Search

Abstract The utility of deep neural nets has been demonstrated for mapping hematoxylin-and-eosin (H&E) stained image features to expression of individual genes. However, these models have not been employed to discover clinically relevant spatial biomarkers. Here we develop MOSBY (Multi-Omic translation of whole slide images for Spatial Biomarker discoverY) that leverages contrastive self-supervised pretraining to extract improved H&E whole slide images features, learns a mapping between image and bulk omic profiles (RNA, DNA, and protein), and utilizes tile-level information to discover spatial biomarkers. We validate MOSBY gene and gene set predictions with spatial transcriptomic and serially-sectioned CD8 IHC image data. We demonstrate that MOSBY-inferred colocalization features have survival-predictive power orthogonal to gene expression, and enable concordance indices highly competitive with survival-trained multimodal networks. We identify and validate (1) an ER stress-associated colocalization feature as a chemotherapy-specific risk factor in lung adenocarcinoma, and (2) the colocalization of T effector cell vs cysteine signatures as a negative prognostic factor in multiple cancer indications. The discovery of clinically relevant biologically interpretable spatial biomarkers showcases the utility of the model in unraveling novel insights in cancer biology as well as informing clinical decision-making.

IntroductionClinician implicit racial bias (IB) may lead to lower quality care and adverse health outcomes for Black patients. Educational efforts to train clinicians to mitigate IB vary widely and have insufficient evidence of impact. We developed and pilot-tested an evidence-based clinician IB curriculum, “REACHing Equity.”MethodsTo assess acceptability and feasibility, we conducted an uncontrolled one-arm pilot trial with post-intervention assessments. REACHing Equity is designed for clinicians to: (1) acquire knowledge about IB and its impact on healthcare, (2) increase awareness of one's own capacity for IB, and (3) develop skills to mitigate IB in the clinical encounter. We delivered REACHing Equity virtually in three facilitated, interactive sessions over 7–9 weeks. Participants were health care providers who completed baseline and end-of-study evaluation surveys.ResultsOf approximately 1,592 clinicians invited, 37 participated, of whom 29 self-identified as women and 24 as non-Hispanic White. Attendance averaged 90% per session; 78% attended all 3 sessions. Response rate for evaluation surveys was 67%. Most respondents agreed or strongly agreed that the curriculum objectives were met, and that REACHing Equity equipped them to mitigate the impact of implicit bias in clinical care. Participants consistently reported higher self-efficacy for mitigating IB after compared to before completing the curriculum.ConclusionsDespite apparent barriers to clinician participation, we demonstrated feasibility and acceptability of the REACHing Equity intervention. Further research is needed to develop objective measures of uptake and clinician skill, test the impact of REACHing Equity on clinically relevant outcomes, and refine the curriculum for uptake and dissemination.ClinicalTrials.gov ID: NCT03415308.

Background and Purpose: No consensus exists on the ideal duration of rehabilitation in patients with intracerebral hemorrhage (ICH). The aim of this study is to identify demographic and clinical characteristics associated with rehabilitation duration (RD) in patients with ICH during hospitalization. Methods: This retrospective study followed consecutive patients admitted to a tertiary care center between 2016 and 2019 with primary diagnosis of ICH. The primary outcome, RD was calculated by adding the total number of therapy (speech, occupational, and physical) minutes received during admission, divided by the hospital length of stay. Variables abstracted included demographic and clinical characteristics (ICH score, neurosurgical procedure). Multiple linear regression models were used to measure adjusted association between select predictors and mean RD. Results: A total of 316 ICH patients (62.5 ± 15.9 years, 49 % White) were included in the final analysis. Compared to Whites, other racial minorities (β= -9.017, p = 0.002) received rehabilitation therapy for a significantly shorter duration in the adjusted model. Age was significantly associated with having higher RD (β=0.320, p < 0.001). Patients with lobar ICH (β= -7.486, p = 0.014) had significantly shorter RD compared to deep. ICH score was significantly associated with having a lower RD (β= -8.624, p < 0.001). Conclusion: Age, race, ICH score, and location were significantly associated with RD. Non-White patients had significantly shorter RD, indicating a potential racial disparity in the rehabilitation of patients with ICH.

