training challenges in neuromodulation is explored as well as other factors related to the use of neuromodulation such as novel indications and economics. We also discuss the concepts of technology and healthcare data. EXPERT OPINION: Patient safety and durable outcomes are the mainstay goal for neuromodulation. Substantial work is needed to assimilate data for larger and more relevant studies reflecting a population. Big data and global interconnectivity efforts provide substantial opportunity to reinvent our scientific approach, data analysis and its management to maximize outcomes and minimize risk. As improvements in data analysis become the standard of innovation and physician training meets demand, we expect to see an expansion of novel indications and its use in broader cohorts.

ProteinFlow: An advanced framework for feature engineering in protein data analysis.

In the burgeoning field of proteins, the effective analysis of intricate protein data remains a formidable challenge, necessitating advanced computational tools for data processing, feature extraction, and interpretation. This study introduces ProteinFlow, an innovative framework designed to revolutionize feature engineering in protein data analysis. ProteinFlow stands out by offering enhanced efficiency in data collection and preprocessing, along with advanced capabilities in feature extraction, directly addressing the complexities inherent in multidimensional protein data sets. Through a comparative analysis, ProteinFlow demonstrated a significant improvement over traditional methods, notably reducing data preprocessing time and expanding the scope of biologically significant features identified. The framework's parallel data processing strategy and advanced algorithms ensure not only rapid data handling but also the extraction of comprehensive, meaningful insights from protein sequences, structures, and interactions. Furthermore, ProteinFlow exhibits remarkable scalability, adeptly managing large-scale data sets without compromising performance, a crucial attribute in the era of big data.

UK Stakeholder Perspectives on Surrogate Endpoints in Cancer, and the Potential for UK Real-World Datasets to Validate Their Use in Decision-Making.

Duration of overall survival in patients with cancer has lengthened due to earlier detection and improved treatments. However, these improvements have created challenges in assessing the impact of newer treatments, particularly those used early in the treatment pathway. As overall survival remains most decision-makers' preferred primary endpoint, therapeutic innovations may take a long time to be introduced into clinical practice. Moreover, it is difficult to extrapolate findings to heterogeneous populations and address the concerns of patients wishing to evaluate everyday quality and extension of life. There is growing interest in the use of surrogate or interim endpoints to demonstrate robust treatment effects sooner than is possible with measurement of overall survival. It is hoped that they could speed up patients' access to new drugs, combinations, and sequences, and inform treatment decision-making. However, while surrogate endpoints have been used by regulators for drug approvals, this has occurred on a case-by-case basis. Evidence standards are yet to be clearly defined for acceptability in health technology appraisals or to shape clinical practice. This article considers the relevance of the use of surrogate endpoints in cancer in the UK context, and explores whether collection and analysis of real-world UK data and evidence might contribute to validation.

Development of Promising Interventions to Improve Human Papillomavirus Vaccination in a School-Based Program in Quebec, Canada: Results From a Formative Evaluation Using a Mixed Methods Design.

BACKGROUND: Despite the availability of school-based human papillomavirus (HPV) vaccination programs, disparities in vaccine coverage persist. Barriers to HPV vaccine acceptance and uptake include parental attitudes, knowledge, beliefs, and system-level barriers. A total of 3 interventions were developed to address these barriers: an in-person presentation by school nurses, an email reminder with a web-based information and decision aid tool, and a telephone reminder using motivational interviewing (MI) techniques. OBJECTIVE: Here we report on the development and formative evaluation of interventions to improve HPV vaccine acceptance and uptake among grade 4 students' parents in Quebec, Canada. METHODS: In the summer of 2019, we conducted a formative evaluation of the interventions to assess the interventions' relevance, content, and format and to identify any unmet needs. We conducted 3 focus group discussions with parents of grade 3 students and nurses. Interviews were recorded, transcribed, and analyzed for thematic content using NVivo software (Lumivero). Nurses received training on MI techniques and we evaluated the effect on nurses' knowledge and skills using a pre-post questionnaire. Descriptive quantitative analyses were carried out on data from questionnaires relating to the training. Comparisons were made using the proportions of the results. Finally, we developed a patient decision aid using an iterative, user-centered design process. The iterative refinement process involved feedback from parents, nurses, and experts to ensure the tool's relevance and effectiveness. The evaluation protocol and data collection tools were approved by the CHU (Centre Hospitalier Universitaire) de Québec Research Ethics Committee (MP-20-2019-4655, May 16, 2019). RESULTS: The data collection was conducted from April 2019 to March 2021. Following feedback (n=28) from the 3 focus group discussions in June 2019, several changes were made to the in-person presentation intervention. Experts (n=27) and school nurses (n=29) recruited for the project appreciated the visual and simplified information on vaccination in it. The results of the MI training for school nurses conducted in August 2019 demonstrated an increase in the skills and knowledge of nurses (n=29). School nurses who took the web-based course (n=24) filled out a pretest and posttest questionnaire to evaluate their learning. The rating increased by 19% between the pretest and posttest questionnaires. Several changes were made between the first draft of the web-based decision-aid tool and the final version during the summer of 2019 after an expert consultation of experts (n=3), focus group participants (n=28), and parents in the iterative process (n=5). More information about HPV and vaccines was added, and users could click if more detail is desired. CONCLUSIONS: We developed and pilot-tested 3 interventions using an iterative process. The interventions were perceived as potentially effective to increase parents' knowledge and positive attitudes toward HPV vaccination, and ultimately, vaccine acceptance. Future research will assess the effectiveness of these interventions on a larger scale.

Investigating Patient Use and Experience of Online Appointment Booking in Primary Care: Mixed Methods Study.

