Automated Growth Rate Measurement of the Facet Surfaces of Single Crystals of the ß-Form of l-Glutamic Acid Using Machine Learning Image Processing.

Precision measurement of the growth rate of individual single crystal facets (hkl) represents an important component in the design of industrial crystallization processes. Current approaches for crystal growth measurement using optical microscopy are labor intensive and prone to error. An automated process using state-of-the-art computer vision and machine learning to segment and measure the crystal images is presented. The accuracies and efficiencies of the new crystal sizing approach are evaluated against existing manual and semi-automatic methods, demonstrating equivalent accuracy but over a much shorter time, thereby enabling a more complete kinematic analysis of the overall crystallization process. This is applied to measure in situ the crystal growth rates and through this determining the associated kinetic mechanisms for the crystallization of ß-form l-glutamic acid from the solution phase. Growth on the {101} capping faces is consistent with a Birth and Spread mechanism, in agreement with the literature, while the growth rate of the {021} prismatic faces, previously not available in the literature, is consistent with a Burton-Cabrera-Frank screw dislocation mechanism. At a typical supersaturation of σ = 0.78, the growth rate of the {101} capping faces (3.2 × 10-8 m s-1) is found to be 17 times that of the {021} prismatic faces (1.9 × 10-9 m s-1). Both capping and prismatic faces are found to have dead zones in their growth kinetic profiles, with the capping faces (σc = 0.23) being about half that of the prismatic faces (σc = 0.46). The importance of this overall approach as an integral component of the digital design of industrial crystallization processes is highlighted.

Mouse Model of Chronic Social Stress-Induced Excessive Pavlovian Aversion Learning-Memory.

Increased experience of aversive stimuli/events is a psychological-neurobiological state of major importance in psychiatry. It occurs commonly in generalized anxiety disorder, post-traumatic stress disorder, and major depression. A sustained period of exposure to threat (chronic stressor) is a common risk factor, and a major symptom is generalized excessive perception of, and reactivity to, aversive stimuli. In rodents, Pavlovian aversion learning and memory (PAL, PAM), quantified in terms of the conditioned defensive behavior freezing, is an extensively studied behavioral paradigm, and well understood in terms of underlying neural circuitry. In mice, chronic social stress (CSS) is a 15-day resident-intruder paradigm in which C57BL/6 adult males are exposed continuously and distally to dominant-aggressive CD-1 male mice (sustained threat) interspersed with a brief daily period of proximal attack (acute threat). To ensure that physical wounding is minimized, proximal attacks are limited to 30 to 60 s/day and lower incisor teeth of CD-1 mice are blunted. Control (comparison) mice are maintained in littermate pairs. The CSS and CD-1 mice are maintained in distal contact during subsequent behavioral testing. For PAL, CSS and control (CON) mice are placed in a conditioning chamber (context) and exposed to a tone [conditioned stimulus (CS)] and mild, brief foot shock [unconditioned stimulus (US)]. For PAM, mice are placed in the same context and presented with CS repetitions. The CSS mice acquire (learn) and express (memory) a higher level of freezing than CON mice, indicating that CSS leads to generalized hypersensitivity to aversion, i.e., chronic social aversion leads to increased aversion salience of foot shock. Distinctive features of the model include the following: high reproducibility; rare, mild wounding only; male specificity; absence of "susceptible" vs "resilient" subgroups; behavioral effects dependent on continued presence of CD-1 mice; and preclinical validation of novel compounds for normalizing aversion hypersensitivity with accurate feedforward prediction of efficacy in human patients. © 2024 The Authors. Current Protocols published by Wiley Periodicals LLC. Basic Protocol 1: Chronic social stress (CSS) Basic Protocol 2: Pavlovian aversion learning and memory (PALM).

Immune Checkpoint Inhibitors in Advanced Cutaneous Squamous Cell Carcinoma: Real-World Experience from a Canadian Comprehensive Cancer Centre.

