ObjectivesThe Indian Liver Patient Dataset (ILPD) is used extensively to create algorithms that predict liver disease. Given the existing research describing demographic inequities in liver disease ...diagnosis and management, these algorithms require scrutiny for potential biases. We address this overlooked issue by investigating ILPD models for sex bias.MethodsFollowing our literature review of ILPD papers, the models reported in existing studies are recreated and then interrogated for bias. We define four experiments, training on sex-unbalanced/balanced data, with and without feature selection. We build random forests (RFs), support vector machines (SVMs), Gaussian Naïve Bayes and logistic regression (LR) classifiers, running experiments 100 times, reporting average results with SD.ResultsWe reproduce published models achieving accuracies of >70% (LR 71.31% (2.37 SD) – SVM 79.40% (2.50 SD)) and demonstrate a previously unobserved performance disparity. Across all classifiers females suffer from a higher false negative rate (FNR). Presently, RF and LR classifiers are reported as the most effective models, yet in our experiments they demonstrate the greatest FNR disparity (RF; −21.02%; LR; −24.07%).DiscussionWe demonstrate a sex disparity that exists in published ILPD classifiers. In practice, the higher FNR for females would manifest as increased rates of missed diagnosis for female patients and a consequent lack of appropriate care. Our study demonstrates that evaluating biases in the initial stages of machine learning can provide insights into inequalities in current clinical practice, reveal pathophysiological differences between the male and females, and can mitigate the digitisation of inequalities into algorithmic systems.ConclusionOur findings are important to medical data scientists, clinicians and policy-makers involved in the implementation medical artificial intelligence systems. An awareness of the potential biases of these systems is essential in preventing the digital exacerbation of healthcare inequalities.
Natural language processing (NLP) has a significant role in advancing healthcare and has been found to be key in extracting structured information from radiology reports. Understanding recent ...developments in NLP application to radiology is of significance but recent reviews on this are limited. This study systematically assesses and quantifies recent literature in NLP applied to radiology reports.
We conduct an automated literature search yielding 4836 results using automated filtering, metadata enriching steps and citation search combined with manual review. Our analysis is based on 21 variables including radiology characteristics, NLP methodology, performance, study, and clinical application characteristics.
We present a comprehensive analysis of the 164 publications retrieved with publications in 2019 almost triple those in 2015. Each publication is categorised into one of 6 clinical application categories. Deep learning use increases in the period but conventional machine learning approaches are still prevalent. Deep learning remains challenged when data is scarce and there is little evidence of adoption into clinical practice. Despite 17% of studies reporting greater than 0.85 F1 scores, it is hard to comparatively evaluate these approaches given that most of them use different datasets. Only 14 studies made their data and 15 their code available with 10 externally validating results.
Automated understanding of clinical narratives of the radiology reports has the potential to enhance the healthcare process and we show that research in this field continues to grow. Reproducibility and explainability of models are important if the domain is to move applications into clinical use. More could be done to share code enabling validation of methods on different institutional data and to reduce heterogeneity in reporting of study properties allowing inter-study comparisons. Our results have significance for researchers in the field providing a systematic synthesis of existing work to build on, identify gaps, opportunities for collaboration and avoid duplication.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
In supervised learning model development, domain experts are often used to provide the class labels (annotations). Annotation inconsistencies commonly occur when even highly experienced clinical ...experts annotate the same phenomenon (e.g., medical image, diagnostics, or prognostic status), due to inherent expert bias, judgments, and slips, among other factors. While their existence is relatively well-known, the implications of such inconsistencies are largely understudied in real-world settings, when supervised learning is applied on such 'noisy' labelled data. To shed light on these issues, we conducted extensive experiments and analyses on three real-world Intensive Care Unit (ICU) datasets. Specifically, individual models were built from a common dataset, annotated independently by 11 Glasgow Queen Elizabeth University Hospital ICU consultants, and model performance estimates were compared through internal validation (Fleiss' κ = 0.383 i.e., fair agreement). Further, broad external validation (on both static and time series datasets) of these 11 classifiers was carried out on a HiRID external dataset, where the models' classifications were found to have low pairwise agreements (average Cohen's κ = 0.255 i.e., minimal agreement). Moreover, they tend to disagree more on making discharge decisions (Fleiss' κ = 0.174) than predicting mortality (Fleiss' κ = 0.267). Given these inconsistencies, further analyses were conducted to evaluate the current best practices in obtaining gold-standard models and determining consensus. The results suggest that: (a) there may not always be a "super expert" in acute clinical settings (using internal and external validation model performances as a proxy); and (b) standard consensus seeking (such as majority vote) consistently leads to suboptimal models. Further analysis, however, suggests that assessing annotation learnability and using only 'learnable' annotated datasets for determining consensus achieves optimal models in most cases.
