Search

Transferring and replicating predictive algorithms across healthcare systems constitutes a unique yet crucial challenge that needs to be addressed to enable the widespread adoption of machine learning in healthcare. In this study, we explored the impact of important differences across healthcare systems and the associated Electronic Health Records (EHRs) on machine-learning algorithms to predict mental health crises, up to 28 days in advance. We evaluated both the transferability and replicability of such machine learning models, and for this purpose, we trained six models using features and methods developed on EHR data from the Birmingham and Solihull Mental Health NHS Foundation Trust in the UK. These machine learning models were then used to predict the mental health crises of 2907 patients seen at the Rush University System for Health in the US between 2018 and 2020. The best one was trained on a combination of US-specific structured features and frequency features from anonymized patient notes and achieved an AUROC of 0.837. A model with comparable performance, originally trained using UK structured data, was transferred and then tuned using US data, achieving an AUROC of 0.826. Our findings establish the feasibility of transferring and replicating machine learning models to predict mental health crises across diverse hospital systems. [ABSTRACT FROM AUTHOR]

Background: To address if the long-standing association between maternal infection, depression/anxiety in pregnancy, and offspring neurodevelopmental disorder (NDD) is causal, we conducted two negative-control studies. Methods: Four primary care cohorts of UK children (pregnancy, 1 and 2 years prior to pregnancy, and siblings) born between 1 January 1990 and 31 December 2017 were constructed. NDD included autism/autism spectrum disorder, attention-deficit/hyperactivity disorder, intellectual disability, cerebral palsy, and epilepsy. Maternal exposures included depression/anxiety and/or infection. Maternal (age, smoking status, comorbidities, body mass index, NDD); child (gender, ethnicity, birth year); and area-level (region and level of deprivation) confounders were captured. The NDD incidence rate among (1) children exposed during or outside of pregnancy and (2) siblings discordant for exposure in pregnancy was compared using Cox-regression models, unadjusted and adjusted for confounders. Results: The analysis included 410 461 children of 297 426 mothers and 2 793 018 person-years of follow-up with 8900 NDD cases (incidence rate = 3.2/1000 person years). After adjustments, depression and anxiety consistently associated with NDD (pregnancy-adjusted HR = 1.58, 95% CI 1.46–1.72; 1-year adj. HR = 1.49, 95% CI 1.39–1.60; 2-year adj. HR = 1.62, 95% CI 1.50–1.74); and to a lesser extent, of infection (pregnancy adj. HR = 1.16, 95% CI 1.10–1.22; 1-year adj. HR = 1.20, 95% CI 1.14–1.27; 2-year adj. HR = 1.19, 95% CI 1.12–1.25). NDD risk did not differ among siblings discordant for pregnancy exposure to mental illness HR = 0.97, 95% CI 0.77–1.21 or infection HR = 0.99, 95% CI 0.90–1.08. Conclusions: Maternal risk appears to be unspecific to pregnancy: our study provided no evidence of a specific, and therefore causal, link between in-utero exposure to infection, common mental illness, and later development of NDD. [ABSTRACT FROM AUTHOR]

Wearable inertial measurement units (IMUs) are being used to quantify gait characteristics that are associated with increased fall risk, but the current limitation is the lack of contextual information that would clarify IMU data. Use of wearable video-based cameras would provide a comprehensive understanding of an individual's habitual fall risk, adding context to clarify abnormal IMU data. Generally, there is taboo when suggesting the use of wearable cameras to capture real-world video, clinical and patient apprehension due to ethical and privacy concerns. This perspective proposes that routine use of wearable cameras could be realized within digital medicine through AI-based computer vision models to obfuscate/blur/shade sensitive information while preserving helpful contextual information for a comprehensive patient assessment. Specifically, no person sees the raw video data to understand context, rather AI interprets the raw video data first to blur sensitive objects and uphold privacy. That may be more routinely achieved than one imagines as contemporary resources exist. Here, to showcase/display the potential an exemplar model is suggested via off-the-shelf methods to detect and blur sensitive objects (e.g., people) with an accuracy of 88%. Here, the benefit of the proposed approach includes a more comprehensive understanding of an individual's free-living fall risk (from free-living IMU-based gait) without compromising privacy. More generally, the video and AI approach could be used beyond fall risk to better inform habitual experiences and challenges across a range of clinical cohorts. Medicine is becoming more receptive to wearables as a helpful toolbox, camera-based devices should be plausible instruments. [ABSTRACT FROM AUTHOR]

