ROAD2H: Development and evaluation of an open-source explainable artificial intelligence approach for managing co-morbidity and clinical guidelines.

Introduction: Clinical decision support (CDS) systems (CDSSs) that integrate clinical guidelines need to reflect real-world co-morbidity. In patient-specific clinical contexts, transparent recommendations that allow for contraindications and other conflicts arising from co-morbidity are a requirement. In this work, we develop and evaluate a non-proprietary, standards-based approach to the deployment of computable guidelines with explainable argumentation, integrated with a commercial electronic health record (EHR) system in Serbia, a middle-income country in West Balkans. Methods: We used an ontological framework, the Transition-based Medical Recommendation (TMR) model, to represent, and reason about, guideline concepts, and chose the 2017 International global initiative for chronic obstructive lung disease (GOLD) guideline and a Serbian hospital as the deployment and evaluation site, respectively. To mitigate potential guideline conflicts, we used a TMR-based implementation of the Assumptions-Based Argumentation framework extended with preferences and Goals (ABA+G). Remote EHR integration of computable guidelines was via a microservice architecture based on HL7 FHIR and CDS Hooks. A prototype integration was developed to manage chronic obstructive pulmonary disease (COPD) with comorbid cardiovascular or chronic kidney diseases, and a mixed-methods evaluation was conducted with 20 simulated cases and five pulmonologists. Results: Pulmonologists agreed 97% of the time with the GOLD-based COPD symptom severity assessment assigned to each patient by the CDSS, and 98% of the time with one of the proposed COPD care plans. Comments were favourable on the principles of explainable argumentation; inclusion of additional co-morbidities was suggested in the future along with customisation of the level of explanation with expertise. Conclusion: An ontological model provided a flexible means of providing argumentation and explainable artificial intelligence for a long-term condition. Extension to other guidelines and multiple co-morbidities is needed to test the approach further.

DEcancer: Machine learning framework tailored to liquid biopsy based cancer detection and biomarker signature selection.

Cancer is a leading cause of mortality worldwide. Over 50% of cancers are diagnosed late, rendering many treatments ineffective. Existing liquid biopsy studies demonstrate a minimally invasive and inexpensive approach for disease detection but lack parsimonious biomarker selection, exhibit poor cancer detection performance and lack appropriate validation and testing. We established a tailored machine learning pipeline, DEcancer, for liquid biopsy analysis that addresses these limitations and improved performance. In a test set from a published cohort of 1,005 patients including 8 cancer types and 812 cancer-free individuals, DEcancer increased stage 1 cancer detection sensitivity across cancer types from 48 to 90%. In addition, with a test set cohort of patients from a high dimensional proteomics dataset of 61 lung cancer patients and 80 cancer-free individuals, DEcancer's performance using a 14-43 protein panel was comparable to 1,000 original proteins. DEcancer is a promising tool which may facilitate improved cancer detection and management.

Remote COVID-19 Assessment in Primary Care (RECAP) risk prediction tool: derivation and real-world validation studies.

