A population-level digital histologic biomarker for enhanced prognosis of invasive breast cancer.

Breast cancer is a heterogeneous disease with variable survival outcomes. Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which are qualitative and do not account for noncancerous elements within the tumor microenvironment. Here we present the Histomic Prognostic Signature (HiPS), a comprehensive, interpretable scoring of the survival risk incurred by breast tumor microenvironment morphology. HiPS uses deep learning to accurately map cellular and tissue structures to measure epithelial, stromal, immune, and spatial interaction features. It was developed using a population-level cohort from the Cancer Prevention Study-II and validated using data from three independent cohorts, including the Prostate, Lung, Colorectal, and Ovarian Cancer trial, Cancer Prevention Study-3, and The Cancer Genome Atlas. HiPS consistently outperformed pathologists in predicting survival outcomes, independent of tumor-node-metastasis stage and pertinent variables. This was largely driven by stromal and immune features. In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve patient prognosis.

A population-level computational histologic signature for invasive breast cancer prognosis.

Breast cancer is a heterogeneous disease with variable survival outcomes. Pathologists grade the microscopic appearance of breast tissue using the Nottingham criteria, which is qualitative and does not account for non-cancerous elements within the tumor microenvironment (TME). We present the Histomic Prognostic Signature (HiPS), a comprehensive, interpretable scoring of the survival risk incurred by breast TME morphology. HiPS uses deep learning to accurately map cellular and tissue structures in order to measure epithelial, stromal, immune, and spatial interaction features. It was developed using a population-level cohort from the Cancer Prevention Study (CPS)-II and validated using data from three independent cohorts, including the PLCO trial, CPS-3, and The Cancer Genome Atlas. HiPS consistently outperformed pathologists' performance in predicting survival outcomes, independent of TNM stage and pertinent variables. This was largely driven by stromal and immune features. In conclusion, HiPS is a robustly validated biomarker to support pathologists and improve prognosis.

Does High-Dose Thromboprophylaxis Improve Outcomes in COVID-19 Patients? A Meta-analysis of Comparative Studies.

Background Thromboembolism remains a detrimental complication of novel coronavirus disease (COVID-19) despite the use of prophylactic doses of anticoagulation Objectives This study aimed to compare different thromboprophylaxis strategies in COVID-19 patients Methods We conducted a systematic database search until June 30, 2022. Eligible studies were randomized (RCTs) and nonrandomized studies that compared prophylactic to intermediate or therapeutic doses of anticoagulation in adult patients with COVID-19, admitted to general wards or intensive care unit (ICU). Primary outcomes were mortality, thromboembolism, and bleeding events. Data are analyzed separately in RCTs and non-RCTs and in ICU and non-ICU patients. Results. We identified 682 studies and included 53 eligible studies. Therapeutic anticoagulation showed no mortality benefit over prophylactic anticoagulation in four RCTs (odds ratio [OR] = 0.67, 95% confidence interval [CI], 0.18-2.54). Therapeutic anticoagulation didn't improve mortality in ICU or non-ICU patients. Risk of thromboembolism was significantly lower among non-ICU patients who received enhanced (therapeutic/intermediate) anticoagulation (OR = 0.21, 95% CI, 0.06-0.74). Two additional RCTs (Multiplatform Trial and HEP-COVID), not included in quantitative meta-analysis, analyzed non-ICU patients, and reported a similar benefit with therapeutic-dose anticoagulation. Therapeutic anticoagulation was associated with a significantly higher risk of bleeding events among non-randomized studies (OR = 3.45, 95% CI, 2.32-5.13). Among RCTs, although patients who received therapeutic-dose anticoagulation had higher numbers of bleeding events, these differences were not statistically significant. Studies comparing prophylactic and intermediate-dose anticoagulation showed no differences in primary outcomes. Conclusion There is a lack of mortality benefit with therapeutic-dose over prophylactic-dose anticoagulation in ICU and non-ICU COVID-19 patients. Therapeutic anticoagulation significantly decreased risk of thromboembolism risk in some of the available RCTs, especially among non-ICU patients. This potential benefit, however, may be counter balanced by higher risk of bleeding. Individualized assessment of patient's bleeding risk will ultimately impact the true clinical benefit of anticoagulation in each patient. Finally, we found no mortality or morbidity benefit with intermediate-dose anticoagulation.