Background: Recent research has shown that insecure attachment, especially attachment anxiety, is associated with poor mental health outcomes, especially during the COVID‐19 pandemic. Other research suggests that insecure attachment may be linked to nonadherence to social distancing behaviours during the pandemic. Aims: The present study aims to examine the causal links between attachment styles (secure, anxious, avoidant), mental health outcomes (depression, anxiety, loneliness) and adherence to social distancing behaviours during the first several months of the UK lockdown (between April and August 2020). Materials & Methods: We used a nationally representative UK sample (cross‐sectional n = 1325; longitudinal n = 950). The data were analysed using state‐of‐the‐art causal discovery and targeted learning algorithms to identify causal processes. Results: The results showed that insecure attachment styles were causally linked to poorer mental health outcomes, mediated by loneliness. Only attachment avoidance was causally linked to nonadherence to social distancing guidelines. Discussion: Future interventions to improve mental health outcomes should focus on mitigating feelings of loneliness. Limitations include no access to pre‐pandemic data and the use of categorical attachment measure. Conclusion: Insecure attachment is a risk factor for poorer mental health outcomes. [ABSTRACT FROM AUTHOR]

Objectives Computer-assisted coding of job descriptions to standardized occupational classification codes facilitates evaluating occupational risk factors in epidemiologic studies by reducing the number of jobs needing expert coding. We evaluated the performance of the 2nd version of SOCcer, a computerized algorithm designed to code free-text job descriptions to US SOC-2010 system based on free-text job titles and work tasks, to evaluate its accuracy. Methods SOCcer v2 was updated by expanding the training data to include jobs from several epidemiologic studies and revising the algorithm to account for nonlinearity and incorporate interactions. We evaluated the agreement between codes assigned by experts and the highest scoring code (a measure of confidence in the algorithm-predicted assignment) from SOCcer v1 and v2 in 14,714 jobs from three epidemiology studies. We also linked exposure estimates for 258 agents in the job-exposure matrix CANJEM to the expert and SOCcer v2-assigned codes and compared those estimates using kappa and intraclass correlation coefficients. Analyses were stratified by SOCcer score, score distance between the top two scoring codes from SOCcer, and features from CANJEM. Results SOCcer's v2 agreement at the 6-digit level was 50%, compared to 44% in v1, and was similar for the three studies (38%–45%). Overall agreement for v2 at the 2-, 3-, and 5-digit was 73%, 63%, and 56%, respectively. For v2, median ICCs for the probability and intensity metrics were 0.67 (IQR 0.59–0.74) and 0.56 (IQR 0.50–0.60), respectively. The agreement between the expert and SOCcer assigned codes linearly increased with SOCcer score. The agreement also improved when the top two scoring codes had larger differences in score. Conclusions Overall agreement with SOCcer v2 applied to job descriptions from North American epidemiologic studies was similar to the agreement usually observed between two experts. SOCcer's score predicted agreement with experts and can be used to prioritize jobs for expert review. [ABSTRACT FROM AUTHOR]

