Deep learning based linear energy transfer calculation for proton therapy.

OBJECTIVE: This study aims to address the limitations of traditional methods for calculating linear energy transfer (LET), a critical component in assessing relative biological effectiveness (RBE). Currently, Monte Carlo (MC) simulation, the gold-standard for accuracy, is resource-intensive and slow for dose optimization, while the speedier analytical approximation has compromised accuracy. Our objective was to prototype a deep-learning-based model for calculating dose-averaged LET (LETd) using patient anatomy and dose-to-water (DW) data, facilitating real-time biological dose evaluation and LET optimization within proton treatment planning systems. Approach: 275 4-field prostate proton Stereotactic Body Radiotherapy (SBRT) plans were analyzed, rendering a total of 1100 fields. Those were randomly split into 880, 110, and 110 fields for training, validation, and testing. A 3D Cascaded UNet model, along with data processing and inference pipelines, was developed to generate patient-specific LETd distributions from CT images and DW. The accuracy of the LETd of the test dataset was evaluated against MC-generated ground truth through voxel-based mean absolute error (MAE) and gamma analysis. Main Results: The proposed model accurately inferred LETd distributions for each proton field in the test dataset. A single-field LETd calculation took around 100 ms with trained models running on a NVidia A100 GPU. The selected model yielded an average MAE of 0.94±0.14 MeV/cm and a gamma passing rate of 97.4% ± 1.3% when applied to the test dataset, with the largest discrepancy at the edge of fields where the dose gradient was the largest and counting statistics was the lowest. Significance: This study demonstrates that deep-learning-based models can efficiently calculate LETd with high accuracy as a fast-forward approach. The model shows great potential to be utilized for optimizing the RBE of proton treatment plans. Future efforts will focus on enhancing the model's performance and evaluating its adaptability to different clinical scenarios.

Health equity assessment of machine learning performance (HEAL): a framework and dermatology AI model case study.

Background: Artificial intelligence (AI) has repeatedly been shown to encode historical inequities in healthcare. We aimed to develop a framework to quantitatively assess the performance equity of health AI technologies and to illustrate its utility via a case study. Methods: Here, we propose a methodology to assess whether health AI technologies prioritise performance for patient populations experiencing worse outcomes, that is complementary to existing fairness metrics. We developed the Health Equity Assessment of machine Learning performance (HEAL) framework designed to quantitatively assess the performance equity of health AI technologies via a four-step interdisciplinary process to understand and quantify domain-specific criteria, and the resulting HEAL metric. As an illustrative case study (analysis conducted between October 2022 and January 2023), we applied the HEAL framework to a dermatology AI model. A set of 5420 teledermatology cases (store-and-forward cases from patients of 20 years or older, submitted from primary care providers in the USA and skin cancer clinics in Australia), enriched for diversity in age, sex and race/ethnicity, was used to retrospectively evaluate the AI model's HEAL metric, defined as the likelihood that the AI model performs better for subpopulations with worse average health outcomes as compared to others. The likelihood that AI performance was anticorrelated to pre-existing health outcomes was estimated using bootstrap methods as the probability that the negated Spearman's rank correlation coefficient (i.e., "R") was greater than zero. Positive values of R suggest that subpopulations with poorer health outcomes have better AI model performance. Thus, the HEAL metric, defined as p (R >0), measures how likely the AI technology is to prioritise performance for subpopulations with worse average health outcomes as compared to others (presented as a percentage below). Health outcomes were quantified as disability-adjusted life years (DALYs) when grouping by sex and age, and years of life lost (YLLs) when grouping by race/ethnicity. AI performance was measured as top-3 agreement with the reference diagnosis from a panel of 3 dermatologists per case. Findings: Across all dermatologic conditions, the HEAL metric was 80.5% for prioritizing AI performance of racial/ethnic subpopulations based on YLLs, and 92.1% and 0.0% respectively for prioritizing AI performance of sex and age subpopulations based on DALYs. Certain dermatologic conditions were significantly associated with greater AI model performance compared to a reference category of less common conditions. For skin cancer conditions, the HEAL metric was 73.8% for prioritizing AI performance of age subpopulations based on DALYs. Interpretation: Analysis using the proposed HEAL framework showed that the dermatology AI model prioritised performance for race/ethnicity, sex (all conditions) and age (cancer conditions) subpopulations with respect to pre-existing health disparities. More work is needed to investigate ways of promoting equitable AI performance across age for non-cancer conditions and to better understand how AI models can contribute towards improving equity in health outcomes. Funding: Google LLC.

