Studies in health technology and informatics最新文献

The identification of medications prescribed to patients in routinely collected health records is an important part of the identification of cohorts for surveillance and research. Preparations available for prescription can change frequently and this presents challenges to the maintenance of extensional or "flat lists" of medications, particularly in ongoing studies such as disease surveillance. The NHS publishes a Dictionary of Medicines and Devices weekly, listing almost all the medications available in the UK as an extension to the UK edition of SNOMED CT. We developed a method of creating intensional specifications of medications using specified active ingredients and the form of the medication. The specifications can be expressed using the SNOMED CT Expression Constraint Language, and can be used to form a library which may be used across multiple projects. We have developed intensional definitions of medication groups for all drugs likely to be used in primary care. We have shown that these can be shared as FHIR valuesets using the NHS Terminology Server. Here we show examples of expressions about medications used for neuropathic pain. We have created expressions which improve the specificity of the extraction by filtering on the form and number of ingredients.

Proximal humeral fractures are among the most common fractures seen in emergency departments. Accurately diagnosing and selecting the most appropriate treatment for these fractures can be challenging, and consultation with a senior orthopedic surgeon can be time-consuming for both the patient and the emergency unit. We developed a machine learning model for predicting the type of treatment based on injury radiographic images. The model distinguishes between nonoperative and operative treatment options, achieving an accuracy of 86% and an interobserver reliability (kappa) of 0.722 for test-dataset, which is more than the interobserver agreement between shoulder surgeons. This model has the potential to serve as a therapeutic decision support system for the practitioners in the emergency departments to expedite treatment decisions and to reduce patients' waiting time.

The COVID-19 pandemic has accelerated the adoption of telemedicine in healthcare. This study explores the feasibility of telemedicine for foot and ankle care in primary settings, using a mixed-methods approach with online questionnaires, focus groups, and interviews. Stakeholders, including patients, podiatrists, and senior healthcare managers, agreed on the need for a telemedicine service. Recommendations include creating evidence-based guidelines, providing professional training, and enhancing community education. The research highlights the necessity for structured telemedicine services, identifying gaps in existing pandemic responses and the need for further guidelines and training.

Pharmacogenetics (PGx) explores the influence of genetic variability on drug efficacy and tolerability. Synthetic Data Generation (SDG) has emerged as a promising alternative to the labor-intensive process of collecting real-world PGx data, which is required for high-qualitative prediction models. This study investigates the performance of two Generative Adversarial Network (GAN) models, CTGAN and CTAB-GAN+, in generating synthetic PGx data. The benchmarking is based on utility metrics (Hellinger distance and Random Forest accuracy) and ϵ-identifiability. Results demonstrate that synthetic data generated by CTAB-GAN+ can surpass the original dataset in terms of utility. For instance, CTAB-GAN+ achieves higher Random Forest accuracy compared to the original data, indicating better predictive performance. These improvements suggest that synthetic data not only capture the essential patterns of the original data but also enhance model generalization and prediction capabilities, providing a more robust training ground for machine learning models. Consequently, SDG offers a promising solution to address data scarcity and imbalance in pharmacogenetic research.

This scoping review explores mobile health (mHealth) technologies and their features affecting medication adherence in cancer patients. Among 11 selected studies, predominantly from the USA, mHealth tools, particularly smartphone apps, were examined for their features in managing cancer patient's medication adherence. The studies highlighted the importance of adherence in continuous cancer therapy, with mHealth tools offering reminders and interactive features, that aim to enhance patient engagement. However, the review identified research gaps, emphasizing the need for broader investigations into diverse mHealth tools beyond apps, including electronic capsules and smart pill dispensers. Additionally, it underscored the absence of information on costs, user input, integration with electronic health records, and data management. While acknowledging potential positive impacts on adherence, the review calls for more comprehensive research to substantiate these findings in clinical oncology.

Hospital at Home (HaH) is a model of care that provides hospital-level care in the patient's home, requiring a unique set of competencies and skills from both multidisciplinary care teams and informal caregivers. These skills are often different from those required in traditional hospital settings. The aim of this paper is to consolidate the information of HaH-related education and training to support the development of standardized curricula to ensure safe hospitalization at home. We compiled relevant information from the scientific literature on HaH approaches and studies and conducted a web search. Our results indicate that healthcare professionals are trained in short training sessions, covering specific skills needed in the HaH context. These skills comprise, among others, communication, medication safety, infection control, and wound care. Patients and their families receive training in recognizing symptoms of deterioration and self-care. Concrete guidelines or standardized training programs are still missing. Future research should thus focus on developing standardized HaH training protocols and programs for both staff and patients to ensure patient safety at home.

This research investigates the application of a hybrid Retrieval-Augmented Generation (RAG) and Generative Pre-trained Transformer (GPT) pipeline for extracting and categorizing substance use information from unstructured clinical notes. The aim is to enhance the accuracy and efficiency of identifying substance use mentions and determining their status in patient documentation. By integrating RAG to pre-filter and focus the input for GPT, the pipeline strategically narrows the scope of analysis to the most relevant text segments, thereby improving the precision and recall of the extraction. Utilizing the Medical Information Mart for Intensive Care III dataset, the performance of the pipeline was evaluated through manual verification, assessing various metrics including recall, precision, F1-score, and accuracy. The results demonstrated high precision rates (up to 0.99 for drug and alcohol mentions), and substantial recall (0.88 across all substances for status of the usage).

Data-driven technologies have improved the efficiency, reliability and effectiveness of healthcare services, but come with an increasing demand for data, which is challenging due to privacy-related constraints on sharing data in healthcare contexts. Synthetic data has recently gained popularity as potential solution, but in the flurry of current research it can be hard to oversee its potential. This paper proposes a novel taxonomy of synthetic data in healthcare to navigate the landscape in terms of three main varieties. Data Proportion comprises different ratios of synthetic data in a dataset and associated pros and cons. Data Modality refers to the different data formats amenable to synthesis and format-specific challenges. Data Transformation concerns improving specific aspects of a dataset like its utility or privacy with synthetic data. Our taxonomy aims to help researchers in the healthcare domain interested in synthetic data to grasp what types of datasets, data modalities, and transformations are possible with synthetic data, and where the challenges and overlaps between the varieties lie.

This study leverages the DCTPep database, a comprehensive repository of cancer therapy peptides, to explore the application of machine learning in accelerating cancer research. We applied Principal Component Analysis (PCA) and K-means clustering to categorize cancer therapy peptides based on their physicochemical properties. Our analysis identified three distinct clusters, each characterized by unique features such as sequence length, isoelectric point (pI), net charge, and mass. These findings provide valuable insights into the key properties that influence peptide efficacy, offering a foundation for the design of new therapeutic peptides. Future work will focus on experimental validation and the integration of additional data sources to refine the clustering and enhance the predictive power of the model, ultimately contributing to the development of more effective peptide-based cancer treatments.

We propose a deep learning method to model and generate synthetic aortic shapes based on representing shapes as the zero-level set of a neural signed distance field, conditioned by a family of trainable embedding vectors with encode the geometric features of each shape. The network is trained on a dataset of aortic root meshes reconstructed from CT images by making the neural field vanish on sampled surface points and enforcing its spatial gradient to have unit norm. Empirical results show that our model can represent aortic shapes with high fidelity. Moreover, by sampling from the learned embedding vectors, we can generate novel shapes that resemble real patient anatomies, which can be used for in-silico trials.