Immune checkpoint inhibitors (ICI) cemiplimab and pembrolizumab have revolutionized the treatment of advanced cutaneous squamous cell carcinoma (cSCC). We aimed to evaluate the effectiveness and safety of ICI in a real-world cSCC population, including patients with conditions that would exclude clinical trial participation. In this single-center, retrospective cohort study, we included all non-trial patients with advanced cSCC treated with ICI between 2017 and 2022. We evaluated investigator-assessed best overall response (BOR) and immune-related adverse events (irAEs). We correlated survival outcomes with age, performance status, immune status and irAEs. Of the 36 patients identified, the best overall response (BOR) to ICI was a partial response (PR) in 41.7%, a complete response (CR) in 27.8%, and stable disease in (SD) 13.9%. The progression-free survival (PFS) rate for 1 year was 58.1%; the median PFS was 21.3 months (95% CI 6.4-NE). The 1-year overall survival (OS) was 76.7%, and the median OS was 38.6 months (95% CI 25.4-NE). Immune-compromised patients, ECOG performance 2-3, and age ≥ 75 years were not significantly associated with PFS or OS. IrAE grades 3-4 were seen in 13.9% of patients. In our Canadian experience with real-world patients, ICI was an effective and safe treatment for advanced cSCC patients. Patients achieved great benefits with ICI regardless of age, immune status or ECOG performance status. We acknowledge the small sample size and retrospective methodology as the main limitations of our study.

Future Innovations in Novel Detection for Atrial Fibrillation (FIND-AF): pilot study of an electronic health record machine learning algorithm-guided intervention to identify undiagnosed atrial fibrillation.

INTRODUCTION: Atrial fibrillation (AF) is associated with a fivefold increased risk of stroke. Oral anticoagulation reduces the risk of stroke, but AF is elusive. A machine learning algorithm (Future Innovations in Novel Detection of Atrial Fibrillation (FIND-AF)) developed to predict incident AF within 6 months using data in primary care electronic health records (EHRs) could be used to guide AF screening. The objectives of the FIND-AF pilot study are to determine yields of AF during ECG monitoring across AF risk estimates and establish rates of recruitment and protocol adherence in a remote AF screening pathway. METHODS AND ANALYSIS: The FIND-AF Pilot is an interventional, non-randomised, single-arm, open-label study that will recruit 1955 participants aged 30 years or older, without a history of AF and eligible for oral anticoagulation, identified as higher risk and lower risk by the FIND-AF risk score from their primary care EHRs, to a period of remote ECG monitoring with a Zenicor-ECG device. The primary outcome is AF diagnosis during ECG monitoring, and secondary outcomes include recruitment rates, withdrawal rates, adherence to ECG monitoring and prescription of oral anticoagulation to participants diagnosed with AF during ECG monitoring. ETHICS AND DISSEMINATION: The study has ethical approval (the North West-Greater Manchester South Research Ethics Committee reference 23/NW/0180). Findings will be announced at relevant conferences and published in peer-reviewed journals in line with the Funder's open access policy. TRIAL REGISTRATION NUMBER: NCT05898165.

Prediction models for heart failure in the community: A systematic review and meta-analysis.

AIMS: Multivariable prediction models can be used to estimate risk of incident heart failure (HF) in the general population. A systematic review and meta-analysis was performed to determine the performance of models. METHODS AND RESULTS: From inception to 3 November 2022 MEDLINE and EMBASE databases were searched for studies of multivariable models derived, validated and/or augmented for HF prediction in community-based cohorts. Discrimination measures for models with c-statistic data from ≥3 cohorts were pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using PROBAST. We included 36 studies with 59 prediction models. In meta-analysis, the Atherosclerosis Risk in Communities (ARIC) risk score (summary c-statistic 0.802, 95% confidence interval [CI] 0.707-0.883), GRaph-based Attention Model (GRAM; 0.791, 95% CI 0.677-0.885), Pooled Cohort equations to Prevent Heart Failure (PCP-HF) white men model (0.820, 95% CI 0.792-0.843), PCP-HF white women model (0.852, 95% CI 0.804-0.895), and REverse Time AttentIoN model (RETAIN; 0.839, 95% CI 0.748-0.916) had a statistically significant 95% PI and excellent discrimination performance. The ARIC risk score and PCP-HF models had significant summary discrimination among cohorts with a uniform prediction window. 77% of model results were at high risk of bias, certainty of evidence was low, and no model had a clinical impact study. CONCLUSIONS: Prediction models for estimating risk of incident HF in the community demonstrate excellent discrimination performance. Their usefulness remains uncertain due to high risk of bias, low certainty of evidence, and absence of clinical effectiveness research.