NuCLS: A scalable crowdsourcing approach and dataset for nucleus classification and segmentation in breast cancer.

BACKGROUND: Deep learning enables accurate high-resolution mapping of cells and tissue structures that can serve as the foundation of interpretable machine-learning models for computational pathology. However, generating adequate labels for these structures is a critical barrier, given the time and effort required from pathologists. RESULTS: This article describes a novel collaborative framework for engaging crowds of medical students and pathologists to produce quality labels for cell nuclei. We used this approach to produce the NuCLS dataset, containing >220,000 annotations of cell nuclei in breast cancers. This builds on prior work labeling tissue regions to produce an integrated tissue region- and cell-level annotation dataset for training that is the largest such resource for multi-scale analysis of breast cancer histology. This article presents data and analysis results for single and multi-rater annotations from both non-experts and pathologists. We present a novel workflow that uses algorithmic suggestions to collect accurate segmentation data without the need for laborious manual tracing of nuclei. Our results indicate that even noisy algorithmic suggestions do not adversely affect pathologist accuracy and can help non-experts improve annotation quality. We also present a new approach for inferring truth from multiple raters and show that non-experts can produce accurate annotations for visually distinctive classes. CONCLUSIONS: This study is the most extensive systematic exploration of the large-scale use of wisdom-of-the-crowd approaches to generate data for computational pathology applications.

Explainable nucleus classification using Decision Tree Approximation of Learned Embeddings.

MOTIVATION: Nucleus detection, segmentation and classification are fundamental to high-resolution mapping of the tumor microenvironment using whole-slide histopathology images. The growing interest in leveraging the power of deep learning to achieve state-of-the-art performance often comes at the cost of explainability, yet there is general consensus that explainability is critical for trustworthiness and widespread clinical adoption. Unfortunately, current explainability paradigms that rely on pixel saliency heatmaps or superpixel importance scores are not well-suited for nucleus classification. Techniques like Grad-CAM or LIME provide explanations that are indirect, qualitative and/or nonintuitive to pathologists. RESULTS: In this article, we present techniques to enable scalable nuclear detection, segmentation and explainable classification. First, we show how modifications to the widely used Mask R-CNN architecture, including decoupling the detection and classification tasks, improves accuracy and enables learning from hybrid annotation datasets like NuCLS, which contain mixtures of bounding boxes and segmentation boundaries. Second, we introduce an explainability method called Decision Tree Approximation of Learned Embeddings (DTALE), which provides explanations for classification model behavior globally, as well as for individual nuclear predictions. DTALE explanations are simple, quantitative, and can flexibly use any measurable morphological features that make sense to practicing pathologists, without sacrificing model accuracy. Together, these techniques present a step toward realizing the promise of computational pathology in computer-aided diagnosis and discovery of morphologic biomarkers. AVAILABILITY AND IMPLEMENTATION: Relevant code can be found at github.com/CancerDataScience/NuCLS. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Severe multiorgan toxicity after first dose of Capizzi methotrexate in a young adult patient with acute lymphocytic leukaemia.

Methotrexate is a versatile antineoplastic and immunosuppressive agent. We report a case of a young adult on the Cancer and Leukaemia Group B 10403 treatment protocol for B-cell acute lymphoblastic leukaemia. She has previously completed the induction and consolidation phases with good tolerance then started on Capizzi methotrexate during the interim maintenance phase. Few days after receiving one intermediate dose of methotrexate, she developed severe multiorgan toxicities including pancytopaenia and several dermatologic toxicities. The patient underwent extensive diagnostic workup, with all results negative, pointing eventually towards severe methotrexate toxicity. This case highlights the broad spectrum of toxicities that can occur even with low doses of methotrexate. Capizzi methotrexate therapy implies no leucovorin therapy, hence putting patients at risk for multiorgan toxicity. Our experience reinforces the importance of close monitoring for patients receiving methotrexate, regardless of dose, and the prompt administration of high-dose leucovorin once toxicity suspected.

