Enabling large-scale screening of Barrett's esophagus using weakly supervised deep learning in histopathology.

Timely detection of Barrett's esophagus, the pre-malignant condition of esophageal adenocarcinoma, can improve patient survival rates. The Cytosponge-TFF3 test, a non-endoscopic minimally invasive procedure, has been used for diagnosing intestinal metaplasia in Barrett's. However, it depends on pathologist's assessment of two slides stained with H&E and the immunohistochemical biomarker TFF3. This resource-intensive clinical workflow limits large-scale screening in the at-risk population. To improve screening capacity, we propose a deep learning approach for detecting Barrett's from routinely stained H&E slides. The approach solely relies on diagnostic labels, eliminating the need for expensive localized expert annotations. We train and independently validate our approach on two clinical trial datasets, totaling 1866 patients. We achieve 91.4% and 87.3% AUROCs on discovery and external test datasets for the H&E model, comparable to the TFF3 model. Our proposed semi-automated clinical workflow can reduce pathologists' workload to 48% without sacrificing diagnostic performance, enabling pathologists to prioritize high risk cases.

Deep learning for the prediction of clinical outcomes in internet-delivered CBT for depression and anxiety.

In treating depression and anxiety, just over half of all clients respond. Monitoring and obtaining early client feedback can allow for rapidly adapted treatment delivery and improve outcomes. This study seeks to develop a state-of-the-art deep-learning framework for predicting clinical outcomes in internet-delivered Cognitive Behavioural Therapy (iCBT) by leveraging large-scale, high-dimensional time-series data of client-reported mental health symptoms and platform interaction data. We use de-identified data from 45,876 clients on SilverCloud Health, a digital platform for the psychological treatment of depression and anxiety. We train deep recurrent neural network (RNN) models to predict whether a client will show reliable improvement by the end of treatment using clinical measures, interaction data with the iCBT program, or both. Outcomes are based on total improvement in symptoms of depression (Patient Health Questionnaire-9, PHQ-9) and anxiety (Generalized Anxiety Disorder-7, GAD-7), as reported within the iCBT program. Using internal and external datasets, we compare the proposed models against several benchmarks and rigorously evaluate them according to their predictive accuracy, sensitivity, specificity and AUROC over treatment. Our proposed RNN models consistently predict reliable improvement in PHQ-9 and GAD-7, using past clinical measures alone, with above 87% accuracy and 0.89 AUROC after three or more review periods, outperforming all benchmark models. Additional evaluations demonstrate the robustness of the achieved models across (i) different health services; (ii) geographic locations; (iii) iCBT programs, and (iv) client severity subgroups. Results demonstrate the robust performance of dynamic prediction models that can yield clinically helpful prognostic information ready for implementation within iCBT systems to support timely decision-making and treatment adjustments by iCBT clinical supporters towards improved client outcomes.

A Machine Learning Approach to Understanding Patterns of Engagement With Internet-Delivered Mental Health Interventions.

Importance: The mechanisms by which engagement with internet-delivered psychological interventions are associated with depression and anxiety symptoms are unclear. Objective: To identify behavior types based on how people engage with an internet-based cognitive behavioral therapy (iCBT) intervention for symptoms of depression and anxiety. Design, Setting, and Participants: Deidentified data on 54 604 adult patients assigned to the Space From Depression and Anxiety treatment program from January 31, 2015, to March 31, 2019, were obtained for probabilistic latent variable modeling using machine learning techniques to infer distinct patient subtypes, based on longitudinal heterogeneity of engagement patterns with iCBT. Interventions: A clinician-supported iCBT-based program that follows clinical guidelines for treating depression and anxiety, delivered on a web 2.0 platform. Main Outcomes and Measures: Log data from user interactions with the iCBT program to inform engagement patterns over time. Clinical outcomes included symptoms of depression (Patient Health Questionnaire-9 [PHQ-9]) and anxiety (Generalized Anxiety Disorder-7 [GAD-7]); PHQ-9 cut point greater than or equal to 10 and GAD-7 scores greater than or equal to 8 were used to define depression and anxiety. Results: Patients spent a mean (SD) of 111.33 (118.92) minutes on the platform and completed 230.60 (241.21) tools. At baseline, mean PHQ-9 score was 12.96 (5.81) and GAD-7 score was 11.85 (5.14). Five subtypes of engagement were identified based on patient interaction with different program sections over 14 weeks: class 1 (low engagers, 19 930 [36.5%]), class 2 (late engagers, 11 674 [21.4%]), class 3 (high engagers with rapid disengagement, 13 936 [25.5%]), class 4 (high engagers with moderate decrease, 3258 [6.0%]), and class 5 (highest engagers, 5799 [10.6%]). Estimated mean decrease (SE) in PHQ-9 score was 6.65 (0.14) for class 3, 5.88 (0.14) for class 5, and 5.39 (0.14) for class 4; class 2 had the lowest rate of decrease at -4.41 (0.13). Compared with PHQ-9 score decrease in class 1, the Cohen d effect size (SE) was -0.46 (0.014) for class 2, -0.46 (0.014) for class 3, -0.61 (0.021) for class 4, and -0.73 (0.018) for class 5. Similar patterns were found across groups for GAD-7. Conclusions and Relevance: The findings of this study may facilitate tailoring interventions according to specific subtypes of engagement for individuals with depression and anxiety. Informing clinical decision needs of supporters may be a route to successful adoption of machine learning insights, thus improving clinical outcomes overall.