Incident cardiovascular, renal, metabolic diseases and death in individuals identified for risk-guided atrial fibrillation screening: a nationwide cohort study.

OBJECTIVE: Risk-guided atrial fibrillation (AF) screening may be an opportunity to prevent adverse events in addition to stroke. We compared events rates for new diagnoses of cardio-renal-metabolic diseases and death in individuals identified at higher versus lower-predicted AF risk. METHODS: From the UK Clinical Practice Research Datalink-GOLD dataset, 2 January 1998-30 November 2018, we identified individuals aged ≥30 years without known AF. The risk of AF was estimated using the FIND-AF (Future Innovations in Novel Detection of Atrial Fibrillation) risk score. We calculated cumulative incidence rates and fit Fine and Gray's models at 1, 5 and 10 years for nine diseases and death adjusting for competing risks. RESULTS: Of 416 228 individuals in the cohort, 82 942 were identified as higher risk for AF. Higher-predicted risk, compared with lower-predicted risk, was associated with incident chronic kidney disease (cumulative incidence per 1000 persons at 10 years 245.2; HR 6.85, 95% CI 6.70 to 7.00; median time to event 5.44 years), heart failure (124.7; 12.54, 12.08 to 13.01; 4.06), diabetes mellitus (123.3; 2.05, 2.00 to 2.10; 3.45), stroke/transient ischaemic attack (118.9; 8.07, 7.80 to 8.34; 4.27), myocardial infarction (69.6; 5.02, 4.82 to 5.22; 4.32), peripheral vascular disease (44.6; 6.62, 6.28 to 6.98; 4.28), valvular heart disease (37.8; 6.49, 6.14 to 6.85; 4.54), aortic stenosis (18.7; 9.98, 9.16 to 10.87; 4.41) and death from any cause (273.9; 10.45, 10.23 to 10.68; 4.75). The higher-risk group constituted 74% of deaths from cardiovascular or cerebrovascular causes (8582 of 11 676). CONCLUSIONS: Individuals identified for risk-guided AF screening are at risk of new diseases across the cardio-renal-metabolic spectrum and death, and may benefit from interventions beyond ECG monitoring.

Prediction of short-term atrial fibrillation risk using primary care electronic health records.

OBJECTIVE: Atrial fibrillation (AF) screening by age achieves a low yield and misses younger individuals. We aimed to develop an algorithm in nationwide routinely collected primary care data to predict the risk of incident AF within 6 months (Future Innovations in Novel Detection of Atrial Fibrillation (FIND-AF)). METHODS: We used primary care electronic health record data from individuals aged ≥30 years without known AF in the UK Clinical Practice Research Datalink-GOLD dataset between 2 January 1998 and 30 November 2018, randomly divided into training (80%) and testing (20%) datasets. We trained a random forest classifier using age, sex, ethnicity and comorbidities. Prediction performance was evaluated in the testing dataset with internal bootstrap validation with 200 samples, and compared against the CHA2DS2-VASc (Congestive heart failure, Hypertension, Age >75 (2 points), Stroke/transient ischaemic attack/thromboembolism (2 points), Vascular disease, Age 65-74, Sex category) and C2HEST (Coronary artery disease/Chronic obstructive pulmonary disease (1 point each), Hypertension, Elderly (age ≥75, 2 points), Systolic heart failure, Thyroid disease (hyperthyroidism)) scores. Cox proportional hazard models with competing risk of death were fit for incident longer-term AF between higher and lower FIND-AF-predicted risk. RESULTS: Of 2 081 139 individuals in the cohort, 7386 developed AF within 6 months. FIND-AF could be applied to all records. In the testing dataset (n=416 228), discrimination performance was strongest for FIND-AF (area under the receiver operating characteristic curve 0.824, 95% CI 0.814 to 0.834) compared with CHA2DS2-VASc (0.784, 0.773 to 0.794) and C2HEST (0.757, 0.744 to 0.770), and robust by sex and ethnic group. The higher predicted risk cohort, compared with lower predicted risk, had a 20-fold higher 6-month incidence rate for AF and higher long-term hazard for AF (HR 8.75, 95% CI 8.44 to 9.06). CONCLUSIONS: FIND-AF, a machine learning algorithm applicable at scale in routinely collected primary care data, identifies people at higher risk of short-term AF.

