Search

Abstract Studies have shown that colorectal cancer prognosis can be predicted by deep learning-based analysis of histological tissue sections of the primary tumor. So far, this has been achieved using a binary prediction. Survival curves might contain more detailed information and thus enable a more fine-grained risk prediction. Therefore, we established survival curve-based CRC survival predictors and benchmarked them against standard binary survival predictors, comparing their performance extensively on the clinical high and low risk subsets of one internal and three external cohorts. Survival curve-based risk prediction achieved a very similar risk stratification to binary risk prediction for this task. Exchanging other components of the pipeline, namely input tissue and feature extractor, had largely identical effects on model performance independently of the type of risk prediction. An ensemble of all survival curve-based models exhibited a more robust performance, as did a similar ensemble based on binary risk prediction. Patients could be further stratified within clinical risk groups. However, performance still varied across cohorts, indicating limited generalization of all investigated image analysis pipelines, whereas models using clinical data performed robustly on all cohorts.

Abstract Many artificial intelligence models have been developed to predict clinically relevant biomarkers for colorectal cancer (CRC), including microsatellite instability (MSI). However, existing deep learning networks require large training datasets, which are often hard to obtain. In this study, based on the latest Hierarchical Vision Transformer using Shifted Windows (Swin Transformer [Swin‐T]), we developed an efficient workflow to predict biomarkers in CRC (MSI, hypermutation, chromosomal instability, CpG island methylator phenotype, and BRAF and TP53 mutation) that required relatively small datasets. Our Swin‐T workflow substantially achieved the state‐of‐the‐art (SOTA) predictive performance in an intra‐study cross‐validation experiment on the Cancer Genome Atlas colon and rectal cancer dataset (TCGA‐CRC‐DX). It also demonstrated excellent generalizability in cross‐study external validation and delivered a SOTA area under the receiver operating characteristic curve (AUROC) of 0.90 for MSI, using the Molecular and Cellular Oncology dataset for training (N = 1,065) and the TCGA‐CRC‐DX (N = 462) for testing. A similar performance (AUROC = 0.91) was reported in a recent study, using ~8,000 training samples (ResNet18) on the same testing dataset. Swin‐T was extremely efficient when using small training datasets and exhibited robust predictive performance with 200–500 training samples. Our findings indicate that Swin‐T could be 5–10 times more efficient than existing algorithms for MSI prediction based on ResNet18 and ShuffleNet. Furthermore, the Swin‐T models demonstrated their capability in accurately predicting MSI and BRAF mutation status, which could exclude and therefore reduce samples before subsequent standard testing in a cascading diagnostic workflow, in turn reducing turnaround time and costs.

BackgroundElectronic health records (EHRs) in unstructured formats are valuable sources of information for research in both the clinical and biomedical domains. However, before such records can be used for research purposes, sensitive health information (SHI) must be removed in several cases to protect patient privacy. Rule-based and machine learning–based methods have been shown to be effective in deidentification. However, very few studies investigated the combination of transformer-based language models and rules. ObjectiveThe objective of this study is to develop a hybrid deidentification pipeline for Australian EHR text notes using rules and transformers. The study also aims to investigate the impact of pretrained word embedding and transformer-based language models. MethodsIn this study, we present a hybrid deidentification pipeline called OpenDeID, which is developed using an Australian multicenter EHR-based corpus called OpenDeID Corpus. The OpenDeID corpus consists of 2100 pathology reports with 38,414 SHI entities from 1833 patients. The OpenDeID pipeline incorporates a hybrid approach of associative rules, supervised deep learning, and pretrained language models. ResultsThe OpenDeID achieved a best F1-score of 0.9659 by fine-tuning the Discharge Summary BioBERT model and incorporating various preprocessing and postprocessing rules. The OpenDeID pipeline has been deployed at a large tertiary teaching hospital and has processed over 8000 unstructured EHR text notes in real time. ConclusionsThe OpenDeID pipeline is a hybrid deidentification pipeline to deidentify SHI entities in unstructured EHR text notes. The pipeline has been evaluated on a large multicenter corpus. External validation will be undertaken as part of our future work to evaluate the effectiveness of the OpenDeID pipeline.