BACKGROUND: Accurate assessment of COVID-19 severity in the community is essential for patient care and requires COVID-19-specific risk prediction scores adequately validated in a community setting. Following a qualitative phase to identify signs, symptoms, and risk factors, we aimed to develop and validate two COVID-19-specific risk prediction scores. Remote COVID-19 Assessment in Primary Care-General Practice score (RECAP-GP; without peripheral oxygen saturation [SpO2]) and RECAP-oxygen saturation score (RECAP-O2; with SpO2). METHODS: RECAP was a prospective cohort study that used multivariable logistic regression. Data on signs and symptoms (predictors) of disease were collected from community-based patients with suspected COVID-19 via primary care electronic health records and linked with secondary data on hospital admission (outcome) within 28 days of symptom onset. Data sources for RECAP-GP were Oxford-Royal College of General Practitioners Research and Surveillance Centre (RCGP-RSC) primary care practices (development set), northwest London primary care practices (validation set), and the NHS COVID-19 Clinical Assessment Service (CCAS; validation set). The data source for RECAP-O2 was the Doctaly Assist platform (development set and validation set in subsequent sample). The two probabilistic risk prediction models were built by backwards elimination using the development sets and validated by application to the validation datasets. Estimated sample size per model, including the development and validation sets was 2880 people. FINDINGS: Data were available from 8311 individuals. Observations, such as SpO2, were mostly missing in the northwest London, RCGP-RSC, and CCAS data; however, SpO2 was available for 1364 (70·0%) of 1948 patients who used Doctaly. In the final predictive models, RECAP-GP (n=1863) included sex (male and female), age (years), degree of breathlessness (three point scale), temperature symptoms (two point scale), and presence of hypertension (yes or no); the area under the curve was 0·80 (95% CI 0·76-0·85) and on validation the negative predictive value of a low risk designation was 99% (95% CI 98·1-99·2; 1435 of 1453). RECAP-O2 included age (years), degree of breathlessness (two point scale), fatigue (two point scale), and SpO2 at rest (as a percentage); the area under the curve was 0·84 (0·78-0·90) and on validation the negative predictive value of low risk designation was 99% (95% CI 98·9-99·7; 1176 of 1183). INTERPRETATION: Both RECAP models are valid tools to assess COVID-19 patients in the community. RECAP-GP can be used initially, without need for observations, to identify patients who require monitoring. If the patient is monitored and SpO2 is available, RECAP-O2 is useful to assess the need for treatment escalation. FUNDING: Community Jameel and the Imperial College President's Excellence Fund, the Economic and Social Research Council, UK Research and Innovation, and Health Data Research UK.

Deep learning-based quantification of temporalis muscle has prognostic value in patients with glioblastoma.

BACKGROUND: Glioblastoma is the commonest malignant brain tumour. Sarcopenia is associated with worse cancer survival, but manually quantifying muscle on imaging is time-consuming. We present a deep learning-based system for quantification of temporalis muscle, a surrogate for skeletal muscle mass, and assess its prognostic value in glioblastoma. METHODS: A neural network for temporalis segmentation was trained with 366 MRI head images from 132 patients from 4 different glioblastoma data sets and used to quantify muscle cross-sectional area (CSA). Association between temporalis CSA and survival was determined in 96 glioblastoma patients from internal and external data sets. RESULTS: The model achieved high segmentation accuracy (Dice coefficient 0.893). Median age was 55 and 58 years and 75.6 and 64.7% were males in the in-house and TCGA-GBM data sets, respectively. CSA was an independently significant predictor for survival in both the in-house and TCGA-GBM data sets (HR 0.464, 95% CI 0.218-0.988, p = 0.046; HR 0.466, 95% CI 0.235-0.925, p = 0.029, respectively). CONCLUSIONS: Temporalis CSA is a prognostic marker in patients with glioblastoma, rapidly and accurately assessable with deep learning. We are the first to show that a head/neck muscle-derived sarcopenia metric generated using deep learning is associated with oncological outcomes and one of the first to show deep learning-based muscle quantification has prognostic value in cancer.

An Early Warning Risk Prediction Tool (RECAP-V1) for Patients Diagnosed With COVID-19: Protocol for a Statistical Analysis Plan.

BACKGROUND: Since the start of the COVID-19 pandemic, efforts have been made to develop early warning risk scores to help clinicians decide which patient is likely to deteriorate and require hospitalization. The RECAP (Remote COVID-19 Assessment in Primary Care) study investigates the predictive risk of hospitalization, deterioration, and death of patients with confirmed COVID-19, based on a set of parameters chosen through a Delphi process performed by clinicians. We aim to use rich data collected remotely through the use of electronic data templates integrated in the electronic health systems of several general practices across the United Kingdom to construct accurate predictive models. The models will be based on preexisting conditions and monitoring data of a patient's clinical parameters (eg, blood oxygen saturation) to make reliable predictions as to the patient's risk of hospital admission, deterioration, and death. OBJECTIVE: This statistical analysis plan outlines the statistical methods to build the prediction model to be used in the prioritization of patients in the primary care setting. The statistical analysis plan for the RECAP study includes the development and validation of the RECAP-V1 prediction model as a primary outcome. This prediction model will be adapted as a three-category risk score split into red (high risk), amber (medium risk), and green (low risk) for any patient with suspected COVID-19. The model will predict the risk of deterioration and hospitalization. METHODS: After the data have been collected, we will assess the degree of missingness and use a combination of traditional data imputation using multiple imputation by chained equations, as well as more novel machine-learning approaches to impute the missing data for the final analysis. For predictive model development, we will use multiple logistic regression analyses to construct the model. We aim to recruit a minimum of 1317 patients for model development and validation. We will then externally validate the model on an independent dataset of 1400 patients. The model will also be applied for multiple different datasets to assess both its performance in different patient groups and its applicability for different methods of data collection. RESULTS: As of May 10, 2021, we have recruited 3732 patients. A further 2088 patients have been recruited through the National Health Service Clinical Assessment Service, and approximately 5000 patients have been recruited through the DoctalyHealth platform. CONCLUSIONS: The methodology for the development of the RECAP-V1 prediction model as well as the risk score will provide clinicians with a statistically robust tool to help prioritize COVID-19 patients. TRIAL REGISTRATION: ClinicalTrials.gov NCT04435041; https://clinicaltrials.gov/ct2/show/NCT04435041. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/30083.