Laser nanostructured gold biosensor for proto-oncogene detection.

The advancement of biosensor research has been a primary driving force in the continuing progress of modern medical science. While traditional nanofabrication methods have long been the foundation of biosensor research, recent years have seen a shift in the field of nanofabrication towards laser-based techniques. Here we report a gold-based biosensor, with a limit of detection (LoD) 3.18 µM, developed using environmentally friendly Laser Ablation Synthesis in Liquid (LASiS) and Confined Atmospheric Pulsed-laser (CAP) deposition techniques for the first time. The sensors were able detect a DNA fragment corresponding to the longest unpaired sequence of the c-Myc gene, indicating their potential for detecting such fragments in the ctDNA signature of various cancers. The LoD of the developed novel biosensor highlights its reliability and sensitivity as an analytical platform. The reproducibility of the sensor was examined via the production and testing of 200 sensors with the same fabrication methodology. This work offers a scalable, and green approach to fabricating viable biosensors capable of detecting clinically relevant oncogenic targets.

Validation of clinical acceptability of deep-learning-based automated segmentation of organs-at-risk for head-and-neck radiotherapy treatment planning.

Introduction: Organ-at-risk segmentation for head and neck cancer radiation therapy is a complex and time-consuming process (requiring up to 42 individual structure, and may delay start of treatment or even limit access to function-preserving care. Feasibility of using a deep learning (DL) based autosegmentation model to reduce contouring time without compromising contour accuracy is assessed through a blinded randomized trial of radiation oncologists (ROs) using retrospective, de-identified patient data. Methods: Two head and neck expert ROs used dedicated time to create gold standard (GS) contours on computed tomography (CT) images. 445 CTs were used to train a custom 3D U-Net DL model covering 42 organs-at-risk, with an additional 20 CTs were held out for the randomized trial. For each held-out patient dataset, one of the eight participant ROs was randomly allocated to review and revise the contours produced by the DL model, while another reviewed contours produced by a medical dosimetry assistant (MDA), both blinded to their origin. Time required for MDAs and ROs to contour was recorded, and the unrevised DL contours, as well as the RO-revised contours by the MDAs and DL model were compared to the GS for that patient. Results: Mean time for initial MDA contouring was 2.3 hours (range 1.6-3.8 hours) and RO-revision took 1.1 hours (range, 0.4-4.4 hours), compared to 0.7 hours (range 0.1-2.0 hours) for the RO-revisions to DL contours. Total time reduced by 76% (95%-Confidence Interval: 65%-88%) and RO-revision time reduced by 35% (95%-CI,-39%-91%). All geometric and dosimetric metrics computed, agreement with GS was equivalent or significantly greater (p<0.05) for RO-revised DL contours compared to the RO-revised MDA contours, including volumetric Dice similarity coefficient (VDSC), surface DSC, added path length, and the 95%-Hausdorff distance. 32 OARs (76%) had mean VDSC greater than 0.8 for the RO-revised DL contours, compared to 20 (48%) for RO-revised MDA contours, and 34 (81%) for the unrevised DL OARs. Conclusion: DL autosegmentation demonstrated significant time-savings for organ-at-risk contouring while improving agreement with the institutional GS, indicating comparable accuracy of DL model. Integration into the clinical practice with a prospective evaluation is currently underway.

Use of digital measurement of medication adherence and lung function to guide the management of uncontrolled asthma (INCA Sun): a multicentre, single-blinded, randomised clinical trial.