Abstract Computational pathology is a rapidly expanding area for research due to the current global transformation of histopathology through the adoption of digital workflows. Survival prediction of breast cancer patients is an important task that currently depends on histopathology assessment of cancer morphological features, immunohistochemical biomarker expression and patient clinical findings. To facilitate the manual process of survival risk prediction, we developed a computational pathology framework for survival prediction using digitally scanned haematoxylin and eosin-stained tissue microarray images of clinically aggressive triple negative breast cancer. Our results show that the model can produce an average concordance index of 0.616. Our model predictions are analysed for independent prognostic significance in univariate analysis (hazard ratio = 3.12, 95% confidence interval [1.69,5.75], p < 0.005) and multivariate analysis using clinicopathological data (hazard ratio = 2.68, 95% confidence interval [1.44,4.99], p < 0.005). Through qualitative analysis of heatmaps generated from our model, an expert pathologist is able to associate tissue features highlighted in the attention heatmaps of high-risk predictions with morphological features associated with more aggressive behaviour such as low levels of tumour infiltrating lymphocytes, stroma rich tissues and high-grade invasive carcinoma, providing explainability of our method for triple negative breast cancer.

Abstract Background We investigated whether we could use influenza data to develop prediction models for COVID-19 to increase the speed at which prediction models can reliably be developed and validated early in a pandemic. We developed COVID-19 Estimated Risk (COVER) scores that quantify a patient’s risk of hospital admission with pneumonia (COVER-H), hospitalization with pneumonia requiring intensive services or death (COVER-I), or fatality (COVER-F) in the 30-days following COVID-19 diagnosis using historical data from patients with influenza or flu-like symptoms and tested this in COVID-19 patients. Methods We analyzed a federated network of electronic medical records and administrative claims data from 14 data sources and 6 countries containing data collected on or before 4/27/2020. We used a 2-step process to develop 3 scores using historical data from patients with influenza or flu-like symptoms any time prior to 2020. The first step was to create a data-driven model using LASSO regularized logistic regression, the covariates of which were used to develop aggregate covariates for the second step where the COVER scores were developed using a smaller set of features. These 3 COVER scores were then externally validated on patients with 1) influenza or flu-like symptoms and 2) confirmed or suspected COVID-19 diagnosis across 5 databases from South Korea, Spain, and the United States. Outcomes included i) hospitalization with pneumonia, ii) hospitalization with pneumonia requiring intensive services or death, and iii) death in the 30 days after index date. Results Overall, 44,507 COVID-19 patients were included for model validation. We identified 7 predictors (history of cancer, chronic obstructive pulmonary disease, diabetes, heart disease, hypertension, hyperlipidemia, kidney disease) which combined with age and sex discriminated which patients would experience any of our three outcomes. The models achieved good performance in influenza and COVID-19 cohorts. For COVID-19 the AUC ranges were, COVER-H: 0.69–0.81, COVER-I: 0.73–0.91, and COVER-F: 0.72–0.90. Calibration varied across the validations with some of the COVID-19 validations being less well calibrated than the influenza validations. Conclusions This research demonstrated the utility of using a proxy disease to develop a prediction model. The 3 COVER models with 9-predictors that were developed using influenza data perform well for COVID-19 patients for predicting hospitalization, intensive services, and fatality. The scores showed good discriminatory performance which transferred well to the COVID-19 population. There was some miscalibration in the COVID-19 validations, which is potentially due to the difference in symptom severity between the two diseases. A possible solution for this is to recalibrate the models in each location before use.

Abstract For research purposes, protected health information is often redacted from unstructured electronic health records to preserve patient privacy and confidentiality. The OpenDeID corpus is designed to assist development of automatic methods to redact sensitive information from unstructured electronic health records. We retrieved 4548 unstructured surgical pathology reports from four urban Australian hospitals. The corpus was developed by two annotators under three different experimental settings. The quality of the annotations was evaluated for each setting. Specifically, we employed serial annotations, parallel annotations, and pre-annotations. Our results suggest that the pre-annotations approach is not reliable in terms of quality when compared to the serial annotations but can drastically reduce annotation time. The OpenDeID corpus comprises 2,100 pathology reports from 1,833 cancer patients with an average of 737.49 tokens and 7.35 protected health information entities annotated per report. The overall inter annotator agreement and deviation scores are 0.9464 and 0.9726, respectively. Realistic surrogates are also generated to make the corpus suitable for distribution to other researchers.