During the outbreak of a disease caused by a pathogen with unknown characteristics, the uncertainty of its progression parameters can be reduced by devising methods that, based on rational assumptions, exploit available information to provide actionable insights. In this study, performed a few (~6) weeks into the outbreak of COVID-19 (caused by SARS-CoV-2), one of the most important disease parameters, the average time-to-recovery, was calculated using data publicly available on the internet (daily reported cases of confirmed infections, deaths, and recoveries), and fed into an algorithm that matches confirmed cases with deaths and recoveries. Unmatched cases were adjusted based on the matched cases calculation. The mean time-to-recovery, calculated from all globally reported cases, was found to be 18.01 days (SD 3.31 days) for the matched cases and 18.29 days (SD 2.73 days) taking into consideration the adjusted unmatched cases as well. The proposed method used limited data and provided experimental results in the same region as clinical studies published several months later. This indicates that the proposed method, combined with expert knowledge and informed calculated assumptions, could provide a meaningful calculated average time-to-recovery figure, which can be used as an evidence-based estimation to support containment and mitigation policy decisions, even at the very early stages of an outbreak. [ABSTRACT FROM AUTHOR]

Cardiorespiratory fitness is an established predictor of metabolic disease and mortality. Fitness is directly measured as maximal oxygen consumption (VO2max), or indirectly assessed using heart rate responses to standard exercise tests. However, such testing is costly and burdensome because it requires specialized equipment such as treadmills and oxygen masks, limiting its utility. Modern wearables capture dynamic real-world data which could improve fitness prediction. In this work, we design algorithms and models that convert raw wearable sensor data into cardiorespiratory fitness estimates. We validate these estimates' ability to capture fitness profiles in free-living conditions using the Fenland Study (N=11,059), along with its longitudinal cohort (N = 2675), and a third external cohort using the UK Biobank Validation Study (N = 181) who underwent maximal VO2max testing, the gold standard measurement of fitness. Our results show that the combination of wearables and other biomarkers as inputs to neural networks yields a strong correlation to ground truth in a holdout sample (r = 0.82, 95CI 0.80–0.83), outperforming other approaches and models and detects fitness change over time (e.g., after 7 years). We also show how the model's latent space can be used for fitness-aware patient subtyping paving the way to scalable interventions and personalized trial recruitment. These results demonstrate the value of wearables for fitness estimation that today can be measured only with laboratory tests. [ABSTRACT FROM AUTHOR]

The UK government plans to limit price‐based and location‐based promotions for products high in saturated fat, salt and sugars. The 2004/2005 UK Nutrient Profiling Model (NPM) is the proposed legislative basis, but may be superseded by the draft 2018 NPM. This study develops an algorithm to apply both NPMs to a large food composition database (FCDB), and assesses implementation challenges. UK NPMs were applied algorithmically to the myfood24 FCDB, representing ~45 000 retail products. Pass rates – indicating free or restricted promotions – and micronutrient compositions were compared. Challenges were assessed, and recommendations addressed the legislation's public consultation questions. For products in scope (75% of total), 6% fewer passed the 2018 NPM (36%, P < 0.001) compared with the 2004/2005 NPM (42%). Beverages showed the greatest reduction in pass rate (75%). Under both models, micronutrient contents (per 100 g of product) were generally lower for products that passed; except folate, vitamin C and vitamin D were no different for passed and failed products. Compared with products passing the 2004/2005 NPM, products passing the 2018 NPM on average had marginally higher amounts of iron (0.05 mg, 95% CI: 0.02, 0.08, P < 0.001) and magnesium (1.00 mg, 95% CI: 0.00, 1.17, P = 0.029), but marginally lower levels of calcium (−0.42 mg, 95% CI: −2.00, −0.40, P = 0.025). Missing ingredient information and heterogeneous product categories were challenges for both NPMs. Free sugars calculation further complicated 2018 NPM application. To balance feasibility and public health benefit, the proposed legislative basis may not be appropriate. [ABSTRACT FROM AUTHOR]