BACKGROUND: The clinical value of using digital tools to assess adherence and lung function in uncontrolled asthma is not known. We aimed to compare treatment decisions guided by digitally acquired data on adherence, inhaler technique, and peak flow with existing methods. METHODS: A 32-week prospective, multicentre, single-blinded, parallel, randomly controlled trial was done in ten severe asthma clinics across Ireland, Northern Ireland, and England. Participants were 18 years or older, had uncontrolled asthma, asthma control test (ACT) score of 19 or less, despite treatment with high-dose inhaled corticosteroids, and had at least one severe exacerbation in the past year despite high-dose inhaled corticosteroids. Patients were randomly assigned in a 1:1 ratio to the active group or the control group, by means of a computer-generated randomisation sequence of permuted blocks of varying sizes (2, 4, and 6) stratified by fractional exhaled nitric oxide (FeNO) concentration and recruitment site. In the control group, participants were masked to their adherence and errors in inhaler technique data. A statistician masked to study allocation did the statistical analysis. After a 1-week run-in period, both groups attended three nurse-led education visits over 8 weeks (day 7, week 4, and week 8) and three physician-led treatment adjustment visits at weeks 8, 20, and 32. In the active group, treatment adjustments during the physician visits were informed by digital data on inhaler adherence, twice daily digital peak expiratory flow (ePEF), patient-reported asthma control, and exacerbation history. Treatment was adjusted in the control group on the basis of pharmacy refill rates (a measure of adherence), asthma control by ACT questionnaire, and history of exacerbations and visual management of inhaler technique. Both groups used a digitally enabled Inhaler Compliance Assessment (INCA) and PEF. The primary outcomes were asthma medication burden measured as proportion of patients who required a net increase in treatment at the end of 32 weeks and adherence rate measured in the last 12 weeks by area under the curve in the intention-to-treat population. The safety analyses included all patients who consented for the trial. The trial is registered with ClinicalTrials.gov, NCT02307669 and is complete. FINDINGS: Between Oct 25, 2015, and Jan 26, 2020, of 425 patients assessed for eligibility, 220 consented to participate in the study, 213 were randomly assigned (n=108 in the active group; n=105 in the control group) and 200 completed the study (n=102 in the active group; n=98 in the control group). In the intention-to-treat analysis at week 32, 14 (14%) active and 31 (32%) control patients had a net increase in treatment compared with baseline (odds ratio [OR] 0·31 [95% CI 0·15-0·64], p=0·0015) and 11 (11%) active and 21 (21%) controls required add-on biological therapy (0·42 [0·19-0·95], p=0·038) adjusted for study site, age, sex, and baseline FeNO. Three (16%) of 19 active and 11 (44%) of 25 control patients increased their medication from fluticasone propionate 500 µg daily to 1000 µg daily (500 µg twice a day; adjusted OR 0·23 [0·06-0·87], p=0·026). 26 (31%) of 83 active and 13 (18%) of 73 controls reduced their medication from fluticasone propionate 1000 µg once daily to 500 µg once daily (adjusted OR 2·43 [1·13-5·20], p=0·022. Week 20-32 actual mean adherence was 64·9% (SD 23·5) in the active group and 55·5% (26·8) in the control group (between-group difference 11·1% [95% CI 4·4-17·9], p=0·0012). A total of 29 serious adverse events were recorded (16 [55%] in the active group, and 13 [45%] in the control group), 11 of which were confirmed as respiratory. None of the adverse events reported were causally linked to the study intervention, to the use of salmeterol-fluticasone inhalers, or the use of the digital PEF or INCA. INTERPRETATION: Evidence-based care informed by digital data led to a modest improvement in medication adherence and a significantly lower treatment burden. FUNDING: Health Research Board of Ireland, Medical Research Council, INTEREG Europe, and an investigator-initiated project grant from GlaxoSmithKline.

Predicting the immediate impact of national lockdown on neovascular age-related macular degeneration and associated visual morbidity: an INSIGHT Health Data Research Hub for Eye Health report.

OBJECTIVE: Predicting the impact of neovascular age-related macular degeneration (nAMD) service disruption on visual outcomes following national lockdown in the UK to contain SARS-CoV-2. METHODS AND ANALYSIS: This retrospective cohort study includes deidentified data from 2229 UK patients from the INSIGHT Health Data Research digital hub. We forecasted the number of treatment-naïve nAMD patients requiring anti-vascular endothelial growth factor (anti-VEGF) initiation during UK lockdown (16 March 2020 through 31 July 2020) at Moorfields Eye Hospital (MEH) and University Hospitals Birmingham (UHB). Best-measured visual acuity (VA) changes without anti-VEGF therapy were predicted using post hoc analysis of Minimally Classic/Occult Trial of the Anti-VEGF Antibody Ranibizumab in the Treatment of Neovascular AMD trial sham-control arm data (n=238). RESULTS: At our centres, 376 patients were predicted to require anti-VEGF initiation during lockdown (MEH: 325; UHB: 51). Without treatment, mean VA was projected to decline after 12 months. The proportion of eyes in the MEH cohort predicted to maintain the key positive visual outcome of ≥70 ETDRS letters (Snellen equivalent 6/12) fell from 25.5% at baseline to 5.8% at 12 months (UHB: 9.8%-7.8%). Similarly, eyes with VA <25 ETDRS letters (6/96) were predicted to increase from 4.3% to 14.2% at MEH (UHB: 5.9%-7.8%) after 12 months without treatment. CONCLUSIONS: Here, we demonstrate how combining data from a recently founded national digital health data repository with historical industry-funded clinical trial data can enhance predictive modelling in nAMD. The demonstrated detrimental effects of prolonged treatment delay should incentivise healthcare providers to support nAMD patients accessing care in safe environments. TRIAL REGISTRATION NUMBER: NCT00056836.

