Methods of Information in Medicine最新文献

Assessing treatment response in patients with myeloproliferative neoplasms is difficult because data components exist in unstructured bone marrow pathology (hematopathology) reports, which require specialized, manual annotation, and interpretation. Although natural language processing (NLP) has been successfully implemented for the extraction of features from solid tumor reports, little is known about its application to hematopathology.An open-source NLP framework called Leo was implemented to parse document segments and extract concept phrases utilized for assessing responses in myeloproliferative neoplasms. A reference standard was generated through the manual review of hematopathology notes.Compared with a reference standard (n = 300 reports), our NLP method extracted features such as aspirate myeloblasts (F1 = 98%) and biopsy reticulin fibrosis (F1 = 93%) with high accuracy. However, other values, such as myeloblasts from the biopsy (F1 = 6%) and via flow cytometry (F1 = 8%), were affected by sparsity representative of reporting conventions. The four features with the highest clinical importance were extracted with F1 scores exceeding 90%. Whereas manual annotation of 300 reports required 30 hours of staff effort, automated NLP required 3.5 hours of runtime for 34,301 reports.To the best of our knowledge, this is among the first studies to demonstrate the application of NLP to hematopathology for clinical feature extraction. The approach may inform efforts at other institutions, and the code is available at https://github.com/wcmc-research-informatics/BmrExtractor.

Background:  Fibrotic lung disease is a progressive illness that causes scarring and ultimately respiratory failure, with irreversible damage by the time it is diagnosed on computed tomography imaging. Recent research postulates the role of the lung vasculature on the pathogenesis of the disease. With the recent development of high-resolution hierarchical phase-contrast tomography (HiP-CT), we have the potential to understand and detect changes in the lungs long before conventional imaging. However, to gain quantitative insight into vascular changes you first need to be able to segment the vessels before further downstream analysis can be conducted. Aside from this, HiP-CT generates large-volume, high-resolution data which is time-consuming and expensive to label.

Objectives:  This project aims to qualitatively assess the latest machine learning methods for vessel segmentation in HiP-CT data to enable label propagation as the first step for imaging biomarker discovery, with the goal to identify early-stage interstitial lung disease amenable to treatment, before fibrosis begins.

Methods:  Semisupervised learning (SSL) has become a growing method to tackle sparsely labeled datasets due to its leveraging of unlabeled data. In this study, we will compare two SSL methods; Seg PL, based on pseudo-labeling, and MisMatch, using consistency regularization against state-of-the-art supervised learning method, nnU-Net, on vessel segmentation in sparsely labeled lung HiP-CT data.

Results:  On initial experimentation, both MisMatch and SegPL showed promising performance on qualitative review. In comparison with supervised learning, both MisMatch and SegPL showed better out-of-distribution performance within the same sample (different vessel morphology and texture vessels), though supervised learning provided more consistent segmentations for well-represented labels in the limited annotations.

Conclusion:  Further quantitative research is required to better assess the generalizability of these findings, though they show promising first steps toward leveraging this novel data to tackle fibrotic lung disease.

Semantic interoperability among health information systems (HISs), in particular electronic health records (EHRs), is crucial for informed healthcare decisions and access to vital health data by the patient. However, inconsistent medication information and limited health data exchange contribute to medication errors worldwide. Although Sweden offers various solutions for health information exchange, there is a limitation in the exchange of medication orders and a lack of understanding the structure of medication orders among EHRs, highlighting the need for further exploration of the structure of medication orders.This study aims to develop a common information model of medication orders for EHRs to be used in the Swedish context.An explorative qualitative design study was conducted. Documents and reference models of how medication orders are structured were collected, and semi-structured interviews were conducted with five purposefully selected participants with insight into how medication orders are structured in EHRs in Sweden. Data were analyzed using information needs analysis, information structure analysis, and code systems, classifications, and terminology analysis.The following information areas were identified for a medication order: medication, medication indication, way of administration, medication order details, and dosage. These information areas were conceptualized into a Unified Modeling Language Class Diagram information model with defined classes, attributes, and data types. The resulting information model provides a representation of how medication orders are depicted in EHRs in Sweden and is aligned with existing national information models such as the National Medication List, while still providing additional information related to medication order details.The developed information model could potentially provide a national standardized model for medication orders, contributing to enhanced semantic interoperability and improving data exchange across various HISs. This could enhance data consistency, reducing the risk of medication errors and thereby improving patient safety.

Background:  The current gap between the availability of routine imaging data and its provisioning for medical research hinders the utilization of radiological information for secondary purposes. To address this, the German Medical Informatics Initiative (MII) has established frameworks for harmonizing and integrating clinical data across institutions, including the integration of imaging data into research repositories, which can be expanded to routine imaging data.

Objectives:  This project aims to address this gap by developing a large-scale data processing pipeline to extract, convert, and pseudonymize DICOM (Digital Imaging and Communications in Medicine) metadata into "ImagingStudy" Fast Healthcare Interoperability Resources (FHIR) and integrate them into research repositories for secondary use.