Abstract Consumer wearables and sensors are a rich source of data about patients’ daily disease and symptom burden, particularly in the case of movement disorders like Parkinson’s disease (PD). However, interpreting these complex data into so-called digital biomarkers requires complicated analytical approaches, and validating these biomarkers requires sufficient data and unbiased evaluation methods. Here we describe the use of crowdsourcing to specifically evaluate and benchmark features derived from accelerometer and gyroscope data in two different datasets to predict the presence of PD and severity of three PD symptoms: tremor, dyskinesia, and bradykinesia. Forty teams from around the world submitted features, and achieved drastically improved predictive performance for PD status (best AUROC = 0.87), as well as tremor- (best AUPR = 0.75), dyskinesia- (best AUPR = 0.48) and bradykinesia-severity (best AUPR = 0.95).

Background: Chest pain misinterpretation is the leading cause of pre-hospital delay in acute coronary syndrome (ACS). This study aims to identify and differentiate the chest pain characteristics associated with ACS. Methods: A total of 164 patients with a primary complaint of chest pain in the ER were included in the study. ACS diagnosis was made by a cardiologist based on the WHO criteria, and the patients were interviewed 48 hours after their admission. Furthermore, every question was analysed using the crosstabs method to obtain the odds ratio, and logistic regression analysis was applied to identify the model of focused questions on chest pain assessment. Results: Among the samples, 50% of them had an ACS. Four questions fitted the final model of ACS chest pain focused questions: 1) Did the chest pain occur at the left/middle chest? 2) Did the chest pain radiate to the back? 3) Was the chest pain provoked by activity and relieved by rest? 4) Was the chest pain provoked by food ingestion, positional changes, or breathing? This model has 92.7% sensitivity, 84.1% specificity, 85% positive predictive value (PPV), 86% negative predictive value (NPV), and 86% accuracy. After adjusting for gender and diabetes mellitus (DM), the final model has a significant increase in Nagelkerke R-square to 0.737 and Hosmer and Lemeshow test statistic of 0.639. Conclusion: Focused questions on 1) left/middle chest pain, 2) retrosternal chest pain, 3) exertional chest pain that is relieved by rest, and 4) chest pain from food ingestion, positional changes, or breathing triggering can be used to rule out ACS with high predictive value. The findings from this study can be used in health promotion materials and campaigns to improve public awareness regarding ACS symptoms. Additionally, digital health interventions to triage patients’ suffering with chest pain can also be developed.

Background and Objectives: Taiwan is among the nations with the highest rates of Type 2 Diabetes Mellitus (T2DM) and Hypertension (HTN). As more cases are reported each year, there is a rise in hospital admissions for people seeking medical attention. This creates a burden on hospitals and affects the overall management and administration of the hospitals. Hence, this study aimed to develop a machine learning (ML) model to predict the Length of Stay (LoS) and mortality among T2DM and HTN inpatients. Materials and Methods: Using Taiwan’s National Health Insurance Research Database (NHIRD), this cohort study consisted of 58,618 patients, where 25,868 had T2DM, 32,750 had HTN, and 6419 had both T2DM and HTN. We analyzed the data with different machine learning models for the prediction of LoS and mortality. The evaluation was done by plotting descriptive statistical graphs, feature importance, precision-recall curve, accuracy plots, and AUC. The training and testing data were set at a ratio of 8:2 before applying ML algorithms. Results: XGBoost showed the best performance in predicting LoS (R2 0.633; RMSE 0.386; MAE 0.123), and RF resulted in a slightly lower performance (R2 0.591; RMSE 0.401; MAE 0.027). Logistic Regression (LoR) performed the best in predicting mortality (CV Score 0.9779; Test Score 0.9728; Precision 0.9432; Recall 0.9786; AUC 0.97 and AUPR 0.93), closely followed by Ridge Classifier (CV Score 0.9736; Test Score 0.9692; Precision 0.9312; Recall 0.9463; AUC 0.94 and AUPR 0.89). Conclusions: We developed a robust prediction model for LoS and mortality of T2DM and HTN inpatients. Linear Regression showed the best performance for LoS, and Logistic Regression performed the best in predicting mortality. The results showed that ML algorithms can not only help healthcare professionals in data-driven decision-making but can also facilitate early intervention and resource planning.