Clinically Applicable Segmentation of Head and Neck Anatomy for Radiotherapy: Deep Learning Algorithm Development and Validation Study.

BACKGROUND: Over half a million individuals are diagnosed with head and neck cancer each year globally. Radiotherapy is an important curative treatment for this disease, but it requires manual time to delineate radiosensitive organs at risk. This planning process can delay treatment while also introducing interoperator variability, resulting in downstream radiation dose differences. Although auto-segmentation algorithms offer a potentially time-saving solution, the challenges in defining, quantifying, and achieving expert performance remain. OBJECTIVE: Adopting a deep learning approach, we aim to demonstrate a 3D U-Net architecture that achieves expert-level performance in delineating 21 distinct head and neck organs at risk commonly segmented in clinical practice. METHODS: The model was trained on a data set of 663 deidentified computed tomography scans acquired in routine clinical practice and with both segmentations taken from clinical practice and segmentations created by experienced radiographers as part of this research, all in accordance with consensus organ at risk definitions. RESULTS: We demonstrated the model's clinical applicability by assessing its performance on a test set of 21 computed tomography scans from clinical practice, each with 21 organs at risk segmented by 2 independent experts. We also introduced surface Dice similarity coefficient, a new metric for the comparison of organ delineation, to quantify the deviation between organ at risk surface contours rather than volumes, better reflecting the clinical task of correcting errors in automated organ segmentations. The model's generalizability was then demonstrated on 2 distinct open-source data sets, reflecting different centers and countries to model training. CONCLUSIONS: Deep learning is an effective and clinically applicable technique for the segmentation of the head and neck anatomy for radiotherapy. With appropriate validation studies and regulatory approvals, this system could improve the efficiency, consistency, and safety of radiotherapy pathways.

Validation and Clinical Applicability of Whole-Volume Automated Segmentation of Optical Coherence Tomography in Retinal Disease Using Deep Learning.

IMPORTANCE: Quantitative volumetric measures of retinal disease in optical coherence tomography (OCT) scans are infeasible to perform owing to the time required for manual grading. Expert-level deep learning systems for automatic OCT segmentation have recently been developed. However, the potential clinical applicability of these systems is largely unknown. OBJECTIVE: To evaluate a deep learning model for whole-volume segmentation of 4 clinically important pathological features and assess clinical applicability. DESIGN, SETTING, PARTICIPANTS: This diagnostic study used OCT data from 173 patients with a total of 15 558 B-scans, treated at Moorfields Eye Hospital. The data set included 2 common OCT devices and 2 macular conditions: wet age-related macular degeneration (107 scans) and diabetic macular edema (66 scans), covering the full range of severity, and from 3 points during treatment. Two expert graders performed pixel-level segmentations of intraretinal fluid, subretinal fluid, subretinal hyperreflective material, and pigment epithelial detachment, including all B-scans in each OCT volume, taking as long as 50 hours per scan. Quantitative evaluation of whole-volume model segmentations was performed. Qualitative evaluation of clinical applicability by 3 retinal experts was also conducted. Data were collected from June 1, 2012, to January 31, 2017, for set 1 and from January 1 to December 31, 2017, for set 2; graded between November 2018 and January 2020; and analyzed from February 2020 to November 2020. MAIN OUTCOMES AND MEASURES: Rating and stack ranking for clinical applicability by retinal specialists, model-grader agreement for voxelwise segmentations, and total volume evaluated using Dice similarity coefficients, Bland-Altman plots, and intraclass correlation coefficients. RESULTS: Among the 173 patients included in the analysis (92 [53%] women), qualitative assessment found that automated whole-volume segmentation ranked better than or comparable to at least 1 expert grader in 127 scans (73%; 95% CI, 66%-79%). A neutral or positive rating was given to 135 model segmentations (78%; 95% CI, 71%-84%) and 309 expert gradings (2 per scan) (89%; 95% CI, 86%-92%). The model was rated neutrally or positively in 86% to 92% of diabetic macular edema scans and 53% to 87% of age-related macular degeneration scans. Intraclass correlations ranged from 0.33 (95% CI, 0.08-0.96) to 0.96 (95% CI, 0.90-0.99). Dice similarity coefficients ranged from 0.43 (95% CI, 0.29-0.66) to 0.78 (95% CI, 0.57-0.85). CONCLUSIONS AND RELEVANCE: This deep learning-based segmentation tool provided clinically useful measures of retinal disease that would otherwise be infeasible to obtain. Qualitative evaluation was additionally important to reveal clinical applicability for both care management and research.