Methods:  The data processing pipeline was developed, implemented, and tested at the Data Integration Center of the University Hospital Erlangen. It leverages existing open-source solutions and integrates seamlessly into the hospital's research IT infrastructure. The pipeline automates the extraction, conversion, and pseudonymization processes, ensuring compliance with both local and MII data protection standards. A large-scale evaluation was conducted using the imaging studies acquired by two departments at University Hospital Erlangen within 1 year. Attributes such as modality, examined body region, laterality, and the number of series and instances were analyzed to assess the quality and availability of the metadata.

Results:  Once established, the pipeline processed a substantial dataset comprising over 150,000 DICOM studies within an operational period of 26 days. Data analysis revealed significant heterogeneity and incompleteness in certain attributes, particularly the DICOM tag "Body Part Examined." Despite these challenges, the pipeline successfully generated valid and standardized FHIR, providing a robust basis for future research.

Conclusion:  We demonstrated the setup and test of a large-scale end-to-end data processing pipeline that transforms DICOM imaging metadata directly from clinical routine into the Health Level 7-FHIR format, pseudonymizes the resources, and stores them in an FHIR server. We showcased that the derived FHIRs offer numerous research opportunities, for example, feasibility assessments within Bavarian and Germany-wide research infrastructures. Insights from this study highlight the need to extend the "ImagingStudy" FHIR with additional attributes and refine their use within the German MII.

Balancing artificial intelligence (AI) support with appropriate human oversight is challenging, with associated risks such as algorithm aversion and technology dominance. Research areas like eXplainable AI (XAI) and Frictional AI aim to address these challenges. Studies have shown that presenting XAI explanations as "juxtaposed evidence" supporting contrasting classifications, rather than just providing predictions, can be beneficial.This study aimed to design and compare multiple pipelines for generating juxtaposed evidence in the form of class activation maps (CAMs) that highlight areas of interest in a fracture detection task with X-ray images.We designed three pipelines to generate such evidence. The pipelines are based on a fracture detection task from 630 thoraco-lumbar X-ray images (48% of which contained fractures). The first, a single-model approach, uses an algorithm of the Grad-CAM family applied to a ResNeXt-50 network trained through transfer learning. The second, a dual-model approach, employs two networks-one optimized for sensitivity and the other for specificity-providing targeted explanations for positive and negative cases. The third, a generative approach, leverages autoencoders to create activation maps from feature tensors, extracted from the raw images. Each approach produced two versions of activation maps: AM3-as we termed it-which captures fine-grained, low-level features, and AM4, highlighting high-level, aggregated features. We conducted a validation study by comparing the generated maps with binary ground-truth masks derived from a consensus of four clinician annotators, identifying the actual locations of fractures in a subset of positive cases.HiResCAM proved to be the best performing Grad-CAM variant and was used in both the single- and dual-model strategies. The generative approach demonstrated the greatest overlap with the clinicians' assessments, indicating its ability to align with human expertise.The results highlight the potential of Judicial AI to enhance diagnostic decision-making and foster a synergistic collaboration between humans and AI.

Background:  Multidisciplinary tumor boards (MTBs) have been established in most countries to allow experts collaboratively determine the best treatment decisions for cancer patients. However, MTBs often face challenges such as case overload, which can compromise MTB decision quality. Clinical decision support systems (CDSSs) have been introduced to assist clinicians in this process. Despite their potential, CDSSs are still underutilized in routine practice. The emergence of large language models (LLMs), such as ChatGPT, offers new opportunities to improve the efficiency and usability of traditional CDSSs.

Objectives:  OncoDoc2 is a guideline-based CDSS developed using a documentary approach and applied to breast cancer management. This study aims to evaluate the potential of LLMs, used as question-answering (QA) systems, to improve the usability of OncoDoc2 across different prompt engineering techniques (PETs).

Methods:  Data extracted from breast cancer patient summaries (BCPSs), together with questions formulated by OncoDoc2, were used to create prompts for various LLMs, and several PETs were designed and tested. Using a sample of 200 randomized BCPSs, LLMs and PETs were initially compared with regard to their responses to OncoDoc2 questions using classic metrics (accuracy, precision, recall, and F1 score). Best performing LLMs and PETs were further assessed by comparing the therapeutic recommendations generated by OncoDoc2, based on LLM inputs, to those provided by MTB clinicians using OncoDoc2. Finally, the best performing method was validated using a new sample of 30 randomized BCPSs.

Results:  The combination of Mistral and OpenChat models under the enhanced Zero-Shot PET showed the best performance as a question-answering system. This approach gets a precision of 60.16%, a recall of 54.18%, an F1 score of 56.59%, and an accuracy of 75.57% on the validation set of 30 BCPSs. However, this approach yielded poor results as a CDSS, with only 16.67% of the recommendations generated by OncoDoc2 based on LLM inputs matching the gold standard.