Traditional health information systems are generally devised to support clinical data collection at the point of care. However, as the significance of the modern information economy expands in scope ...and permeates the healthcare domain, there is an increasing urgency for healthcare organisations to offer information systems that address the expectations of clinicians, researchers and the business intelligence community alike. Amongst other emergent requirements, the principal unmet need might be defined as the 3R principle (right data, right place, right time) to address deficiencies in organisational data flow while retaining the strict information governance policies that apply within the UK National Health Service (NHS). Here, we describe our work on creating and deploying a low cost structured and unstructured information retrieval and extraction architecture within King's College Hospital, the management of governance concerns and the associated use cases and cost saving opportunities that such components present.
To date, our CogStack architecture has processed over 300 million lines of clinical data, making it available for internal service improvement projects at King's College London. On generated data designed to simulate real world clinical text, our de-identification algorithm achieved up to 94% precision and up to 96% recall.
We describe a toolkit which we feel is of huge value to the UK (and beyond) healthcare community. It is the only open source, easily deployable solution designed for the UK healthcare environment, in a landscape populated by expensive proprietary systems. Solutions such as these provide a crucial foundation for the genomic revolution in medicine.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Clinical coding is the task of transforming medical information in a patient's health records into structured codes so that they can be used for statistical analysis. This is a cognitive and ...time-consuming task that follows a standard process in order to achieve a high level of consistency. Clinical coding could potentially be supported by an automated system to improve the efficiency and accuracy of the process. We introduce the idea of automated clinical coding and summarise its challenges from the perspective of Artificial Intelligence (AI) and Natural Language Processing (NLP), based on the literature, our project experience over the past two and half years (late 2019-early 2022), and discussions with clinical coding experts in Scotland and the UK. Our research reveals the gaps between the current deep learning-based approach applied to clinical coding and the need for explainability and consistency in real-world practice. Knowledge-based methods that represent and reason the standard, explainable process of a task may need to be incorporated into deep learning-based methods for clinical coding. Automated clinical coding is a promising task for AI, despite the technical and organisational challenges. Coders are needed to be involved in the development process. There is much to achieve to develop and deploy an AI-based automated system to support coding in the next five years and beyond.
Blockchain, as the application of distributed computing and data storage, point-to-point transmission, encryption algorithm, consensus mechanism, and other technologies, has become an important ...hotspot of data technology in banks, securities, and other Internet enterprises. In view of the problems of delay and large throughput in the current intelligent interconnection system of block chain, this paper proposes an optimization method of intelligent interconnection of block chain technology, so as to improve the performance of the system. In this paper, firstly, the development of intelligent interconnection and the related concepts of intelligent interconnection system optimization are put forward. Then, the related algorithms of blockchain are proposed, including the consensus algorithm of blockchain and the throughput delay algorithm of blockchain. Finally, in the experimental part, the blockchain technology is deeply studied, and the advantages and internal structure of blockchain are clearly analyzed. Then, by comparing the consensus of blockchain to optimize intelligent interconnected system and comparing blockchain technology with ordinary technology to optimize intelligent interconnected system, it is concluded that blockchain plays a positive role in optimizing intelligent interconnected system and also promotes the optimization of intelligent system. Therefore, we should introduce the related technologies of blockchain into the optimization of intelligent interconnection system, and its blockchain technology analysis can make up for the shortcomings of intelligent interconnection system. It also shows that blockchain technology is suitable for many information research fields and plays an irreplaceable role. The blockchain system consists of six different hierarchies, mainly network data layer and blockchain consensus layer. The data layer mainly encrypts the data related to blockchain. The consensus layer recognizes the main algorithms of blockchain, which can encapsulate the network information nodes of blockchain. Therefore, when blockchain carries out relevant information analysis algorithms, it mainly relies on blockchain consensus algorithm. It is beneficial to analyze the complex information of the system and promote the optimal development of blockchain.
Several common conditions have been widely recognised as risk factors for COVID-19 related death, but risks borne by people with rare diseases are largely unknown. Therefore, we aim to estimate the ...difference of risk for people with rare diseases comparing to the unaffected.
To estimate the correlation between rare diseases and COVID-19 related death, we performed a retrospective cohort study in Genomics England 100k Genomes participants, who tested positive for Sars-Cov-2 during the first wave (16-03-2020 until 31-July-2020) of COVID-19 pandemic in the UK (n = 283). COVID-19 related mortality rates were calculated in two groups: rare disease patients (n = 158) and unaffected relatives (n = 125). Fisher's exact test and logistic regression was used for univariable and multivariable analysis, respectively.
People with rare diseases had increased risk of COVID19-related deaths compared to the unaffected relatives (OR 95% CI = 3.47 1.21- 12.2). Although, the effect was insignificant after adjusting for age and number of comorbidities (OR 95% CI = 1.94 0.65-5.80). Neurology and neurodevelopmental diseases was significantly associated with COVID19-related death in both univariable (OR 95% CI = 4.07 1.61-10.38) and multivariable analysis (OR 95% CI = 4.22 1.60-11.08).
Our results showed that rare disease patients, especially ones affected by neurology and neurodevelopmental disorders, in the Genomics England cohort had increased risk of COVID-19 related death during the first wave of the pandemic in UK. The high risk is likely associated with rare diseases themselves, while we cannot rule out possible mediators due to the small sample size. We would like to raise the awareness that rare disease patients may face increased risk for COVID-19 related death. Proper considerations for rare disease patients should be taken when relevant policies (e.g., returning to workplace) are made.