Use of deep learning to develop continuous-risk models for adverse event prediction from electronic health records.

Early prediction of patient outcomes is important for targeting preventive care. This protocol describes a practical workflow for developing deep-learning risk models that can predict various clinical and operational outcomes from structured electronic health record (EHR) data. The protocol comprises five main stages: formal problem definition, data pre-processing, architecture selection, calibration and uncertainty, and generalizability evaluation. We have applied the workflow to four endpoints (acute kidney injury, mortality, length of stay and 30-day hospital readmission). The workflow can enable continuous (e.g., triggered every 6 h) and static (e.g., triggered at 24 h after admission) predictions. We also provide an open-source codebase that illustrates some key principles in EHR modeling. This protocol can be used by interdisciplinary teams with programming and clinical expertise to build deep-learning prediction models with alternate data sources and prediction tasks.

Application of Artificial Intelligence for the Diagnosis and Treatment of Liver Diseases.

Modern medical care produces large volumes of multimodal patient data, which many clinicians struggle to process and synthesize into actionable knowledge. In recent years, artificial intelligence (AI) has emerged as an effective tool in this regard. The field of hepatology is no exception, with a growing number of studies published that apply AI techniques to the diagnosis and treatment of liver diseases. These have included machine-learning algorithms (such as regression models, Bayesian networks, and support vector machines) to predict disease progression, the presence of complications, and mortality; deep-learning algorithms to enable rapid, automated interpretation of radiologic and pathologic images; and natural-language processing to extract clinically meaningful concepts from vast quantities of unstructured data in electronic health records. This review article will provide a comprehensive overview of hepatology-focused AI research, discuss some of the barriers to clinical implementation and adoption, and suggest future directions for the field.

Trace multi-class organic explosives analysis in complex matrices enabled using LEGO®-inspired clickable 3D-printed solid phase extraction block arrays.

The development of a new, lower cost method for trace explosives recovery from complex samples is presented using miniaturised, click-together and leak-free 3D-printed solid phase extraction (SPE) blocks. For the first time, a large selection of ten commercially available 3D printing materials were comprehensively evaluated for practical, flexible and multiplexed SPE using stereolithography (SLA), PolyJet and fused deposition modelling (FDM) technologies. Miniaturised single-piece, connectable and leak-free block housings inspired by Lego® were 3D-printed in a methacrylate-based resin, which was found to be most stable under different aqueous/organic solvent and pH conditions, using a cost-effective benchtop SLA printer. Using a tapered SPE bed format, frit-free packing of multiple different commercially available sorbent particles was also possible. Coupled SPE blocks were then shown to offer efficient analyte enrichment and a potentially new approach to improve the stability of recovered analytes in the field when stored on the sorbent, rather than in wet swabs. Performance was measured using liquid chromatography-high resolution mass spectrometry and was better, or similar, to commercially available coupled SPE cartridges, with respect to recovery, precision, matrix effects, linearity and range, for a selection of 13 peroxides, nitramines, nitrate esters and nitroaromatics. Mean % recoveries from dried blood, oil residue and soil matrices were 79 ± 24%, 71 ± 16% and 76 ± 24%, respectively. Excellent detection limits between 60 fg for 3,5-dinitroaniline to 154 pg for nitroglycerin were also achieved across all matrices. To our knowledge, this represents the first application of 3D printing to SPE of so many organic compounds in complex samples. Its introduction into this forensic method offered a low-cost, 'on-demand' solution for selective extraction of explosives, enhanced flexibility for multiplexing/design alteration and potential application at-scene.

Development of a selective inhibitor for Kv1.1 channels prevalent in demyelinated nerves.

Members of the voltage-gated K+ channel subfamily (Kv1), involved in regulating transmission between neurons or to muscles, are associated with human diseases and, thus, putative targets for neurotherapeutics. This applies especially to those containing Kv1.1 α subunits which become prevalent in murine demyelinated axons and appear abnormally at inter-nodes, underlying the perturbed propagation of nerve signals. To overcome this dysfunction, akin to the consequential debilitation in multiple sclerosis (MS), small inhibitors were sought that are selective for the culpable hyper-polarising K+ currents. Herein, we report a new semi-podand - compound 3 - that was designed based on the modelling of its interactions with the extracellular pore region in a deduced Kv1.1 channel structure. After synthesis, purification, and structural characterisation, compound 3 was found to potently (IC50 = 8 µM) and selectively block Kv1.1 and 1.6 channels. The tested compound showed no apparent effect on native Nav and Cav channels expressed in F-11 cells. Compound 3 also extensively and selectively inhibited MS-related Kv1.1 homomer but not the brain native Kv1.1- or 1.6-containing channels. These collective findings highlight the therapeutic potential of compound 3 to block currents mediated by Kv1.1 channels enriched in demyelinated central neurons.