Predicting Risk of Hospital Admission in Patients With Suspected COVID-19 in a Community Setting: Protocol for Development and Validation of a Multivariate Risk Prediction Tool.

BACKGROUND: During the pandemic, remote consultations have become the norm for assessing patients with signs and symptoms of COVID-19 to decrease the risk of transmission. This has intensified the clinical uncertainty already experienced by primary care clinicians when assessing patients with suspected COVID-19 and has prompted the use of risk prediction scores, such as the National Early Warning Score (NEWS2), to assess severity and guide treatment. However, the risk prediction tools available have not been validated in a community setting and are not designed to capture the idiosyncrasies of COVID-19 infection. OBJECTIVE: The objective of this study is to produce a multivariate risk prediction tool, RECAP-V1 (Remote COVID-19 Assessment in Primary Care), to support primary care clinicians in the identification of those patients with COVID-19 that are at higher risk of deterioration and facilitate the early escalation of their treatment with the aim of improving patient outcomes. METHODS: The study follows a prospective cohort observational design, whereby patients presenting in primary care with signs and symptoms suggestive of COVID-19 will be followed and their data linked to hospital outcomes (hospital admission and death). Data collection will be carried out by primary care clinicians in four arms: North West London Clinical Commissioning Groups (NWL CCGs), Oxford-Royal College of General Practitioners (RCGP) Research and Surveillance Centre (RSC), Covid Clinical Assessment Service (CCAS), and South East London CCGs (Doctaly platform). The study involves the use of an electronic template that incorporates a list of items (known as RECAP-V0) thought to be associated with disease outcome according to previous qualitative work. Data collected will be linked to patient outcomes in highly secure environments. We will then use multivariate logistic regression analyses for model development and validation. RESULTS: Recruitment of participants started in October 2020. Initially, only the NWL CCGs and RCGP RSC arms were active. As of March 24, 2021, we have recruited a combined sample of 3827 participants in these two arms. CCAS and Doctaly joined the study in February 2021, with CCAS starting the recruitment process on March 15, 2021. The first part of the analysis (RECAP-V1 model development) is planned to start in April 2021 using the first half of the NWL CCGs and RCGP RSC combined data set. Posteriorly, the model will be validated with the rest of the NWL CCGs and RCGP RSC data as well as the CCAS and Doctaly data sets. The study was approved by the Research Ethics Committee on May 27, 2020 (Integrated Research Application System number: 283024, Research Ethics Committee reference number: 20/NW/0266) and badged as National Institute of Health Research Urgent Public Health Study on October 14, 2020. CONCLUSIONS: We believe the validated RECAP-V1 early warning score will be a valuable tool for the assessment of severity in patients with suspected COVID-19 in the community, either in face-to-face or remote consultations, and will facilitate the timely escalation of treatment with the potential to improve patient outcomes. TRIAL REGISTRATION: ISRCTN registry ISRCTN13953727; https://www.isrctn.com/ISRCTN13953727. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/29072.

Do patients and carers agree on symptom burden in advanced COPD?