Predictors of Survival among Early Onset Pancreatic Adenocarcinoma Patients A Tertiary Care Center Experience.

OBJECTIVES: To characterize clinical features of early onset pancreatic adenocarcinoma (EOPC) patients and explore prognostic factors affecting their survival. Methods: Retrospective review of 95 patients, 45 years old, who presented to the University of Alabama Hospitals with pancreatic adenocarcinoma from September 1998 to June 2018. Results: Median survival time was 12.9 months for all patients. Obesity, male gender, race, and tumor location were not associated with survival. Smoking at time of diagnosis increased risk of death by three folds (HR 3.05, 95% CI, 1.45 - 6.40). Risk of death decreased by 64% (HR 0.36, 95% CI, 0.16 - 0.78) if patients underwent surgery. Median survival was 119.5 months for stage I, 29.9 months for stage II, 23.23 months for stage III, and 6.3 months for stage IV patients. The survival benefit of chemotherapy was only significant with the use of FOLFIRINOX. Conclusions: Some established prognostic features in typical pancreatic adenocarcinoma patients are not predictive of survival in young patients. Cigarette smoking, a known risk factor for the development of EOPC, is also a significant predictor of survival in this patient population. Efforts to improve prognosis of EOPC include early detection, tobacco control, individualized treatment protocols, and studying the biological behavior.

Clinical Utilization and Cost of Thrombophilia Testing in Patients with Venous Thromboembolism.

Introduction Testing for inherited and acquired thrombophilias adds to the cost of care of patients with venous thromboembolism (VTE), though results may not influence patient management. Methods This is a single-center, retrospective study conducted at Emory University Hospitals from January to December 2015 to (1) determine the pattern of thrombophilia testing in patients with VTE, (2) study the impact of results of thrombophilia testing on clinical decision-making, and (3) determine the direct costs of thrombophilia testing in patients with VTE. Results Of the 266 eligible patients, 189 (71%) underwent testing; 51 (26.9%) tested positive and the results impacted management in 32 (16.9%) of tested patients. Patient undergoing testing were more likely to be younger than 40 years (30.9 vs. 18.2%), have had prior pregnancy loss (9.0 vs. 0%), or known family history of hypercoagulability (24.9 vs. 10.4%), and were less likely to have had provoked VTE (37 vs. 79.2%). The most common thrombophilias tested were antiphospholipid syndrome (60.1%), factor V Leiden (59.7%), and prothrombin gene mutation (57.5%). Direct costs of thrombophilia testing were $2,364.32 per patient, $12,331.55 to diagnose 1 positive, and $19,653.41 per patient-management affected. Conclusion We noted significant variability in selection of patients and panel of tests, sparse utilization of test results in patient management, but high cost associated with thrombophilia testing in patients with VTE. With guidelines advocating selective use of thrombophilia testing and attention to potential impact of test results in patient management, we propose the need for measures at institutional levels to improve test-ordering practices.

Structured crowdsourcing enables convolutional segmentation of histology images.

MOTIVATION: While deep-learning algorithms have demonstrated outstanding performance in semantic image segmentation tasks, large annotation datasets are needed to create accurate models. Annotation of histology images is challenging due to the effort and experience required to carefully delineate tissue structures, and difficulties related to sharing and markup of whole-slide images. RESULTS: We recruited 25 participants, ranging in experience from senior pathologists to medical students, to delineate tissue regions in 151 breast cancer slides using the Digital Slide Archive. Inter-participant discordance was systematically evaluated, revealing low discordance for tumor and stroma, and higher discordance for more subjectively defined or rare tissue classes. Feedback provided by senior participants enabled the generation and curation of 20 000+ annotated tissue regions. Fully convolutional networks trained using these annotations were highly accurate (mean AUC=0.945), and the scale of annotation data provided notable improvements in image classification accuracy. AVAILABILITY AND IMPLEMENTATION: Dataset is freely available at: https://goo.gl/cNM4EL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Direct oral anticoagulants in patients with venous thromboembolism and thrombophilia: a systematic review and meta-analysis.