Skeletal muscle metabolism and contraction performance regulation by teneurin C-terminal-associated peptide-1.

Skeletal muscle regulation is responsible for voluntary muscular movement in vertebrates. The genes of two essential proteins, teneurins and latrophilins (LPHN), evolving in ancestors of multicellular animals form a ligand-receptor pair, and are now shown to be required for skeletal muscle function. Teneurins possess a bioactive peptide, termed the teneurin C-terminal associated peptide (TCAP) that interacts with the LPHNs to regulate skeletal muscle contractility strength and fatigue by an insulin-independent glucose importation mechanism in rats. CRISPR-based knockouts and siRNA-associated knockdowns of LPHN-1 and-3 in the C2C12 mouse skeletal cell line shows that TCAP stimulates an LPHN-dependent cytosolic Ca2+ signal transduction cascade to increase energy metabolism and enhance skeletal muscle function via increases in type-1 oxidative fiber formation and reduce the fatigue response. Thus, the teneurin/TCAP-LPHN system is presented as a novel mechanism that regulates the energy requirements and performance of skeletal muscle.

Distal extracellular teneurin region (teneurin C-terminal associated peptide; TCAP) possesses independent intracellular calcium regulating actions, in vitro: A potential antagonist of corticotropin-releasing factor (CRF).

Teneurin C-terminal associated peptides (TCAP) are natural bioactive peptides that possess anxiety-reducing roles in animals, in vivo, and increase cell viability, in vitro. Although these peptides have some primary structural similarity to corticotropin-releasing factor (CRF), they are derived from the distal extracellular region of the teneurin transmembrane protein where they may act as separate soluble peptides after auto-catalytic cleavage from the teneurin protein following interaction with the cognate teneurin receptor, latrophilin (ADGRL), or expressed as a separate mRNA. However, although the signal transduction mechanism of TCAP in neurons has not been established, previous studies indicate an association with the intracellular calcium flux. Therefore, in this study, we have characterized the TCAP-mediated calcium response in hypothalamic cell lines using single-cell calcium methods with pharmacological antagonists to identify potential calcium channels, in vitro. Under normal circumstances, TCAP-1 reduces cytosolic calcium concentrations by uptake into the mitochondria and efflux through the plasma membrane independently of the teneurins. In doing so, TCAP-1 could inhibit the potential 'stress' -inducing actions of CRF.

Moving towards intelligent telemedicine: Computer vision measurement of human movement.

BACKGROUND: Telemedicine video consultations are rapidly increasing globally, accelerated by the COVID-19 pandemic. This presents opportunities to use computer vision technologies to augment clinician visual judgement because video cameras are so ubiquitous in personal devices and new techniques, such as DeepLabCut (DLC) can precisely measure human movement from smartphone videos. However, the accuracy of DLC to track human movements in videos obtained from laptop cameras, which have a much lower FPS, has never been investigated; this is a critical gap because patients use laptops for most telemedicine consultations. OBJECTIVES: To determine the validity and reliability of DLC applied to laptop videos to measure finger tapping, a validated test of human movement. METHOD: Sixteen adults completed finger-tapping tests at 0.5 Hz, 1 Hz, 2 Hz, 3 Hz and at maximal speed. Hand movements were recorded simultaneously by a laptop camera at 30 frames per second (FPS) and by Optotrak, a 3D motion analysis system at 250 FPS. Eight DLC neural network architectures (ResNet50, ResNet101, ResNet152, MobileNetV1, MobileNetV2, EfficientNetB0, EfficientNetB3, EfficientNetB6) were applied to the laptop video and extracted movement features were compared to the ground truth Optotrak motion tracking. RESULTS: Over 96% (529/552) of DLC measures were within +/-0.5 Hz of the Optotrak measures. At tapping frequencies >4 Hz, there was progressive decline in accuracy, attributed to motion blur associated with the laptop camera's low FPS. Computer vision methods hold potential for moving us towards intelligent telemedicine by providing human movement analysis during consultations. However, further developments are required to accurately measure the fastest movements.