Background Racial and ethnic minority groups are at a higher stroke risk and have poor poststroke outcomes. The aim of this study was to assess the frequency of race reporting and proportions of race and ethnicity representation in stroke‐related clinical trials. Methods and Results This is a descriptive study of stroke‐related clinical trials completed between January 1, 2010 and December 31, 2020, and registered on ClinicalTrials.gov. Trials conducted in the United States, related to stroke and enrolling participants ≥18 years, were considered eligible. Trials were reviewed for availability of published results, data on race and ethnicity distribution, and trial characteristics. Overall, 60.1% of published trials reported race or ethnicity of participants, with a 2.6‐fold increase in reporting between 2010 and 2020. White patients represented 65.0% of the participants, followed by 24.8% Black, 2.4% Asian or Pacific Islander, and

Abstract Background For patients and their intimate partners, advanced cancer poses significant challenges that can negatively impact both individuals and their relationship. Prior studies have found evidence that couple-based communication skills interventions can to be beneficial for patients and partners. However, these studies have been limited by reliance on in-person treatment delivery and have not targeted couples at high risk for poor outcomes. This study tests the efficacy of a Couples Communication Skills Training (CCST) intervention delivered via videoconference for couples reporting high levels of holding back from discussing cancer-related concerns, a variable associated with poorer psychological and relationship functioning. Methods This RCT is designed to evaluate the efficacy of CCST in improving patient and partner relationship functioning (primary outcome). Secondary outcomes include patient and partner psychological functioning and patient symptoms and health care use. We also examine the role of objective and self-reported communication behaviors as mediators of treatment effects. Two hundred thirty patients with advanced lung, gastrointestinal, genitourinary, and breast cancer and their partners will be randomized to CCST or an education control intervention. Participants in both conditions complete self-reported outcome measures at baseline, mid-treatment, post-treatment, and 3 months post-treatment. Objective measures of communication are derived from video-recorded couple conversations collected at baseline and post-treatment. An implementation-related process evaluation (assessing implementation outcomes and potential barriers to/facilitators of implementation) will be conducted to inform future efforts to implement CCST in real-world settings. Discussion This trial can yield important new knowledge about effective ways to improve patient and partner adjustment to advanced cancer. Trial registration This study trial is registered at clinicaltrials.gov (Trial # NCT04590885); registration date: October 19, 2020.

Our objective was to develop an automated deep-learning-based method to evaluate cellularity in rat bone marrow hematoxylin and eosin whole slide images for preclinical safety assessment. We trained a shallow CNN for segmenting marrow, 2 Mask R-CNN models for segmenting megakaryocytes (MKCs), and small hematopoietic cells (SHCs), and a SegNet model for segmenting red blood cells. We incorporated the models into a pipeline that identifies and counts MKCs and SHCs in rat bone marrow. We compared cell segmentation and counts that our method generated to those that pathologists generated on 10 slides with a range of cell depletion levels from 10 studies. For SHCs, we compared cell counts that our method generated to counts generated by Cellpose and Stardist. The median Dice and object Dice scores for MKCs using our method vs pathologist consensus and the inter- and intra-pathologist variation were comparable, with overlapping first-third quartile ranges. For SHCs, the median scores were close, with first-third quartile ranges partially overlapping intra-pathologist variation. For SHCs, in comparison to Cellpose and Stardist, counts from our method were closer to pathologist counts, with a smaller 95% limits of agreement range. The performance of the bone marrow analysis pipeline supports its incorporation into routine use as an aid for hematotoxicity assessment by pathologists. The pipeline could help expedite hematotoxicity assessment in preclinical studies and consequently could expedite drug development. The method may enable meta-analysis of rat bone marrow characteristics from future and historical whole slide images and may generate new biological insights from cross-study comparisons.