Predicting conversion to wet age-related macular degeneration using deep learning.

Progression to exudative 'wet' age-related macular degeneration (exAMD) is a major cause of visual deterioration. In patients diagnosed with exAMD in one eye, we introduce an artificial intelligence (AI) system to predict progression to exAMD in the second eye. By combining models based on three-dimensional (3D) optical coherence tomography images and corresponding automatic tissue maps, our system predicts conversion to exAMD within a clinically actionable 6-month time window, achieving a per-volumetric-scan sensitivity of 80% at 55% specificity, and 34% sensitivity at 90% specificity. This level of performance corresponds to true positives in 78% and 41% of individual eyes, and false positives in 56% and 17% of individual eyes at the high sensitivity and high specificity points, respectively. Moreover, we show that automatic tissue segmentation can identify anatomical changes before conversion and high-risk subgroups. This AI system overcomes substantial interobserver variability in expert predictions, performing better than five out of six experts, and demonstrates the potential of using AI to predict disease progression.

BalanCI: Head-Referenced Cochlear Implant Stimulation Improves Balance in Children with Bilateral Cochleovestibular Loss.

INTRODUCTION: To determine the impact of a head-referenced cochlear implant (CI) stimulation system, BalanCI, on balance and postural control in children with bilateral cochleovestibular loss (BCVL) who use bilateral CI. METHODS: Prospective, blinded case-control study. Balance and postural control testing occurred in two settings: (1) quiet clinical setting and (2) immersive realistic virtual environment (Challenging Environment Assessment Laboratory [CEAL], Toronto Rehabilitation Institute). Postural control was assessed in 16 and balance in 10 children with BCVL who use bilateral CI, along with 10 typically developing children. Children with neuromotor, cognitive, or visual deficits that would prevent them from performing the tests were excluded. Children wore the BalanCI, which is a head-mounted device that couples with their CIs through the audio port and provides head-referenced spatial information delivered via the intracochlear electrode array. Postural control was measured by center of pressure (COP) and time to fall using the WiiTM (Nintendo, WA, USA) Balance Board for feet and the BalanCI for head, during the administration of the Modified Clinical Test of Sensory Interaction in Balance (CTSIB-M). The COP of the head and feet were assessed for change by deviation, measured as root mean square around the COP (COP-RMS), rate of deviation (COP-RMS/duration), and rate of path length change from center (COP-velocity). Balance was assessed by the Bruininks-Oseretsky Test of Motor Proficiency 2, balance subtest (BOT-2), specifically, BOT-2 score as well as time to fall/fault. RESULTS: In the virtual environment, children demonstrated more stable balance when using BalanCI as measured by an improvement in BOT-2 scores. In a quiet clinical setting, the use of BalanCI led to improved postural control as demonstrated by significant reductions in COP-RMS and COP-velocity. With the use of BalanCI, the number of falls/faults was significantly reduced and time to fall increased. CONCLUSIONS: BalanCI is a simple and effective means of improving postural control and balance in children with BCVL who use bilateral CI. BalanCI could potentially improve the safety of these children, reduce the effort they expend maintaining balance and allow them to take part in more complex balance tasks where sensory information may be limited and/or noisy.

Implementation of a Digitally Enabled Care Pathway (Part 2): Qualitative Analysis of Experiences of Health Care Professionals.