Essentials We investigated direct oral anticoagulant (DOAC) use in venous thromboembolism and thrombophilia. A comprehensive search identified 10 studies, 8 of which were included in a meta-analysis. DOACs were overall safe and effective in patients with venous thromboembolism and thrombophilia. Efficacy/safety of DOACs was maintained in low-risk antiphospholipid syndrome patient subgroup. SUMMARY: Background Direct oral anticoagulants (DOACs) are increasingly used in acute and long-term treatment of venous thromboembolism (VTE). However, their role in management of thrombophilia-associated VTE is controversial. Methods Through a comprehensive search on MEDLINE, Cochrane Library, and Clinicaltrials.gov, we identified 10 eligible studies, 8 of which reporting data on 1994 thrombophilia patients were included in a random-effects meta-analysis. Eligible studies were phase 2 to 3 randomized controlled trials comparing DOACs to vitamin K antagonists (VKAs) in patients with VTE, including those with thrombophilia. Results Of eight studies included in meta-analysis, four evaluated rivaroxaban, three dabigatran, and one edoxaban. No results could be obtained on apixaban use. The rates of VTE recurrence (RR, 0.70; 95% CI, 0.34-1.44; I2  = 0%) and major/clinically relevant non-major bleeding events (RR, 0.92; 95% CI, 0.62-1.36; I2  = 23%) were similar between thrombophilia patients treated with DOACs compared to VKAs. Results were comparable to findings in patients without known thrombophilia: RR, 1.02; 95% CI, 0.80-1.30; I2  = 46% for VTE recurrence and RR, 0.72; 95% CI, 0.57-0.90; I2  = 84% for major/clinically relevant non-major bleeding events. Conclusions Rates of VTE recurrence and bleeding events were both low and comparable in patients with various thrombophilias receiving either treatment, suggesting that DOACs are an appropriate treatment option in this population. Due to limited data, it is unclear whether these findings apply to specific subgroups such as high-risk antiphospholipid syndrome, uncommon thrombophilias, or the use of apixaban.

Publisher Correction: Management of Low and Intermediate Risk Adult Rhabdomyosarcoma: A Pooled Survival Analysis of 553 Patients.

A correction to this article has been published and is linked from the HTML and PDF versions of this paper. The error has been fixed in the paper.

Management of Low and Intermediate Risk Adult Rhabdomyosarcoma: A Pooled Survival Analysis of 553 Patients.

This is the second-largest retrospective analysis addressing the controversy of whether adult rhabdomyosarcoma (RMS) should be treated with chemotherapy regimens adopted from pediatric RMS protocols or adult soft-tissue sarcoma protocols. A comprehensive database search identified 553 adults with primary non-metastatic RMS. Increasing age, intermediate-risk disease, no chemotherapy use, anthacycline-based and poor chemotherapy response were significant predictors of poor overall and progression-free survival. In contrast, combined cyclophosphamide-based, cyclophosphamide + anthracycline-based, or cyclophosphamide + ifosfamide + anthracycline-based regimens significantly improved outcomes. Intermediate-risk disease was a significant predictor of poor chemotherapy response. Overall survival of clinical group-III patients was significantly improved if they underwent delayed complete resection. Non-parameningeal clinical group-I patients had the best local control, which was not affected by additional adjuvant radiotherapy. This study highlights the superiority of chemotherapy regimens -adapted from pediatric protocols- compared to anthracycline-based regimens. There is lack of data to support the routine use of adjuvant radiotherapy for non-parameningeal group-I patients. Nonetheless, intensive local therapy should be always considered for those at high risk for local recurrence, including intermediate-risk disease, advanced IRS stage, large tumors or narrow surgical margins. Although practically difficult (due to tumor's rarity), there is a pressing need for high quality randomized controlled trials to provide further guidance.

Is fertility-preservation safe for adult non-metastatic gynecologic rhabdomyosarcoma patients? Systematic review and pooled survival analysis of 137 patients.