The TAS Test project: a prospective longitudinal validation of new online motor-cognitive tests to detect preclinical Alzheimer's disease and estimate 5-year risks of cognitive decline and dementia.

BACKGROUND: The worldwide prevalence of dementia is rapidly rising. Alzheimer's disease (AD), accounts for 70% of cases and has a 10-20-year preclinical period, when brain pathology covertly progresses before cognitive symptoms appear. The 2020 Lancet Commission estimates that 40% of dementia cases could be prevented by modifying lifestyle/medical risk factors. To optimise dementia prevention effectiveness, there is urgent need to identify individuals with preclinical AD for targeted risk reduction. Current preclinical AD tests are too invasive, specialist or costly for population-level assessments. We have developed a new online test, TAS Test, that assesses a range of motor-cognitive functions and has capacity to be delivered at significant scale. TAS Test combines two innovations: using hand movement analysis to detect preclinical AD, and computer-human interface technologies to enable robust 'self-testing' data collection. The aims are to validate TAS Test to [1] identify preclinical AD, and [2] predict risk of cognitive decline and AD dementia. METHODS: Aim 1 will be addressed through a cross-sectional study of 500 cognitively healthy older adults, who will complete TAS Test items comprising measures of motor control, processing speed, attention, visuospatial ability, memory and language. TAS Test measures will be compared to a blood-based AD biomarker, phosphorylated tau 181 (p-tau181). Aim 2 will be addressed through a 5-year prospective cohort study of 10,000 older adults. Participants will complete TAS Test annually and subtests of the Cambridge Neuropsychological Test Battery (CANTAB) biennially. 300 participants will undergo in-person clinical assessments. We will use machine learning of motor-cognitive performance on TAS Test to develop an algorithm that classifies preclinical AD risk (p-tau181-defined) and determine the precision to prospectively estimate 5-year risks of cognitive decline and AD. DISCUSSION: This study will establish the precision of TAS Test to identify preclinical AD and estimate risk of cognitive decline and AD. If accurate, TAS Test will provide a low-cost, accessible enrichment strategy to pre-screen individuals for their likelihood of AD pathology prior to more expensive tests such as blood or imaging biomarkers. This would have wide applications in public health initiatives and clinical trials. TRIAL REGISTRATION: ClinicalTrials.gov Identifier: NCT05194787 , 18 January 2022. Retrospectively registered.

Pegylated Liposomal Doxorubicin and Kidney-Limited Thrombotic Microangiopathy in a Kidney Transplant Recipient: A Case Report.

A 64-year-old man with Kaposi sarcoma in clinical remission after treatment with pegylated liposomal doxorubicin and a history of deceased-donor kidney transplantation 4 years prior presented with a slowly progressive increase in his serum creatinine level, well-controlled hypertension, stable subnephrotic-range proteinuria, and bland urinary sediment. An allograft kidney biopsy demonstrated thrombotic microangiopathy, without clinical or laboratory features of systemic involvement. Based on the timing of drug initiation preceding thrombotic microangiopathy, complete recovery after drug withdrawal, and the absence of other etiologies, it was concluded that pegylated liposomal doxorubicin was the likely cause of kidney-limited thrombotic microangiopathy. When pegylated liposomal doxorubicin was resumed, the patient developed hypertension and kidney allograft dysfunction. A new kidney biopsy was not performed because of the overall risk benefit. The case highlights the importance of recognizing novel etiologies of thrombotic microangiopathy in kidney transplant patients with malignancy. Although Kaposi sarcoma has not been linked to thrombotic microangiopathy, pegylated liposomal doxorubicin has been increasingly associated with drug-induced thrombotic microangiopathy. To our knowledge, this is the first case report that etiologically links pegylated liposomal doxorubicin to kidney-limited thrombotic microangiopathy in a kidney transplant patient.