Objective: Accurate informal carer assessment of patient symptoms is likely to be valuable for decision making in managing the high symptom burden of COPD in the home setting. Few studies have investigated agreement between patients and carers in COPD. We aimed to assess agreement between patients and carers on symptoms, and factors associated with disagreement in a population-based sample of patients with advanced COPD. Patients and methods: This was a prospective, cross-sectional analysis of data from 119 advanced COPD patients and their carers. Patients and carers separately rated symptoms on a 4-point scale. Wilcoxon signed-rank tests and weighted Cohen's kappa determined differences in patient and carer scores and patient-carer agreement, respectively. We identified characteristics associated with incongruence using Spearman's rank correlation and Mann-Whitney U tests. Results: There were no significant differences between group-level patient and carer scores for any symptom. Patient-carer individual-level agreement was moderate for constipation (k=0.423), just below moderate for diarrhea (k=0.393) and fair for depression (k=0.341), fatigue (k=0.294), anxiety (k=0.289) and breathlessness (k=0.210). Estimation of greater patient symptom burden by carers relative to patients themselves was associated with non-spousal patient-carer relationship, non-cohabitating patients and carers, carer symptoms of anxiety and depression and more carer unmet support needs. Greater symptom burden estimation by the patient relative to the carer was associated with younger patients and longer duration of COPD. Conclusion: Overall, agreement between patients and carers was fair to moderate and was poorer for more subjective symptoms. There is a need to encourage open dialogue between patients and carers to promote shared understanding, help patients express themselves and encourage carers to draw attention to symptoms that patients do not report. The findings suggest a need to screen for and address both the psychological morbidities in patients with advanced COPD and their carers and unmet support needs in carers.

Comparative study of endoscopic surveillance in hereditary diffuse gastric cancer according to CDH1 mutation status.

BACKGROUND AND AIMS: Hereditary diffuse gastric cancer (HDGC) accounts for 1% of gastric cancer cases. For patients with a germline CDH1 mutation, risk-reducing gastrectomy is recommended. However, for those delaying surgery or for families with no causative mutation identified, regular endoscopy is advised. This study aimed to determine the yield of signet ring cell carcinoma (SRCC) foci in individuals with a CDH1 pathogenic variant compared with those without and how this varies with successive endoscopies. METHODS: Patients fulfilling HDGC criteria were recruited to a prospective longitudinal cohort study. Endoscopy was performed according to a strict protocol with visual inspection followed by focal lesion and random biopsy sampling to detect foci of SRCC. Survival analysis determined progression to finding of SRCC according to CDH1 mutation status. The European Organization for Research and Treatment of Cancer Quality of Life Questionnaire Core 30 and 36-item Short Form Health Survey questionnaires assessed quality of life before surveillance and each endoscopy. RESULTS: Eighty-five individuals fulfilling HDGC criteria underwent 201 endoscopies; 54 (63.5%) tested positive for CDH1 mutation. SRCC yield was 61.1% in CDH1 mutation carriers compared with 9.7% in noncarriers, and mutation-positive patients had a 10-fold risk of SRCC on endoscopy compared with those with no mutation detected (P < .0005). Yield of SRCC decreased substantially with subsequent endoscopies. Surveillance was associated with improved psychological health. CONCLUSIONS: SRCC foci are prevalent in CDH1 mutation carriers and can be detected at endoscopy using a standardized, multiple biopsy sampling protocol. Decreasing yield over time suggests that the frequency of endoscopy might be reduced. For patients with no CDH1 pathogenic variant detected, the cost-to-benefit ratio needs to be assessed in view of the low yield.

A case series of an off-the-shelf online health resource with integrated nurse coaching to support self-management in COPD.