BACKGROUND: One reason for the introduction of digital technologies into health care has been to try to improve safety and patient outcomes by providing real-time access to patient data and enhancing communication among health care professionals. However, the adoption of such technologies into clinical pathways has been less examined, and the impacts on users and the broader health system are poorly understood. We sought to address this by studying the impacts of introducing a digitally enabled care pathway for patients with acute kidney injury (AKI) at a tertiary referral hospital in the United Kingdom. A dedicated clinical response team-comprising existing nephrology and patient-at-risk and resuscitation teams-received AKI alerts in real time via Streams, a mobile app. Here, we present a qualitative evaluation of the experiences of users and other health care professionals whose work was affected by the implementation of the care pathway. OBJECTIVE: The aim of this study was to qualitatively evaluate the impact of mobile results viewing and automated alerting as part of a digitally enabled care pathway on the working practices of users and their interprofessional relationships. METHODS: A total of 19 semistructured interviews were conducted with members of the AKI response team and clinicians with whom they interacted across the hospital. Interviews were analyzed using inductive and deductive thematic analysis. RESULTS: The digitally enabled care pathway improved access to patient information and expedited early specialist care. Opportunities were identified for more constructive planning of end-of-life care due to the earlier detection and alerting of deterioration. However, the shift toward early detection also highlighted resource constraints and some clinical uncertainty about the value of intervening at this stage. The real-time availability of information altered communication flows within and between clinical teams and across professional groups. CONCLUSIONS: Digital technologies allow early detection of adverse events and of patients at risk of deterioration, with the potential to improve outcomes. They may also increase the efficiency of health care professionals' working practices. However, when planning and implementing digital information innovations in health care, the following factors should also be considered: the provision of clinical training to effectively manage early detection, resources to cope with additional workload, support to manage perceived information overload, and the optimization of algorithms to minimize unnecessary alerts.

Implementation of a Digitally Enabled Care Pathway (Part 1): Impact on Clinical Outcomes and Associated Health Care Costs.

BACKGROUND: The development of acute kidney injury (AKI) in hospitalized patients is associated with adverse outcomes and increased health care costs. Simple automated e-alerts indicating its presence do not appear to improve outcomes, perhaps because of a lack of explicitly defined integration with a clinical response. OBJECTIVE: We sought to test this hypothesis by evaluating the impact of a digitally enabled intervention on clinical outcomes and health care costs associated with AKI in hospitalized patients. METHODS: We developed a care pathway comprising automated AKI detection, mobile clinician notification, in-app triage, and a protocolized specialist clinical response. We evaluated its impact by comparing data from pre- and postimplementation phases (May 2016 to January 2017 and May to September 2017, respectively) at the intervention site and another site not receiving the intervention. Clinical outcomes were analyzed using segmented regression analysis. The primary outcome was recovery of renal function to ≤120% of baseline by hospital discharge. Secondary clinical outcomes were mortality within 30 days of alert, progression of AKI stage, transfer to renal/intensive care units, hospital re-admission within 30 days of discharge, dependence on renal replacement therapy 30 days after discharge, and hospital-wide cardiac arrest rate. Time taken for specialist review of AKI alerts was measured. Impact on health care costs as defined by Patient-Level Information and Costing System data was evaluated using difference-in-differences (DID) analysis. RESULTS: The median time to AKI alert review by a specialist was 14.0 min (interquartile range 1.0-60.0 min). There was no impact on the primary outcome (estimated odds ratio [OR] 1.00, 95% CI 0.58-1.71; P=.99). Although the hospital-wide cardiac arrest rate fell significantly at the intervention site (OR 0.55, 95% CI 0.38-0.76; P<.001), DID analysis with the comparator site was not significant (OR 1.13, 95% CI 0.63-1.99; P=.69). There was no impact on other secondary clinical outcomes. Mean health care costs per patient were reduced by £2123 (95% CI -£4024 to -£222; P=.03), not including costs of providing the technology. CONCLUSIONS: The digitally enabled clinical intervention to detect and treat AKI in hospitalized patients reduced health care costs and possibly reduced cardiac arrest rates. Its impact on other clinical outcomes and identification of the active components of the pathway requires clarification through evaluation across multiple sites.

Evaluation of a digitally-enabled care pathway for acute kidney injury management in hospital emergency admissions.

We developed a digitally enabled care pathway for acute kidney injury (AKI) management incorporating a mobile detection application, specialist clinical response team and care protocol. Clinical outcome data were collected from adults with AKI on emergency admission before (May 2016 to January 2017) and after (May to September 2017) deployment at the intervention site and another not receiving the intervention. Changes in primary outcome (serum creatinine recovery to ≤120% baseline at hospital discharge) and secondary outcomes (30-day survival, renal replacement therapy, renal or intensive care unit (ICU) admission, worsening AKI stage and length of stay) were measured using interrupted time-series regression. Processes of care data (time to AKI recognition, time to treatment) were extracted from casenotes, and compared over two 9-month periods before and after implementation (January to September 2016 and 2017, respectively) using pre-post analysis. There was no step change in renal recovery or any of the secondary outcomes. Trends for creatinine recovery rates (estimated odds ratio (OR) = 1.04, 95% confidence interval (95% CI): 1.00-1.08, p = 0.038) and renal or ICU admission (OR = 0.95, 95% CI: 0.90-1.00, p = 0.044) improved significantly at the intervention site. However, difference-in-difference analyses between sites for creatinine recovery (estimated OR = 0.95, 95% CI: 0.90-1.00, p = 0.053) and renal or ICU admission (OR = 1.06, 95% CI: 0.98-1.16, p = 0.140) were not significant. Among process measures, time to AKI recognition and treatment of nephrotoxicity improved significantly (p < 0.001 and 0.047 respectively).