PURPOSE: Recently, conservative approaches such as wide local excisions and neoadjuvant chemotherapy are being considered to select young adult females with gynecologic RMS who have strong desire to preserve fertility. This analysis aims to identify prognosticators affecting survival outcomes and defining potential candidacy for fertility-preservation. Another focus is to explore the role of chemotherapy in reducing the need for aggressive surgery and the role of radiotherapy in decreasing rates of local failure. METHODS: A comprehensive database search identified 137 females > 16 years old with primary non-metastatic gynecologic RMS, who were included in a multivariate survival analysis. RESULTS: 5-year overall survival rate was 65%. Patients < 50 years old, with cervix uteri primaries, well-defined/polypoid presentations, embryonal histology and superficial tumors were more likely to survive. Deeply invasive disease and alveolar/pleomorphic histology significantly increased risks of treatment failure and tumor recurrence. Chemotherapy use was a significant multivariate predictor of better overall and metastasis-free survival. Radical surgery did not add local control or overall survival benefit for patients with superficial lesions (minimal/no cervical stromal invasion and no myometrial invasion). CONCLUSIONS: While high-quality clinical trial evidence is missing, existing evidence seems to support holding back on radical surgery for selected candidates with well-defined, polypoid, superficial, embryonal cervical/endometrial RMS lesions that could be completely excised with conservative surgery; further local resections with/without radiotherapy are then warranted based on margin status. Experience on the use of neoadjuvant chemotherapy in the conservative management of uterine RMS in adults is very limited, though this approach is golden-standard in pediatrics. A suggested scheme is introduced for the management of uterine RMS.

Congestive heart failure disease management program: 1-Year population experience from a tertiary center heart failure registry in Saudi Arabia.

AIMS: We aimed to evaluate congestive heart failure (CHF) multidisciplinary disease management program (DMProg) impact on mortality, readmission rates, length of stay (LOS), and gender health characteristics. METHODS AND RESULTS: This was a quasi-observational, pre- and post-trial with a parallel nonequivalent group. We enrolled 174 inpatients having CHF with reduced ejection fraction and New York Heart Association (NYHA) Class II-IV, and a total of 197 hospital admissions. A comparative follow-up was performed from 15 December 2014 to 15 December 2015. Among 197 consecutive hospital admissions, 76 (39%) were included in the preintervention or usual care group and 121 (61%) were assigned to the postintervention group. After 1 year, in comparison with the preintervention group, the postintervention group had shorter average LOS in days (7.6 days vs. 11.1 days, p < 0.002), lower 1-year readmission rate (36% vs. 57%, p < 0.003), and lower in-house mortality (1.6% vs. 7.8%, p = 0.03), but similar baseline mortality scores (38.2 vs. 38.6, p = 0.7), 30-day and 90-day readmission rates (15% vs. 18.3%, p = 0.62 and 27.6% vs. 30%, p = 0.65), and 30-day readmission risk score (24.9% vs. 26.2%, p = 0.09). By regression analysis, the DMProg intervention was an independent factor for 1-year readmission reduction (p = 0.001). Kaplan-Meier survival analysis favored the postintervention group (log-rank, p < 0.001). CONCLUSION: DMProg significantly decreased 1-year readmission rates, LOS, and in-house mortality.

A new metabolic mechanism for absence of pain in patients with silent myocardial ischemia.

BACKGROUND AND AIMS: We undertook this study to detect if there is a relationship between lactate production in the myocardium and the presence or absence of chest pain in patients with coronary artery disease (CAD). METHODS: Forty six patients with significant CAD including left anterior descending artery underwent echocardiography study, coronary angiography and pacing-induced ischemia. Serum lactate levels were determined in four blood samples, from mid-LV cavity and from coronary sinus before and after pacing-induced ischemia. Twenty eight patients comprised angina group and 18 patients comprised silent myocardial ischemia (SMI) group during pacing-induced ischemia. RESULTS: Eighteen patients (64.3%) of angina group had lactate production during ischemia. Eighteen patients of SMI group (100%) had diminished lactate extraction, and none had lactate production. CONCLUSION: The novel finding of this study is that the major difference in metabolism during SMI and angina pectoris is in the state of lactate production, which is absent during SMI and present during angina. We assume that lactate is the stimulus of cardiac ischemic pain and when its level increases, it stimulates pain receptors leading to chest pain.