Background: The literature contains limited information on the problems faced by dying patients with COVID-19 and the effectiveness of interventions to manage these. Aim: The aim of this audit was to assess the utility of our end-of-life care plan, and specifically the effectiveness of our standardised end-of-life care treatment algorithms, in dying patients with COVID-19. Design: The audit primarily involved data extraction from the end-of-life care plan, which includes four hourly nursing (ward nurses) assessments of specific problems: patients with problems were managed according to standardised treatment algorithms, and the intervention was deemed to be effective if the problem was not present at subsequent assessments. Setting/participants: This audit was undertaken at a general hospital in England, covered the 8 weeks from 16 March to 11 May 2020 and included all inpatients with COVID-19 who had an end-of-life care plan (and died). Results: Sixty-one patients met the audit criteria: the commonest problem was shortness of breath (57.5%), which was generally controlled with conservative doses of morphine (10–20 mg/24 h via a syringe pump). Cough and audible respiratory secretions were relatively uncommon. The second most common problem was agitation/delirium (55.5%), which was generally controlled with standard pharmacological interventions. The cumulative number of patients with shortness of breath, agitation and audible respiratory secretions increased over the last 72 h of life, but most patients were symptom controlled at the point of death. Conclusion: Patients dying of COVID-19 experience similar end-of-life problems to other groups of patients. Moreover, they generally respond to standard interventions for these end-of-life problems. [ABSTRACT FROM AUTHOR]

Purpose: To assess the feasibility and acceptability of the Howz smart home system for stroke survivors. Materials: Howz uses smart home technology to monitor users' activity in the home and machine learning algorithms to detect when their activity changes. This information made available to the user and a named contact (usually a family member) via the Howz app. If activity changes, an alert is then sent to the user and the named contact. Methods: Howz was installed in the homes of 19 stroke survivors who lived alone. The sensors installed; the number and nature of alerts; adverse events; any technical difficulties and how Howz was used were recorded. We also interviewed participants and their named contacts about their views and experiences of using Howz eight weeks after installation. Results: Installation was effective; no technological problems or adverse events were reported. All participants chose alerts regarding "getting up" and activity during the day and at night. There was a mean of 1.1 (sd 1.2) alerts/person. Participants found the system unobtrusive and were positive about it. They found it easy to use and would recommend it to others with stroke. The most frequently reported benefit was that Howz gave peace of mind for the users and/or the family/named contact that help would be at hand if needed. Conclusions: The Howz system was feasible and acceptable for stroke survivors. It gave users and their family an enhanced sense of security and peace of mind that help would be at hand if needed. Although most stroke survivors are elderly and often suffer physical, visual and cognitive disabilities which are often considered as barriers to using smart home technology, this project has demonstrated the well-developed smart home technology is feasible and acceptable. Users were able and willing to engage with the technology (to varying degrees) and had no concerns about invasion of privacy. The main benefit of the Howz system is an enhanced sense of security for the user and their family that help is at hand if needed. [ABSTRACT FROM AUTHOR]

Purpose: To review the management of children and adolescents (0–18 years), with blunt splenic injury treated at a single UK major trauma centre over a 5-year period, focusing upon efficacy of non-operative management and the use of haemodynamic stability as a guide to planning treatment strategy, rather than radiological injury grading. To produce a treatment pathway for management of blunt splenic injury in children. Methods: Retrospective, cross-sectional study of all paediatric patients admitted with radiologically proven blunt splenic injury between January 2011 and March 2016. Penetrating injuries were excluded. Follow up was for at least 30 days. Results: 30 Patients were included, mean age was 14.5 (SD 3.6), median injury severity score was 16 (IQR 10–31). 6 Patients (20%) had a splenectomy, whilst 22 patients (73%) were successfully treated non-operatively with 100% efficacy at index admission. 5/8 (63%) patients with radiological grade V injuries were managed non-operatively, injury grade was not associated with surgical intervention (p = 1.57). Haemodynamic instability was initially treated with fluid resuscitation leading to successful non-operative management in 5/11 (45%) patients. However, haemodynamic instability is a significant predictor of requirement for surgical intervention (p = 0.03), admission to critical care (p = 0.017), presence of additional injuries (p = 0.015) and increased length of stay (p = 0.038). No such relationships were found to be associated with increased radiological injury grade. Conclusions: Non-operative management should be first-line treatment in the haemodynamically stable child with a blunt splenic injury and may be carried out with a high degree of efficacy. It may also be successfully implemented in those initially showing signs of haemodynamic instability that respond to fluid resuscitation. Radiological injury grade does not predict definitive management, level of care, or length of stay; however, haemodynamic stability may be utilised to produce a treatment algorithm and is key to guiding management. [ABSTRACT FROM AUTHOR]