Turnaround Times in Melanoma BRAF Testing and the Impact on the Initiation of Systemic Therapy at a Single Tertiary Care Cancer Center.

PURPOSE: The identification of BRAF mutations in melanoma enables targeted therapy and improves patient outcomes. Barriers to BRAF molecular testing affect the quality of care and therapeutic options. METHODS: This retrospective study mapped BRAF testing timelines in adult patients with melanoma at the Princess Margaret Cancer Centre to identify obstacles to timely BRAF reporting and its impact on the initiation of therapy. RESULTS: Sixty-six cases were included. The median time between BRAF request and result was 12 days (95% CI, 8 to 15) when the BRAF test was ordered by pathology, compared with 20 days (95% CI, 16 to 23) if the test was requested by another specialist (P < .001). When the BRAF test and biopsy were performed within the same institution, the BRAF median turnaround time (TAT) was 13 days (95% CI, 6 to 19) compared with 19 days (95% CI, 16 to 21) if the sample was transferred from another institution (P = .02). Forty-seven patients received systemic therapy, and 20 had metastatic disease. In the metastatic subgroup, if the BRAF result was available at the first medical oncology visit, the initiation of treatment was 20 days (95% CI, 9.6 to 30.3), but was delayed to 31 days (95% CI, 10.8 to 51.1) if the BRAF result was not available (P = .03). CONCLUSION: This study showed variations in BRAF test results in TAT. One factor affecting this timeline is the transfer time, which can be streamlined by pathology reflex testing. Delays in TAT affect the timing and type of therapeutic intervention, especially in patients with stage IV disease.

Prediction of incident atrial fibrillation in community-based electronic health records: a systematic review with meta-analysis.

OBJECTIVE: Atrial fibrillation (AF) is common and is associated with an increased risk of stroke. We aimed to systematically review and meta-analyse multivariable prediction models derived and/or validated in electronic health records (EHRs) and/or administrative claims databases for the prediction of incident AF in the community. METHODS: Ovid Medline and Ovid Embase were searched for records from inception to 23 March 2021. Measures of discrimination were extracted and pooled by Bayesian meta-analysis, with heterogeneity assessed through a 95% prediction interval (PI). Risk of bias was assessed using Prediction model Risk Of Bias ASsessment Tool and certainty in effect estimates by Grading of Recommendations, Assessment, Development and Evaluation. RESULTS: Eleven studies met inclusion criteria, describing nine prediction models, with four eligible for meta-analysis including 9 289 959 patients. The CHADS (Congestive heart failure, Hypertension, Age>75, Diabetes mellitus, prior Stroke or transient ischemic attack) (summary c-statistic 0.674; 95% CI 0.610 to 0.732; 95% PI 0.526-0.815), CHA2DS2-VASc (Congestive heart failure, Hypertension, Age>75 (2 points), Stroke/transient ischemic attack/thromboembolism (2 points), Vascular disease, Age 65-74, Sex category) (summary c-statistic 0.679; 95% CI 0.620 to 0.736; 95% PI 0.531-0.811) and HATCH (Hypertension, Age, stroke or Transient ischemic attack, Chronic obstructive pulmonary disease, Heart failure) (summary c-statistic 0.669; 95% CI 0.600 to 0.732; 95% PI 0.513-0.803) models resulted in a c-statistic with a statistically significant 95% PI and moderate discriminative performance. No model met eligibility for inclusion in meta-analysis if studies at high risk of bias were excluded and certainty of effect estimates was 'low'. Models derived by machine learning demonstrated strong discriminative performance, but lacked rigorous external validation. CONCLUSIONS: Models externally validated for prediction of incident AF in community-based EHR demonstrate moderate predictive ability and high risk of bias. Novel methods may provide stronger discriminative performance. SYSTEMATIC REVIEW REGISTRATION: PROSPERO CRD42021245093.

What is next for screening for undiagnosed atrial fibrillation? Artificial intelligence may hold the key.

