Search

BACKGROUND Microscopic inflammation has been shown to be an important indicator of disease activity in ulcerative colitis (UC). However, manual histologic scoring is semi-quantitative and subject to interobserver variation, and AI-based solutions often lack interpretability. Here we report two distinct quantitative approaches to predict disease activity scores and histological remission using AI-powered digital pathology. Both the random forest classifier (RFC) and graph neural network (GNN) further provide explainability and biological insight by identifying histological features informing model predictions. METHODS Convolutional neural networks (CNNs) were developed using >162k annotations on 820 WSI of H&E-stained colorectal biopsies for pixel-level identification of tissue regions (e.g. crypt abscesses, erosion/ulceration) and cell types (e.g. neutrophils, plasma cells). All WSI were scored by 5 board-certified pathologists using the Nancy Histological Index (NHI) to establish consensus ground truth. A rich, quantitative set of human interpretable features that capture CNN predictions of the tissue region and cell type across each WSI was extracted and used to train a RFC to predict slide-level NHI score. To test the hypothesis that tissue region spatial relationships and cellular composition can inform AI-based predictions of disease activity, a separate GNN was trained, using nodes defined by spatially-resolved CNN model-generated outputs, to predict NHI score. The RFC and GNN also predicted histologic remission (NHI RESULTS The RFC and GNN both predicted histologic remission with high accuracy (weighted kappa 0.87 and 0.85, respectively). Both models also identified histologic features relevant to disease activity predictions. Some features are well established, e.g. infiltrated epithelium or neutrophil cell features distinguish cases with histologic remission. The models also identified features beyond those assessed by the NHI, e.g. area proportion of basal plasmacytosis associated with predictions of NHI 2 and 3. Other features not previously implicated in UC disease activity were also identified, e.g. intraepithelial lymphocytes differentiate cases with NHI 3. CONCLUSIONS We report quantitative and interpretable AI-powered approaches for UC histological assessment. CNN identification of UC histology was used as input to two distinct disease activity classifiers that showed strong concordance with consensus pathologist scoring. Both approaches provide interpretable features that explain model predictions and that may be used to inform biomarker selection and clinical development efforts.

BACKGROUND Histology is emerging as a key therapeutic endpoint for ulcerative colitis driven by associations between histologic response and long-term outcomes. However, existing scoring systems are subjective and consequently have variable inter- and intra-reader variability. Geboes scoring is a well-established system for ulcerative colitis histologic assessment that has previously been used to define thresholds for histo-endoscopic mucosal improvement (Geboes Score ≤3.1, together with Mayo score 0 or 1) and histologic remission (Geboes Score METHODS 3,148 WSI were scored by three expert gastrointestinal pathologists and the median consensus score was used to determine the Geboes score for each slide as ground truth. ML models were trained on median consensus scores to predict the Geboes score and subscores for each slide. Model performance vs. pathologist median consensus score was measured using accuracy and the F1 score, which accounts for both false positive and false negative errors. RESULTS The ML-based model performance, measured against median consensus scores of three pathologists, showed strong performance at predicting overall Geboes Score, with a quadratic kappa of 0.89. The model was also able to predict both histologic improvement and histologic remission with high accuracy. For predicting histological improvement as defined by a Geboes Score of ≤3.1, the model showed accuracy of 0.92 and F1 score of 0.92 (Figure 1). For predicting histological remission as defined by a Geboes Score of < 2, the model showed accuracy of 0.91 and F1 score of 0.89 (Figure 2). CONCLUSIONS We report a ML-based approach for predicting Geboes score and Geboes score-based key thresholds of histologic improvement and histologic remission. Model predictions show high accuracy compared to median consensus pathologist scores. This approach may enable standardized, reproducible and accurate prediction of these clinically relevant thresholds to better measure histologic disease activity and treatment response in clinical trials.

Ulcerative colitis (UC) is a chronic inflammatory bowel disease that is characterized by a relapsing and remitting course. Appropriate assessment of disease activity is critical for adequate treatment decisions. In addition to endoscopic mucosal healing, histologic remission is emerging as a treatment target and a key factor in the evaluation of disease activity and therapeutic efficacy. However, there is no standardized definition of histologic remission, limiting the utility of histologic scoring, and manual pathologist evaluation is subject to intra-and inter-observer variability. Machine learning approaches are increasingly being developed to aid pathologists in accurate and reproducible scoring of histology, and can enable sensitive assessment of clinically relevant features. Here we report a proof-of-concept study using the PathAI platform to develop ML models for identification and quantification of UC histological features directly from hematoxylin and eosin (H&E)-stained whole slide images. Model-predicted histological features were used to quantify tissue area proportions and cell count proportions and densities, which correlated with disease severity and pathologist-assigned Nancy Histological Index (NHI) scores. Moreover, using multivariate analysis based on selected model-predicted histological features, we were able to accurately predict NHI scores, with a weighted kappa (k=0.93) and Spearman correlation (ρ=0.93, p