Delayed ischaemic neurological deficits after subarachnoid haemorrhage are associated with clusters of spreading depolarizations.

Progressive ischaemic damage in animals is associated with spreading mass depolarizations of neurons and astrocytes, detected as spreading negative slow voltage variations. Speculation on whether spreading depolarizations occur in human ischaemic stroke has continued for the past 60 years. Therefore, we performed a prospective multicentre study assessing incidence and timing of spreading depolarizations and delayed ischaemic neurological deficit (DIND) in patients with major subarachnoid haemorrhage (SAH) requiring aneurysm surgery. Spreading depolarizations were recorded by electrocorticography with a subdural electrode strip placed on cerebral cortex for up to 10 days. A total of 2110 h recording time was analysed. The clinical state was monitored every 6 h. Delayed infarcts after SAH were verified by serial CT scans and/or MRI. Electrocorticography revealed 298 spreading depolarizations in 13 of the 18 patients (72%). A clinical DIND was observed in seven patients 7.8 days (7.3, 8.2) after SAH. DIND was time-locked to a sequence of recurrent spreading depolarizations in every single case (positive and negative predictive values: 86 and 100%, respectively). In four patients delayed infarcts developed in the recording area. As in the ischaemic penumbra of animals, delayed infarction was preceded by progressive prolongation of the electrocorticographic depression periods associated with spreading depolarizations to >60 min in each case. This study demonstrates that spreading depolarizations have a high incidence in major SAH and occur in ischaemic stroke. Repeated spreading depolarizations with prolonged depression periods are an early indicator of delayed ischaemic brain damage after SAH. In view of experimental evidence and the present clinical results, we suggest that spreading depolarizations with prolonged depressions are a promising target for treatment development in SAH and ischaemic stroke.

Inactivation of platelet glycoprotein IIb/IIIa receptor by nitric oxide donor 3-morpholino-sydnonimine.

Nitric oxide (NO) is known to modulate platelet adhesion and aggregation, which are both mediated by fibrinogen receptor glycoprotein (GP)IIb/IIIa. To investigate effects of NO on GPIIb/IIIa activation and inactivation, platelets were exposed to NO donor 3-morpholino-sydnonimine (SIN-1) before and after stimulation with different agonists: thromboxane analog U-46619, epinephrine, adenosine diphosphate, human a-thrombin, and phorbol-12-myristate-13-acetate (0.02 micromol/l). (1) Flow cytometry analysis of SIN-1-pre-incubated samples using PAC-1 monoclonal antibody revealed an inhibition of receptor activation by 80.9 +/- 1.2, 71.3 +/- 1.8, 56 +/- 4.9, 87 +/- 3.4, and 56 +/- 5% (mean +/- SEM, relative to baseline). (2) Administration of SIN-1 after stimulation reversed receptor activation by 55 +/- 5.2, 56 +/- 2.0, 53 +/- 5.4, 42 +/- 4.3, and 44 +/- 5%, respectively. With 0.1 micromol/l phorbol-12-myristate-13-acetate, GPIIb/IIIa activation was irreversible. (3) SIN-1 effects could completely be blocked by equimolar addition of guanylyl cyclase inhibitor 1H(1,2,4)oxadiazolo(4,3-alpha)quinoxalin-1-on. (4) Spontaneous receptor closure after activation with human alpha-thrombin and adenosine diphosphate was not due to platelet-derived NO; SIN-1, however accelerated spontaneous receptor inactivation. (5) SIN-1-inactivated receptors still responded to stimulation. In conclusion, SIN-1 or NO modulates GPIIb/IIIa conformational change in vitro via guanosine 3',5'-monophosphate-dependent pathways. Whereas spontaneous receptor inactivation may be enhanced by exogenous NO, platelet-derived NO is not involved in receptor inactivation.