The article focuses on a study which examines large-scale observational evidence of cross-cultural differences in facial behavior using advanced in computer science. Topics discussed include the automated facial coding used, the reliability of the facial action unit detection algorithms across different testing subsets, multilevel regression estimates predicting each facial action's base rate percentage.

Background The first British Dietetic Association ( BDA) guidelines for the dietary management of irritable bowel syndrome ( IBS) in adults were published in 2012. Subsequently, there has been a wealth of new research. The aim of this work was to systematically review the evidence for the role of diet in the management of IBS and to update the guidelines. Methods Twelve questions relating to diet and IBS were defined based on review of the previous guideline questions, current evidence and clinical practice. Chosen topics were on healthy eating and lifestyle (alcohol, caffeine, spicy food, elimination diets, fat and fluid intakes and dietary habits), milk and dairy, dietary fibre, fermentable carbohydrates, gluten, probiotics and elimination diets/food hypersensitivity. Data sources were CINAHL, Cochrane Register of Controlled Trials, Embase, Medline, Scopus and Web of Science up to October 2015. Studies were assessed independently in duplicate using risk of bias tools specific to each included study based on inclusion and exclusion criteria for each question. National Health and Medical Research Council grading evidence levels were used to develop evidence statements and recommendations, in accordance with Practice-based Evidence in Nutrition Global protocol used by the BDA. Results Eighty-six studies were critically appraised to generate 46 evidence statements, 15 clinical recommendations and four research recommendations. The IBS dietary algorithm was simplified to first-line (healthy eating, provided by any healthcare professional) and second-line [low FODMAP ( fermentable oligosaccharides, disaccharides, monosaccharides and polyols) to be provided by dietitian] dietary advice. Conclusions These guidelines provide updated comprehensive evidence-based details to achieve the successful dietary management of IBS in adults. [ABSTRACT FROM AUTHOR]

Objective: To assess (1) the feasibility of incorporating the Ida Institute’s Motivation Tools into a UK audiology service, (2) the potential benefits of motivational engagement in first-time hearing aid users, and (3) predictors of hearing aid and general health outcome measures. Design: A feasibility study using a single-centre, prospective, quasi-randomized controlled design with two arms. The Ida Institute’s Motivation Tools formed the basis for motivational engagement. Study sample: First-time hearing aid users were recruited at the initial hearing assessment appointment. The intervention arm underwent motivational engagement (M+, n = 32), and a control arm (M-, n = 36) received standard care only. Results: The M+ group showed greater self-efficacy, reduced anxiety, and greater engagement with the audiologist at assessment and fitting appointments. However, there were no significant between-group differences 10-weeks post-fitting. Hearing-related communication scores predicted anxiety, and social isolation scores predicted depression for the M+ group. Readiness to address hearing difficulties predicted hearing aid outcomes for the M- group. Hearing sensitivity was not a predictor of outcomes. Conclusions: There were some positive results from motivational engagement early in the patient journey. Future research should consider using qualitative methods to explore whether there are longer-term benefits of motivational engagement in hearing aid users. [ABSTRACT FROM AUTHOR]