206 Background: In prostate cancer, homologous recombination deficiency (HRD) is associated with poor prognosis, and sensitivity to DNA damaging agents and DNA damage repair (DDR) inhibitors. As new classes of DDR inhibitors become available, identifying patients with HRD will be critical for treatment selection. Here, we present machine learning (ML)-based models trained to predict HRD status directly from hematoxylin and eosin (H&E) whole slide images (WSI). Methods: ML models were trained to predict and segment cells and tissue regions within the tumor microenvironment (TME) using annotated (N=91,021 annotations) WSI of H&E-stained resections from the cancer genome atlas prostate adenocarcinoma (TCGA PRAD) dataset (N=401) and needle core biopsies from a proprietary dataset (N=1,000). Quantified Human Interpretable Features (HIFs) that describe the TME composition were extracted. Three models were trained to predict HRD status using 373 WSI with known HRD score (TCGA PRAD; train N=259, validation N=76, and test N=38). Two models used input from the TME model: An HIF multivariate logistic regression model, and a graph neural network (GNN) where predictions are based on the complex spatial relationships within the TME. An end-to-end (E2E) multiple instance learning model predicted directly from the WSI. Two cutoffs for HRD were defined using Gaussian Mixture Models, resulting in 99 WSI (train N=72, validation N=18, and test N=9) positive for the Genomic Instability (>16 events) cutoff, and 58 WSI (train N=44, validation N=10, test N=4) positive for the Genomic Instability (>22 events) cutoff. An independent validation set of 45 biopsies and 16 resections from a biobank of metastatic castration resistant prostate cancer with HRD status determined by whole-exome sequencing was compared to ML model H&E-based HRD prediction. Results: In the TCGA test set of resection samples, all three models moderately or strongly predicted HRD status, with the HIF model showing the best performance (AUROC 0.87, sensitivity 0.88, specificity 0.62). The same HIF model performed equally well (AUROC 0.85, Sensitivity 0.93, specificity 0.67) in the resection samples from the independent validation set. However, the model performance went down (AUROC 0.69, sensitivity 0.91, specificity: 0.3) when both resection and needle biopsy samples were included, highlighting the importance of a representative training set to achieve robust performance in a real world setting. Further model training and validation with a more diverse dataset is required to accurately assess the performance of the model on needle biopsies. Conclusions: ML models trained on resection prostate cancer samples performed well in predicting HRD status when applied to the same sample type, demonstrating the potential of ML models to predict genomic biomarkers status in surgical specimens for treatment decision.

The design of a mobile medication manager within a broader family and elder-centric collaboration platform faces challenges of usability and wide applicability. To inform the development and use cases of eldercare apps, we present the preliminary results of a usability study of an iOS and Android app intended for both family members and aging adults for the mobile management of medication lists. Seven participants were recorded during the performance of eight typical use-case scenarios of the medication portion of the InfoSAGE app. Audio and video recordings were analyzed for themes and events. The aim of this paper is to help inform future design choices for eldercare mobile apps.

Objective Adherence to antiretroviral therapy (ART) is paramount to successful long-term suppression of human immunodeficiency virus (HIV). For poorly adherent patients with HIV, barriers to remaining adherent may be overcome by the implementation of targeted interventions delivered via mobile devices. This systematic review is focused specifically on mobile phone technologies to deliver adherence interventions in HIV/acquired immunodeficiency syndrome (AIDS) populations. Methods This review (PROSPERO #CRD42017065131) systematically extracted data from published literature from five databases on mobile phone interventions to improve adherence to ART for HIV. The reported studies had been conducted between 2007 and 2017. Risk of bias was assessed using the Cochrane method ranking each criterion as low, high, or unclear risk of bias. Results Of the 835 articles returned, we identified 26 randomized controlled trials (RCTs), retrospective and prospective cohort trials, or mixed method studies with a comparison group that fit criteria for inclusion. No standard measure of adherence was consistent throughout the examined studies, and assessments by self-report, pill counting, and medication event monitoring system (MEMS) were utilized. The studies reported mixed results, with 17 reporting significant improvements to adherence, 3 reporting improvements without supplying p-values, and 6 reporting no significant change or a reduction in adherence. Conclusion The mixed nature of the results exemplifies the need for more comprehensive approaches and larger scale trials to confirm results observed in limited cohort sizes. To better retain satisfactory adherence within the HIV population, and especially in low-resource settings, we recommend that future interventions incorporate multiple strategies: mobile-based reminders, social support structures, and personalized content.

Aging creates new information and communication needs for families who are helping to coordinate care for frail parents. To identify how information and communication needs evolve with the aging process, we created a living laboratory of families, supported by an online private social network with tools for care coordination. Site registrants are invite to participate in a more in-depth survey-based longitudinal study. In year one, we assessed the feasibility of an online living laboratory. During this first year, 155 individuals registered on InfoSAGE, and 26% opted into the more in-depth longitudinal study. The survey response rate for those in the study was 61%. We present here a descriptive analysis of our early participants and networks, as well as barriers to participation that the study team encountered.