BACKGROUND: COPD has significant psychosocial impact. Self-management support improves quality of life, but programs are not universally available. IT-based self-management interventions can provide home-based support, but have mixed results. We conducted a case series of an off-the-shelf Internet-based health-promotion program, The Preventive Plan (TPP), coupled with nurse-coach support, which aimed to increase patient activation and provide self-management benefits. MATERIALS AND METHODS: A total of 19 COPD patients were recruited, and 14 completed 3-month follow-up in two groups: groups 1 and 2 with more and less advanced COPD, respectively. Change in patient activation was determined with paired t-tests and Wilcoxon signed-rank tests. Benefits and user experience were explored in semistructured interviews, analyzed thematically. RESULTS: Only group 1 improved significantly in activation, from a lower baseline than group 2; group 1 also improved significantly in mastery and anxiety. Both groups felt significantly more informed about COPD and reported physical functioning improvements. Group 1 reported improvements in mood and confidence. Overall, group 2 reported fewer benefits than group 1. Both groups valued nurse-coach support; for group 1, it was more important than TPP in building confidence to self-manage. The design of TPP and lack of motivation to use IT were barriers to use, but disease severity and poor IT skills were not. DISCUSSION: Our findings demonstrate the feasibility of combining nurse-coach support aligned to an Internet-based health resource, TPP, in COPD and provide learning about the challenges of such an approach and the importance of the nurse-coach role.

Associations between the psychological health of patients and carers in advanced COPD.

OBJECTIVE: Anxiety and depression are highly prevalent in patients with COPD and their informal carers, and associated with numerous risk factors. However, few studies have investigated these in primary care or the link between patient and carer anxiety and depression. We aimed to determine this association and factors associated with anxiety and depression in patients, carers, and both (dyads), in a population-based sample. MATERIALS AND METHODS: This was a prospective, cross-sectional study of 119 advanced COPD patients and their carers. Patient and carer scores ≥8 on the Hospital Anxiety and Depression Scale defined symptoms of anxiety and depression, χ2 tests determined associations between patient and carer symptoms of anxiety/depression, and χ2 and independent t-tests for normally distributed variables (otherwise Mann-Whitney U tests) were used to identify other variables significantly associated with these symptoms in the patient or carer. Patient-carer dyads were categorized into four groups relating to the presence of anxious/depressive symptoms in: both patient and carer, patient only, carer only, and neither. Factors associated with dyad symptoms of anxiety/depression were determined with χ2 tests and one-way analysis of variance for normally distributed variables (otherwise Kruskal-Wallis tests). RESULTS: Prevalence of symptoms of anxiety and depression was 46.4% (n=52) and 42.9% (n=48) in patients, and 46% (n=52) and 23% (n=26) in carers, respectively. Patient and carer symptoms of anxiety/depression were significantly associated. Anxious and depressive symptoms in the patient were also significantly associated with more physical comorbidities, more exacerbations, greater dyspnea, greater fatigue, poor mastery, and depressive symptoms with younger age. Symptoms of carer anxiety were significantly associated with being female and separated/divorced/widowed, and depressive symptoms with younger age, higher educational level, and more physical comorbidities, and symptoms of carer anxiety and depression with more unmet support needs, greater subjective caring burden, and poor patient mastery. Dyad symptoms of anxiety/depression were significantly associated with greater patient fatigue. CONCLUSION: Symptoms of anxiety and depression in COPD patients and carers are significantly associated. Given their high prevalence, considerable impact on mortality, impact on quality of life and health care use, and associations with each other, screening for and addressing patient and carer anxiety and depression in advanced COPD is recommended.

Transforming growth factor ß plays an important role in enhancing wound healing by topical application of Povidone-iodine.

Povidone-iodine (PVI) is principally used as an antimicrobial agent. It has been found that 0.5% PVI can attenuate congestion, edema and pain induced by pressure sores. Thus this study aimed to assess the effects of 0.5% PVI on acute skin wounds. Four full-thickness excisional wounds were generated on the dorsal skin of male Sprague-Dawley rats with a 10-mm sterile punch. Two wounds were left untreated and the other two were dressed with gauze with 0.5% PVI for 1 hour per day for the first 5 days after injury. 10-mm full-thickness excisional wounds were also generated on the dorsal skin of rats treated with 10 mg/kg SB431542 and all wounds were treated with 0.5% PVI for 5 days. PVI treatment enhanced wound healing via promotion of expression of α SMA and TGF ß, neovascularization and re-epithelialization. Interleukin 6 was reduced following PVI treatment. Inhibition of TGF ß abolished the effect of PVI treatment on wound closure. These data show that topical application of 0.5% PVI could promote acute skin wound healing though increased expression of TGF ß leading to enhanced formation of granulation tissue, even in the absence of obvious infection.