Atrial fibrillation (AF) is increasingly common, though often undiagnosed, leaving many people untreated and at elevated risk of ischaemic stroke. Current European guidelines do not recommend systematic screening for AF, even though a number of studies have shown that periods of serial or continuous rhythm monitoring in older people in the general population increase detection of AF and the prescription of oral anticoagulation. This article discusses the conflicting results of two contemporary landmark trials, STROKESTOP and the LOOP, which provided the first evidence on whether screening for AF confers a benefit for people in terms of clinical outcomes. The benefit and efficiency of systematic screening for AF in the general population could be optimized by targeting screening to only those at higher risk of developing AF. For this purpose, evidence is emerging that prediction models developed using artificial intelligence in routinely collected electronic health records can provide strong discriminative performance for AF and increase detection rates when combined with rhythm monitoring in a clinical study. We consider future directions for investigation in this field and how this could be best aligned to the current evidence base to target screening in people at elevated risk of stroke.

Predicting patient-level new-onset atrial fibrillation from population-based nationwide electronic health records: protocol of FIND-AF for developing a precision medicine prediction model using artificial intelligence.

INTRODUCTION: Atrial fibrillation (AF) is a major cardiovascular health problem: it is common, chronic and incurs substantial healthcare expenditure because of stroke. Oral anticoagulation reduces the risk of thromboembolic stroke in those at higher risk; but for a number of patients, stroke is the first manifestation of undetected AF. There is a rationale for the early diagnosis of AF, before the first complication occurs, but population-based screening is not recommended. Previous prediction models have been limited by their data sources and methodologies. An accurate model that uses existing routinely collected data is needed to inform clinicians of patient-level risk of AF, inform national screening policy and highlight predictors that may be amenable to primary prevention. METHODS AND ANALYSIS: We will investigate the application of a range of deep learning techniques, including an adapted convolutional neural network, recurrent neural network and Transformer, on routinely collected primary care data to create a personalised model predicting the risk of new-onset AF over a range of time periods. The Clinical Practice Research Datalink (CPRD)-GOLD dataset will be used for derivation, and the CPRD-AURUM dataset will be used for external geographical validation. Both comprise a sizeable representative population and are linked at patient-level to secondary care databases. The performance of the deep learning models will be compared against classic machine learning and traditional statistical predictive modelling methods. We will only use risk factors accessible in primary care and endow the model with the ability to update risk prediction as it is presented with new data, to make the model more useful in clinical practice. ETHICS AND DISSEMINATION: Permissions for CPRD-GOLD and CPRD-AURUM datasets were obtained from CPRD (ref no: 19_076). The CPRD ethical approval committee approved the study. The results will be submitted as a research paper for publication to a peer-reviewed journal and presented at peer-reviewed conferences. TRIAL REGISTRATION DETAILS: A systematic review to incorporate within the overall project was registered on PROSPERO (registration number CRD42021245093). The study was registered on ClinicalTrials.gov (NCT04657900).

O2A: One-Shot Observational Learning with Action Vectors.

We present O2A, a novel method for learning to perform robotic manipulation tasks from a single (one-shot) third-person demonstration video. To our knowledge, it is the first time this has been done for a single demonstration. The key novelty lies in pre-training a feature extractor for creating a perceptual representation for actions that we call "action vectors". The action vectors are extracted using a 3D-CNN model pre-trained as an action classifier on a generic action dataset. The distance between the action vectors from the observed third-person demonstration and trial robot executions is used as a reward for reinforcement learning of the demonstrated task. We report on experiments in simulation and on a real robot, with changes in viewpoint of observation, properties of the objects involved, scene background and morphology of the manipulator between the demonstration and the learning domains. O2A outperforms baseline approaches under different domain shifts and has comparable performance with an Oracle (that uses an ideal reward function). Videos of the results, including demonstrations, can be found in our: project-website.

Real World Outcomes and Hepatotoxicity of Infliximab in the Treatment of Steroid-Refractory Immune-Related Adverse Events.