A clinically applicable approach to continuous prediction of future acute kidney injury.

The early prediction of deterioration could have an important role in supporting healthcare professionals, as an estimated 11% of deaths in hospital follow a failure to promptly recognize and treat deteriorating patients1. To achieve this goal requires predictions of patient risk that are continuously updated and accurate, and delivered at an individual level with sufficient context and enough time to act. Here we develop a deep learning approach for the continuous risk prediction of future deterioration in patients, building on recent work that models adverse events from electronic health records2-17 and using acute kidney injury-a common and potentially life-threatening condition18-as an exemplar. Our model was developed on a large, longitudinal dataset of electronic health records that cover diverse clinical environments, comprising 703,782 adult patients across 172 inpatient and 1,062 outpatient sites. Our model predicts 55.8% of all inpatient episodes of acute kidney injury, and 90.2% of all acute kidney injuries that required subsequent administration of dialysis, with a lead time of up to 48 h and a ratio of 2 false alerts for every true alert. In addition to predicting future acute kidney injury, our model provides confidence assessments and a list of the clinical features that are most salient to each prediction, alongside predicted future trajectories for clinically relevant blood tests9. Although the recognition and prompt treatment of acute kidney injury is known to be challenging, our approach may offer opportunities for identifying patients at risk within a time window that enables early treatment.

Clinically applicable deep learning for diagnosis and referral in retinal disease.

The volume and complexity of diagnostic imaging is increasing at a pace faster than the availability of human expertise to interpret it. Artificial intelligence has shown great promise in classifying two-dimensional photographs of some common diseases and typically relies on databases of millions of annotated images. Until now, the challenge of reaching the performance of expert clinicians in a real-world clinical pathway with three-dimensional diagnostic scans has remained unsolved. Here, we apply a novel deep learning architecture to a clinically heterogeneous set of three-dimensional optical coherence tomography scans from patients referred to a major eye hospital. We demonstrate performance in making a referral recommendation that reaches or exceeds that of experts on a range of sight-threatening retinal diseases after training on only 14,884 scans. Moreover, we demonstrate that the tissue segmentations produced by our architecture act as a device-independent representation; referral accuracy is maintained when using tissue segmentations from a different type of device. Our work removes previous barriers to wider clinical use without prohibitive training data requirements across multiple pathologies in a real-world setting.

Service evaluation of the implementation of a digitally-enabled care pathway for the recognition and management of acute kidney injury.

Acute Kidney Injury (AKI), an abrupt deterioration in kidney function, is defined by changes in urine output or serum creatinine. AKI is common (affecting up to 20% of acute hospital admissions in the United Kingdom), associated with significant morbidity and mortality, and expensive (excess costs to the National Health Service in England alone may exceed £1 billion per year). NHS England has mandated the implementation of an automated algorithm to detect AKI based on changes in serum creatinine, and to alert clinicians. It is uncertain, however, whether 'alerting' alone improves care quality. We have thus developed a digitally-enabled care pathway as a clinical service to inpatients in the Royal Free Hospital (RFH), a large London hospital. This pathway incorporates a mobile software application - the "Streams-AKI" app, developed by DeepMind Health - that applies the NHS AKI algorithm to routinely collected serum creatinine data in hospital inpatients. Streams-AKI alerts clinicians to potential AKI cases, furnishing them with a trend view of kidney function alongside other relevant data, in real-time, on a mobile device. A clinical response team comprising nephrologists and critical care nurses responds to these AKI alerts by reviewing individual patients and administering interventions according to existing clinical practice guidelines. We propose a mixed methods service evaluation of the implementation of this care pathway. This evaluation will assess how the care pathway meets the health and care needs of service users (RFH inpatients), in terms of clinical outcome, processes of care, and NHS costs. It will also seek to assess acceptance of the pathway by members of the response team and wider hospital community. All analyses will be undertaken by the service evaluation team from UCL (Department of Applied Health Research) and St George's, University of London (Population Health Research Institute).