Background and Objectives: Statins have been extensively utilised in atherosclerotic cardiovascular disease (ASCVD) prevention and can inhibit inflammation. However, the association between statin therapy, subclinical inflammation and associated health outcomes is poorly understood in the primary care setting. Materials and Methods: Primary care electronic health record (EHR) data from the electronic Practice-Based Research Network (ePBRN) from 2012–2019 was used to assess statin usage and adherence in South-Western Sydney (SWS), Australia. Independent determinants of elevated C-reactive protein (CRP) were determined. The relationship between baseline CRP levels and hospitalisation rates at 12 months was investigated. Results: The prevalence of lipid-lowering medications was 14.0% in all adults and 44.6% in the elderly (≥65 years). The prevalence increased from 2012 to 2019 despite a drop in statin use between 2013–2015. A total of 55% of individuals had good adherence (>80%). Hydrophilic statin use and higher intensity statin therapy were associated with elevated CRP levels. However, elevated CRP levels were not associated with all-cause or ASCVD hospitalisations after adjusting for confounders. Conclusions: The prevalence and adherence patterns associated with lipid-lowering medications highlighted the elevated ASCVD-related burden in the SWS population, especially when compared with the Australian general population. Patients in SWS may benefit from enhanced screening protocols, targeted health literacy and promotion campaigns, and timely incorporation of evidence into ASCVD clinical guidelines. This study, which used EHR data, did not support the use of CRP as an independent marker of future short-term hospitalisations.

In Electronic Health Record (EHR) systems, key patient information is often captured in the form of unstructured clinical notes. The information from these notes can be extracted using Clinical Natural Language Processing (NLP). Training corpus is a key factor in development of efficient clinical NLP models. Clinical NLP corpus construction is complex and multifaceted. There are several challenges in corpus construction, but one challenge often not researched well is cohort selection aspect. In this study, we present methods employed and challenges encountered in cohort selection for construction of a clinical NLP corpus. In specific we present our methods in selection of cancer pathology reports to construct a corpus for automatic deidentification. 2100 pathology reports were extracted from 1833 (518 male and 1313 female) cancer patients using Health Level-7 (HL7) message standard. In terms of the age group distribution, the age group 60–70 years was highest with 872 patients. Our findings suggest deciphering the segment information from HL7 messages that are collected from different hospitals is a challenging task. The quality of HL7 messages also varied significantly with inconsistent tags making it difficult to identify reports that meet criteria set a priori. One of key lessons learned is linking the HL7 reports data with additional EMR data such as admissions, would help in identifying high quality reports and resolve duplicates. Also, our findings suggest that, in general the EHR data quality is poor with varying clinical coding and metadata standards between different hospitals. It is vital to identify and address these challenges for development of a high-quality corpus.

Background Healthcare organisations are undergoing a major transformational shift in the use of information and digital health technologies. Enterprise architecture (EA) has been incrementally adopted in many healthcare organisations globally to facilitate this change. EA can increase the effectiveness of an organisation’s digital health capabilities and resources. However, little is known about the status of EA adoption in low-income and middle-income countries. This study aimed to evaluate the challenges, goals and benefits associated with adoption of EA for healthcare in the Asia eHealth Information Network (AeHIN) member countries .Methods We developed an EA Adoption Evaluation framework with four principal layers: governance, strategy, EA and performance. The framework guided the development of a questionnaire to investigate the goals, challenges and benefits faced before and during EA adoption by healthcare organisations.Sample 26 participants from 18 healthcare organisations in the Asia-Pacific region representing 11 countries. Organisations included Ministries of Health, Universities, Non-Governmental Organisations and Technical Advisory Groups.Findings Only 5 of the 18 organisations had begun adopting EA. The goals expressed for EA adoption were to address issues such as interoperability, lack of technical infrastructure and poor alignment of business and information technology strategies. Cost reduction was less emphasised. The main challenges to adopting EA was the lack of EA knowledge, leadership and involvement of senior management.Conclusion The adoption of EA is incipient in AeHIN member healthcare organisations. To encourage EA adoption, these organisations need to invest in internal capacity building, senior management training and seek independent EA expert advice to systematically identify and address the barriers to adopting EA.