Conclusion:  All the criteria in the OncoDoc2 decision tree are crucial for capturing the uniqueness of each patient. Any deviation from a criterion alters the recommendations generated. Despite achieving a good accuracy rate of 75.57%, LLMs still face challenges in reliably understanding complex medical contexts and be effective as CDSSs.

Background:  The aim of the national health care quality registers is to monitor, assess, and improve the quality of care. The information utilized in quality registers must be of high quality to ensure that the information produced by the registers is reliable and useful. In Finland, one of the key sources of information for the quality registers is the national Kanta services.

Objectives:  The objective of the study was to increase understanding of the significance of information quality for the secondary use of the information in the national health care quality registers and to provide information on whether the information quality of the national Kanta services supports the information needs of the national quality registers, and how information quality should be developed.

Methods:  The research data were collected by interviewing six experts responsible for national health care quality registers, and it was analyzed using theory-driven qualitative content analysis based on the DeLone and McLean model.

Results:  Based on the results, the relevance of the information in the Kanta services met the information needs of the national quality registers. However, due to the limited amount of structured information and deficiencies in the completeness of the information, relevant information could not be fully utilized. Deficiencies in information quality posed challenges in information retrieval and hindered drawing conclusions in reporting. Challenges in information quality did not diminish the intention to use the information when information was considered relevant. Solutions to improve information quality included structuring, development of documentation practices, patient information systems and quality assurance, as well as collaboration among stakeholders.

Conclusion:  The Kanta services' information is relevant for the national health care quality registers, but developing the quality of the information, especially in terms of structures and completeness, is the key to fully enabling the secondary use of this information.

In the operating theater, a large collection of data are collected at each surgical visit. Some of these data are patient information, some is related to resource management, which is linked to hospital finances. Poor quality data lead to poor decisions, impacting patient safety and the continuity of care.The study aimed at evaluating the completeness of the data documented within surgical operations. Based on the results, the goal is to improve data quality and to identify improvement ideas of data management.The study was a quantitative evaluation of 33,684 surgical visits, focusing on data omissions. The organization identified 58 operating room data variables related to visits, procedures, resources, and personnel. Data completeness was evaluated for 36 variables, excluding 47 visits that were missing the "Complete" flag. Data preprocessing was done using Python and Pandas, with pseudonymization of personnel names. Data were analyzed using the R programming language. Data omissions were coded as "1" for missing values and "0" for others. Summary variables were created to indicate the number of personnel and procedure and data omissions per visit.The average completeness of the operating room data was 98%, which is considered excellent. However, seven variables-the start and end date and time of anesthesia, the type of treatment, personnel group, and assistant information-had completeness below the 95% target level. A total of 34% of the surgical visits contained at least one data omission. In the yearly comparison, the completeness values of variables were statistically significantly higher in 2022 compared with 2023.By ensuring existing quality assurance practices, verifying internal data maintenance and verifying and standardizing documenting practices the organization can achieve net benefits through improved data completeness, thus enhancing patient records, financial information, and management. Improved data quality will also benefit national and international registers.

Objective: In this study, we propose a novel framework that utilizes deep learning and attention mechanisms to predict the radiographic progression of patellofemoral osteoarthritis (PFOA) over a period of 7 years.

Material and methods: This study included subjects (1,832 subjects, 3,276 knees) from the baseline of the Multicenter Osteoarthritis Study (MOST). Patellofemoral joint regions of interest were identified using an automated landmark detection tool (BoneFinder) on lateral knee X-rays. An end-to-end deep learning method was developed for predicting PFOA progression based on imaging data in a five-fold cross-validation setting. To evaluate the performance of the models, a set of baselines based on known risk factors were developed and analyzed using gradient boosting machine (GBM). Risk factors included age, sex, body mass index, and Western Ontario and McMaster Universities Arthritis Index score, and the radiographic osteoarthritis stage of the tibiofemoral joint (Kellgren and Lawrence [KL] score). Finally, to increase predictive power, we trained an ensemble model using both imaging and clinical data.

Results: Among the individual models, the performance of our deep convolutional neural network attention model achieved the best performance with an area under the receiver operating characteristic curve (AUC) of 0.856 and average precision (AP) of 0.431, slightly outperforming the deep learning approach without attention (AUC = 0.832, AP = 0.4) and the best performing reference GBM model (AUC = 0.767, AP = 0.334). The inclusion of imaging data and clinical variables in an ensemble model allowed statistically more powerful prediction of PFOA progression (AUC = 0.865, AP = 0.447), although the clinical significance of this minor performance gain remains unknown. The spatial attention module improved the predictive performance of the backbone model, and the visual interpretation of attention maps focused on the joint space and the regions where osteophytes typically occur.

Conclusion: This study demonstrated the potential of machine learning models to predict the progression of PFOA using imaging and clinical variables. These models could be used to identify patients who are at high risk of progression and prioritize them for new treatments. However, even though the accuracy of the models were excellent in this study using the MOST dataset, they should be still validated using external patient cohorts in the future.