BACKGROUND AND AIMS: Current guidelines state that infliximab is contraindicated for the treatment of immune checkpoint inhibitor-related hepatitis (ir-hepatitis) due to the risk of inducing further liver damage. As this recommendation is largely based on the use of infliximab for rheumatologic diseases, we evaluated the efficacy and hepatotoxicity of infliximab in patients with steroid-refractory immune-related adverse events (irAEs). METHODS: We retrospectively reviewed consecutive patients treated with infliximab for irAEs at Princess Margaret Cancer Centre. To assess hepatotoxicity, we compared the mean value of ALT, AST, and total bilirubin (BT) before and after infliximab treatment. We used logistic regression to assess factors associated with infliximab efficacy. RESULTS: Between January 2010 and February 2019, 56 patients were identified. The median age of the patients was 63 (27-84) years. Colitis was the most frequent toxicity (66%), followed by pneumonitis (11%). Infliximab was used to treat ir-hepatitis in one patient. The median number of infliximab doses was 1 (1-3) and led to toxicity resolution in 43 (76%) patients. The mean ALT, AST, and BT levels before and after infliximab treatment were not statistically different. The patient treated for ir-hepatitis had a complete recovery, with no incremental liver toxicity. CONCLUSIONS: In this dose-limited setting, infliximab was effective in resolving irAEs and did not induce hepatotoxicity.

Development of a Metastatic Uveal Melanoma Prognostic Score (MUMPS) for Use in Patients Receiving Immune Checkpoint Inhibitors.

Metastatic uveal melanoma (mUM) is a rare disease. There are limited data on prognostic clinical factors for overall survival (OS) in patients with mUM treated with immune checkpoint inhibitors (ICI). Retrospective and non-randomized prospective studies have reported response rates of 0-17% for anti-PD1/L1 ± anti-CTLA4 ICI in mUM, indicating a potential benefit only in a subset of patients. This study evaluates the characteristics associated with ICI benefit in patients with mUM. We performed a single-center retrospective cohort study of patients with mUM who received anti-PD1/L1 ± anti-CTLA4 ICI between 2014-2019. Clinical and genomic characteristics were collected from a chart review. Treatment response and clinical progression were determined by physician assessment. Multivariable Cox regression models and Kaplan-Meier log-rank tests were used to assess differences in clinical progression-free survival (cPFS) and OS between groups and identify clinical variables associated with ICI outcomes. We identified 71 mUM patients who received 75 lines of ICI therapy. Of these, 54 received anti-PD1/L1 alone, and 21 received anti-PD1/L1 + anti-CTLA4. Patient characteristics were: 53% female, 48% were 65 or older, 72% received one or fewer lines of prior therapy. Within our cohort, 53% of patients had developed metastatic disease <2 years after their initial diagnosis. Bone metastases were present in 12% of patients. The median cPFS was 2.7 months, and the median OS was 10.0 months. In multivariable analyses for both cPFS and OS, the following variables were associated with a good prognosis: ≥2 years from the initial diagnosis to metastatic disease (n = 25), LDH < 1.5 × ULN (n = 45), and absence of bone metastases (n = 66). We developed a Metastatic Uveal Melanoma Prognostic Score (MUMPS). Patients were divided into 3 MUMPS groups based on the number of the above-mentioned prognostic variables: Poor prognosis (0-1), Intermediate prognosis (2) and Good prognosis (3). Good prognosis patients experienced longer cPFS (6.0 months) and OS (34.5 months) than patients with intermediate (2.3 months cPFS, 9.4 months OS) and poor prognosis disease (1.8 months cPFS, 3.9 months OS); p < 0.0001. We developed MUMPS-a prognostic score based on retrospective data that is comprised of 3 readily available clinical variables (time to metastatic diagnosis, presence of bone metastases, and LDH). This MUMPS score has a potential prognostic value. Further validation in independent datasets is warranted to determine the role of this MUMPS score in selecting ICI treatment management for mUM.

Process Mining to Explore Variations in Endometrial Cancer Pathways from GP Referral to First Treatment.

The main challenge in the pathway analysis of cancer treatments is the complexity of the process. Process mining is one of the approaches that can be used to visualize and analyze these complex pathways. In this study, our purpose was to use process mining to explore variations in the treatment pathways of endometrial cancer. We extracted patient data from a hospital information system, created the process model, and analyzed the variations of the 62-day pathway from a General Practitioner referral to the first treatment in the hospital. We also analyzed the variations based on three different criteria: the type of the first treatment, the age at diagnosis, and the year of diagnosis. This approach should be of interest to others dealing with complex medical and healthcare processes.