Epidemiological surveillance is an essential component of public health practice especially during infectious disease outbreaks. It is critical to offer transparent epidemiological information in a rigorous manner at different regional levels in countries for managing the outbreak situations. The objectives of this research are to better understand the information flow of COVID-19 health monitoring systems and to determine the data gaps of COVID-19 incidence at the national and provincial levels in Indonesia. COVID-19 information flow was researched using government websites at the national and various provincial levels. To find the disparities, we assessed the number of cases reported at both levels at the same time and displayed the absolute and relative differences. The findings revealed that out of a total of 34 provinces in Indonesia, data differences were seen in 25 (73.52%) provinces in terms of positive cases, 31 (91.18%) provinces in terms of cured cases, and 28 (82.35%) provinces of the number of deaths. Our results showed a pressing need for high-quality, transparent, and timely information. The integration of COVID-19 data in Indonesia has not been optimal, implying that the reported COVID-19 incidence rate may be biased or delayed. COVID-19 incidents must be better monitored to disrupt the disease’s transmission chain.

Introduction:The proportion of people aged over 60 years is increasing globally and expected to double by 2050 [1]. The World Health Organization and health systems globally have identified mobile health (mHealth) as an important strategy to address the health needs of this growing population group. Healthcare innovations focused on ageing, including mHealth interventions, provide an opportunity to enhance service delivery. A systematic review [2] was undertaken to answer the following questions: 1. How is mHealth being used to promote healthy ageing and support the delivery of age-friendly health and long-term care services? 2. What are the effective models for implementing mHealth interventions? 3. What are the lessons learnt from implementation of mHealth initiatives? 4. Is there enough evidence to support the impact of mHealth interventions? Methods:The review was conducted in late 2017, following the PRISMA[3] guidelines for systematic reviews. MEDLINE, EMBASE, Global Health, PsycINFO, Scopus, ScienceDirect, CINAHL and the Cochrane Library were searched.A combination of the terms ‘mHealth OR mobile health’ AND 'healthy ageing’ AND 'aged care’ was used along with the five domains of the RE-AIM framework [4]. The inclusion criteria were: (i) literature published from 2007 to 2017 on mHealth interventions, and (ii) mHealth interventions conducted on people aged 45 years and older. Results:Of 2883 records identified, 133 studies were included in the qualitative synthesis. Most mHealth interventions were an adjunct to existing age-friendly health services, particularly for older adults with chronic health conditions. There were no examples of scaled-up implementations or systematic evaluations of successful feasibility and usability studies that implemented mHealth.The rapid pace of technological change as well as development, adoption and demise of mHealth apps presents crucial challenges for consumers, health care providers and policy makers. Overall, there is a lack of conclusive evidence regarding cost-effectiveness of mHealth to improve healthy ageing and support age-friendly health services. Implications for policy, practice and research: Future mHealth research needs robust experimental designs and a person-centred, biopsychosocial approach that looks at multi-level determinants of health care. Collaborative partnerships for the design, development, testing, implementation and evaluation of mHealth apps are essential.Robust governance frameworks for mHealth strategies are also required, as there is a risk the mHealth initiatives will further fragment care due to development and use of too many disparate apps and platforms without shared data frameworks or governance. References: 1. World Health Organization (2016). World report on ageing and health 2015. 2. Liaw ST, Ansari S, Jonnagaddala J, Narasimhan P, Ashraf MM, Harris-Roxas B and Harris M (2017). A systematic review of the use of mHealth to promote healthy ageing and support the delivery of age-friendly health and long-term care services. PROSPERO CRD42017082383. 3. Moher D, Liberati A, Tetzlaff J, Altman DG and Group P (2009). Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. PLoS medicine. 6(7):e1000097. 4. Gaglio B, Shoup JA and Glasgow RE (2013). The RE-AIM Framework: A Systematic Review of Use Over Time. American Journal of Public Health. 103(6):e38-e46.