Syndromic autism has been described in children adopted after orphanage rearing. We investigated whether the same existed in children adopted after family breakdown. Families of 54/60 adopted children aged 6-11 years (mean 102 months; SD 20; 45 % male) returned screening questionnaires for autism spectrum disorder (ASD); 21/54 (39 %) screened positive. Detailed in-person phenotyping of screen positive cases showed ASD in 6/54 (11 %), Broad ASD (sub threshold traits) in 10/54 (18.5 %); 5/54 (9 %) screened false positive. The ASD group showed impairments across both social communication and restrictive repetitive behaviour domains, Broad ASD was more mixed. These rates, much higher than population prevalence, are comparable with institutionalised samples. There are implications for developmental science, and assessment, treatment and policy for adopted children. [ABSTRACT FROM AUTHOR]

Objective: To formally evaluate the written discharge advice for people with mild traumatic brain injury (mTBI). Methods: Eleven publications met the inclusion criteria: (1) intended for adults; (2) ≤two A4 pages; (3) published in English; (4) freely accessible; and (5) currently used (or suitable for use) in Australian hospital emergency departments or similar settings. Two independent raters evaluated the content and style of each publication against established standards. The readability of the publication, the diagnostic term(s) contained in it and a modified Patient Literature Usefulness Index (mPLUI) were also evaluated. Results: The mean content score was 19.18 ± 8.53 (maximum = 31) and the mean style score was 6.8 ± 1.34 (maximum = 8). The mean Flesch-Kincaid reading ease score was 66.42 ± 4.3. The mean mPLUI score was 65.86 ± 14.97 (maximum = 100). Higher scores on these metrics indicate more desirable properties. Over 80% of the publications used mixed diagnostic terminology. One publication scored optimally on two of the four metrics and highly on the others. Discussion: The content, style, readability and usefulness of written mTBI discharge advice was highly variable. The provision of written information to patients with mTBI is advised, but this variability in materials highlights the need for evaluation before distribution. Areas are identified to guide the improvement of written mTBI discharge advice. [ABSTRACT FROM AUTHOR]

Background: Increases in physical activity through active travel have the potential to have large beneficial effects on populations, through both better health outcomes and reduced motorized traffic. However accurately identifying travel mode in large datasets is problematic. Here we provide an open source tool to quantify time spent stationary and in four travel modes(walking, cycling, train, motorised vehicle) from accelerometer measured physical activity data, combined with GPS and GIS data. Methods: The Examining Neighbourhood Activities in Built Living Environments in London study evaluates the effect of the built environment on health behaviours, including physical activity. Participants wore accelerometers and GPS receivers on the hip for 7 days. We time-matched accelerometer and GPS, and then extracted data from the commutes of 326 adult participants, using stated commute times and modes, which were manually checked to confirm stated travel mode. This yielded examples of five travel modes: walking, cycling, motorised vehicle, train and stationary. We used this example data to train a gradient boosted tree, a form of supervised machine learning algorithm, on each data point (131,537 points), rather than on journeys. Accuracy during training was assessed using five-fold cross-validation. We also manually identified the travel behaviour of both 21 participants from ENABLE London (402,749 points), and 10 participants from a separate study (STAMP-2, 210,936 points), who were not included in the training data. We compared our predictions against this manual identification to further test accuracy and test generalisability. Results: Applying the algorithm, we correctly identified travel mode 97.3% of the time in cross-validation (mean sensitivity 96.3%, mean active travel sensitivity 94.6%). We showed 96.0% agreement between manual identification and prediction of 21 individuals' travel modes (mean sensitivity 92.3%, mean active travel sensitivity 84.9%) and 96.5% agreement between the STAMP-2 study and predictions (mean sensitivity 85.5%, mean active travel sensitivity 78.9%). Conclusion: We present a generalizable tool that identifies time spent stationary and time spent walking with very high precision, time spent in trains or vehicles with good precision, and time spent cycling with moderate precisionIn studies where both accelerometer and GPS data are available this tool complements analyses of physical activity, showing whether differences in PA may be explained by differences in travel mode. All code necessary to replicate, fit and predict to other datasets is provided to facilitate use by other researchers. [ABSTRACT FROM AUTHOR]