BACKGROUND: Online appointment booking is a commonly used tool in several industries. There is limited evidence about the benefits and challenges of using online appointment booking in health care settings. Potential benefits include convenience and the ability to track appointments, although some groups of patients may find it harder to engage with online appointment booking. We sought to understand how patients in England used and experienced online appointment booking. OBJECTIVE: This study aims to describe and compare the characteristics of patients in relation to their use of online appointment booking in general practice and investigate patients' views regarding online appointment booking arrangements. METHODS: This was a mixed methods study set in English general practice comprising a retrospective analysis of the General Practice Patient Survey (GPPS) and semistructured interviews with patients. Data used in the retrospective analysis comprised responses to the 2018 and 2019 GPPS analyzed using mixed-effects logistic regression. Semistructured interviews with purposively sampled patients from 11 general practices in England explored experiences of and views on online appointment booking. Framework analysis was used to allow for comparison with the findings of the retrospective analysis. RESULTS: The retrospective analysis included 1,327,693 GPPS responders (2018-2019 combined). We conducted 43 interviews with patients with a variety of experiences and awareness of online appointment booking; of these 43 patients, 6 (14%) were from ethnic minority groups. In the retrospective analysis, more patients were aware that online appointment booking was available (581,224/1,288,341, 45.11%) than had experience using it (203,184/1,301,694, 15.61%). There were deprivation gradients for awareness and use and a substantial decline in both awareness and use in patients aged >75 years. For interview participants, age and life stage were factors influencing experiences and perceptions, working patients valued convenience, and older patients preferred to use the telephone. Patients with long-term conditions were more aware of (odds ratio [OR] 1.43, 95% CI 1.41-1.44) and more likely to use (OR 1.65, 95% CI 1.63-1.67) online appointment booking. Interview participants with long-term conditions described online appointment booking as useful for routine nonurgent appointments. Patients in deprived areas were clustered in practices with low awareness and use of online appointment booking among GPPS respondents (OR for use 0.65, 95% CI 0.64-0.67). Other key findings included the influence of the availability of appointments online and differences in the registration process for accessing online booking. CONCLUSIONS: Whether and how patients engage with online appointment booking is influenced by the practice with which they are registered, whether they live with long-term conditions, and their deprivation status. These factors should be considered in designing and implementing online appointment booking and have implications for patient engagement with the wider range of online services offered in general practice.

A novel technology for harmonizing and analyzing cancer data. Observations from integrating health connect in Newfoundland and Labrador, Canada.

Objective: This article aims to describe the implementation of a new health information technology system called Health Connect that is harmonizing cancer data in the Canadian province of Newfoundland and Labrador; explain high-level technical details of this technology; provide concrete examples of how this technology is helping to improve cancer care in the province, and to discuss its future expansion and implications. Methods: We give a technical description of the Health Connect architecture, how it integrated numerous data sources into a single, scalable health information system for cancer data and highlight its artificial intelligence and analytics capacity. Results: We illustrated two practical achievements of Health Connect. First, an analytical dashboard that was used to pinpoint variations in colon cancer screening uptake in small defined geographic regions of the province; and second, a natural language processing algorithm that provided AI-assisted decision support in interpreting appropriate follow-up action based on assessments of breast mammography reports. Conclusion: Health Connect is a cutting-edge, health systems solution for harmonizing cancer screening data for practical decision-making. The long term goal is to integrate all cancer care data holdings into Health Connect to build a comprehensive health information system for cancer care in the province.

Machine Learning Methods to Estimate Individualized Treatment Effects for Use in Health Technology Assessment.

BACKGROUND: Recent developments in causal inference and machine learning (ML) allow for the estimation of individualized treatment effects (ITEs), which reveal whether treatment effectiveness varies according to patients' observed covariates. ITEs can be used to stratify health policy decisions according to individual characteristics and potentially achieve greater population health. Little is known about the appropriateness of available ML methods for use in health technology assessment. METHODS: In this scoping review, we evaluate ML methods available for estimating ITEs, aiming to help practitioners assess their suitability in health technology assessment. We present a taxonomy of ML approaches, categorized by key challenges in health technology assessment using observational data, including handling time-varying confounding and time-to event data and quantifying uncertainty. RESULTS: We found a wide range of algorithms for simpler settings with baseline confounding and continuous or binary outcomes. Not many ML algorithms can handle time-varying or unobserved confounding, and at the time of writing, no ML algorithm was capable of estimating ITEs for time-to-event outcomes while accounting for time-varying confounding. Many of the ML algorithms that estimate ITEs in longitudinal settings do not formally quantify uncertainty around the point estimates. LIMITATIONS: This scoping review may not cover all relevant ML methods and algorithms as they are continuously evolving. CONCLUSIONS: Existing ML methods available for ITE estimation are limited in handling important challenges posed by observational data when used for cost-effectiveness analysis, such as time-to-event outcomes, time-varying and hidden confounding, or the need to estimate sampling uncertainty around the estimates. IMPLICATIONS: ML methods are promising but need further development before they can be used to estimate ITEs for health technology assessments. HIGHLIGHTS: Estimating individualized treatment effects (ITEs) using observational data and machine learning (ML) can support personalized treatment advice and help deliver more customized information on the effectiveness and cost-effectiveness of health technologies.ML methods for ITE estimation are mostly designed for handling confounding at baseline but not time-varying or unobserved confounding. The few models that account for time-varying confounding are designed for continuous or binary outcomes, not time-to-event outcomes.Not all ML methods for estimating ITEs can quantify the uncertainty of their predictions.Future work on developing ML that addresses the concerns summarized in this review is needed before these methods can be widely used in clinical and health technology assessment-like decision making.