Better phenotyping of routinely collected coded data would be useful for research and health improvement. For example, the precision of coded data for hemorrhagic stroke (intracerebral hemorrhage ICH ...and subarachnoid hemorrhage SAH) may be as poor as < 50%. This work aimed to investigate the feasibility and added value of automated methods applied to clinical radiology reports to improve stroke subtyping.
From a sub-population of 17,249 Scottish UK Biobank participants, we ascertained those with an incident stroke code in hospital, death record or primary care administrative data by September 2015, and ≥ 1 clinical brain scan report. We used a combination of natural language processing and clinical knowledge inference on brain scan reports to assign a stroke subtype (ischemic vs ICH vs SAH) for each participant and assessed performance by precision and recall at entity and patient levels.
Of 225 participants with an incident stroke code, 207 had a relevant brain scan report and were included in this study. Entity level precision and recall ranged from 78 to 100%. Automated methods showed precision and recall at patient level that were very good for ICH (both 89%), good for SAH (both 82%), but, as expected, lower for ischemic stroke (73%, and 64%, respectively), suggesting coded data remains the preferred method for identifying the latter stroke subtype.
Our automated method applied to radiology reports provides a feasible, scalable and accurate solution to improve disease subtyping when used in conjunction with administrative coded health data. Future research should validate these findings in a different population setting.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Atrial fibrillation (AF) is the most common arrhythmia and significantly increases stroke risk. This risk is effectively managed by oral anticoagulation. Recent studies using national registry data ...indicate increased use of anticoagulation resulting from changes in guidelines and the availability of newer drugs. The aim of this study is to develop and validate an open source risk scoring pipeline for free-text electronic health record data using natural language processing. AF patients discharged from 1st January 2011 to 1st October 2017 were identified from discharge summaries (N = 10,030, 64.6% male, average age 75.3 ± 12.3 years). A natural language processing pipeline was developed to identify risk factors in clinical text and calculate risk for ischaemic stroke (CHA2DS2-VASc) and bleeding (HAS-BLED). Scores were validated vs two independent experts for 40 patients. Automatic risk scores were in strong agreement with the two independent experts for CHA2DS2-VASc (average kappa 0.78 vs experts, compared to 0.85 between experts). Agreement was lower for HAS-BLED (average kappa 0.54 vs experts, compared to 0.74 between experts). In high-risk patients (CHA2DS2-VASc ≥2) OAC use has increased significantly over the last 7 years, driven by the availability of DOACs and the transitioning of patients from AP medication alone to OAC. Factors independently associated with OAC use included components of the CHA2DS2-VASc and HAS-BLED scores as well as discharging specialty and frailty. OAC use was highest in patients discharged under cardiology (69%). Electronic health record text can be used for automatic calculation of clinical risk scores at scale. Open source tools are available today for this task but require further validation. Analysis of routinely collected EHR data can replicate findings from large-scale curated registries.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Computational text phenotyping is the practice of identifying patients with certain disorders and traits from clinical notes. Rare diseases are challenging to be identified due to few cases available ...for machine learning and the need for data annotation from domain experts.
We propose a method using ontologies and weak supervision, with recent pre-trained contextual representations from Bi-directional Transformers (e.g. BERT). The ontology-driven framework includes two steps: (i) Text-to-UMLS, extracting phenotypes by contextually linking mentions to concepts in Unified Medical Language System (UMLS), with a Named Entity Recognition and Linking (NER+L) tool, SemEHR, and weak supervision with customised rules and contextual mention representation; (ii) UMLS-to-ORDO, matching UMLS concepts to rare diseases in Orphanet Rare Disease Ontology (ORDO). The weakly supervised approach is proposed to learn a phenotype confirmation model to improve Text-to-UMLS linking, without annotated data from domain experts. We evaluated the approach on three clinical datasets, MIMIC-III discharge summaries, MIMIC-III radiology reports, and NHS Tayside brain imaging reports from two institutions in the US and the UK, with annotations.
The improvements in the precision were pronounced (by over 30% to 50% absolute score for Text-to-UMLS linking), with almost no loss of recall compared to the existing NER+L tool, SemEHR. Results on radiology reports from MIMIC-III and NHS Tayside were consistent with the discharge summaries. The overall pipeline processing clinical notes can extract rare disease cases, mostly uncaptured in structured data (manually assigned ICD codes).
The study provides empirical evidence for the task by applying a weakly supervised NLP pipeline on clinical notes. The proposed weak supervised deep learning approach requires no human annotation except for validation and testing, by leveraging ontologies, NER+L tools, and contextual representations. The study also demonstrates that Natural Language Processing (NLP) can complement traditional ICD-based approaches to better estimate rare diseases in clinical notes. We discuss the usefulness and limitations of the weak supervision approach and propose directions for future studies.
Celotno besedilo
Dostopno za:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK