Practical Application of Deep Learning in Diagnostic Neuropathology-Reimagining a Histological Asset in the Era of Precision Medicine.

In the past few decades, neuropathology has experienced several paradigm shifts with the introduction of new technologies. Deep learning, a rapidly progressing subfield of machine learning, seems to be the next innovation to alter the diagnostic workflow. In this review, we will explore the recent changes in the field of neuropathology and how this has led to an increased focus on molecular features in diagnosis and prognosis. Then, we will examine the work carried out to train deep learning models for various diagnostic tasks in neuropathology, as well as the machine learning frameworks they used. Focus will be given to both the challenges and successes highlighted therein, as well as what these trends may tell us about future roadblocks in the widespread adoption of this new technology. Finally, we will touch on recent trends in deep learning, as applied to digital pathology more generally, and what this may tell us about the future of deep learning applications in neuropathology.

VOLTA: an enVironment-aware cOntrastive ceLl represenTation leArning for histopathology.

In clinical oncology, many diagnostic tasks rely on the identification of cells in histopathology images. While supervised machine learning techniques necessitate the need for labels, providing manual cell annotations is time-consuming. In this paper, we propose a self-supervised framework (enVironment-aware cOntrastive cell represenTation learning: VOLTA) for cell representation learning in histopathology images using a technique that accounts for the cell's mutual relationship with its environment. We subject our model to extensive experiments on data collected from multiple institutions comprising over 800,000 cells and six cancer types. To showcase the potential of our proposed framework, we apply VOLTA to ovarian and endometrial cancers and demonstrate that our cell representations can be utilized to identify the known histotypes of ovarian cancer and provide insights that link histopathology and molecular subtypes of endometrial cancer. Unlike supervised models, we provide a framework that can empower discoveries without any annotation data, even in situations where sample sizes are limited.

Need for open data on COVID-19 vaccine uptake among pregnant people in the Caribbean: a call to action / Necesidad de datos abiertos sobre la aceptación de la vacuna contra la COVID-19 entre las mujeres durante el embarazo en el Caribe: un llamado a la acción / Necessidade de dados abertos sobre a adesão de gestantes à vacinação contra a COVID-19 no Caribe: um chamado à ação

ABSTRACT Pregnant people with coronavirus disease 2019 (COVID-19) have a higher risk of adverse maternal and fetal outcomes compared with pregnant people without COVID-19. In 2021, large increases in maternal mortality were reported in Jamaica, almost half of which were attributable to COVID-19. COVID-19 vaccination has been shown to reduce these risks, but low- and middle-income countries lack free, publicly available data, known as open data, on COVID-19 vaccine uptake for their pregnant populations. The objectives of this paper were to: review how high-income countries use open data to detect trends in COVID-19 vaccine uptake among pregnant people and develop vaccination distribution strategies; outline barriers to making open data available for maternal COVID-19 vaccination in the Caribbean; and propose a multipronged strategy that would increase the availability of open data on maternal COVID-19 vaccination in the Caribbean. A multipronged strategy to fill the data void would involve: (i) utilizing existing Caribbean maternal immunization data collection entities; (ii) adapting digital software tools to establish maternal electronic immunization registries; and (iii) collaborating with local partners skilled in data analytics. Making open data available for COVID-19 vaccine uptake among pregnant people in the Caribbean could offer substantial benefits, including the development of measurable maternal COVID-19 vaccination goals and the facilitation of vaccine decision-making discussions between providers and pregnant people.

RESUMEN Las embarazadas con la enfermedad por coronavirus del 2019 (COVID-19) tienen un mayor riesgo de resultados maternos y fetales adversos que aquellas libres de la enfermedad. En el 2021, en Jamaica se notificó un gran aumento de la mortalidad materna, del cual casi la mitad fue atribuible a la COVID-19. Se ha demostrado que la vacunación contra la COVID-19 reduce tales riesgos, pero los países de ingresos bajos y medianos carecen de datos gratuitos y de carácter público, conocidos como datos abiertos, sobre la aceptación de la vacuna contra la COVID-19 por parte de las mujeres durante el embarazo. Los objetivos del presente artículo consistieron en examinar cómo los países de ingresos altos utilizan los datos abiertos para detectar las tendencias de aceptación de la vacuna contra la COVID-19 entre las mujeres durante el embarazo y formular estrategias de distribución de las vacunas; señalar los obstáculos que dificultan la disponibilidad de los datos abiertos sobre la vacunación materna contra la COVID-19 en el Caribe; y proponer una estrategia múltiple que permita aumentar la disponibilidad de datos abiertos sobre la vacunación materna contra la COVID-19 en el Caribe. Una estrategia múltiple para llenar este vacío de información implicaría: a) utilizar las entidades de recopilación de datos sobre inmunización materna ya existentes en el Caribe; b) adaptar las herramientas informáticas digitales para crear registros electrónicos de vacunación materna; y c) colaborar con asociados locales especializados en el análisis de datos. Facilitar el acceso a los datos abiertos sobre la aceptación de la vacuna contra la COVID-19 entre las mujeres durante el embarazo en el Caribe podría ofrecer beneficios considerables, tales como el establecimiento de objetivos cuantificables en materia de vacunación materna contra la COVID-19, y propiciar las deliberaciones sobre la toma de decisiones en materia de vacunación entre los prestadores de atención de salud y las embarazadas.

RESUMO Gestantes com a doença pelo coronavírus 2019 (COVID-19) têm maior risco de desfechos maternos e fetais adversos em comparação com gestantes sem COVID-19. Em 2021, foi registrado um aumento acentuado da mortalidade materna na Jamaica, e quase metade era atribuível à COVID-19. Foi demonstrado que a vacinação contra a COVID-19 reduz esses riscos, mas os países de baixa e média renda não dispõem de dados gratuitos e publicamente disponíveis (os chamados dados abertos) sobre a adesão à vacina contra a COVID-19 entre gestantes. Os objetivos deste estudo foram: analisar como os países de alta renda usam dados abertos para detectar tendências na adesão à vacina contra a COVID-19 entre gestantes e desenvolver estratégias de distribuição da vacina; descrever os obstáculos para disponibilizar dados abertos sobre a vacinação materna contra a COVID-19 no Caribe; e propor uma estratégia multifacetada que aumente a disponibilidade de dados abertos sobre a vacinação materna contra a COVID-19 no Caribe. Uma estratégia multifacetada para obter dados a fim de preencher essa lacuna envolveria: (i) utilização das entidades existentes que coletam dados de imunização materna no Caribe; (ii) adaptação de ferramentas de software para estabelecer registros eletrônicos de imunização materna; e (iii) colaboração com parceiros locais especializados em análise de dados. A disponibilização de dados abertos sobre a adesão de gestantes à vacinação contra a COVID-19 no Caribe poderia oferecer benefícios substanciais, incluindo o desenvolvimento de metas mensuráveis de vacinação materna contra a COVID-19, e facilitar discussões entre profissionais de saúde e gestantes para a tomada de decisões sobre vacinas.

Integrated Models of Care for Individuals with Opioid Use Disorder: How Do We Prevent HIV and HCV?

PURPOSE OF REVIEW: To describe models of integrated and co-located care for opioid use disorder (OUD), hepatitis C (HCV), and HIV. RECENT FINDINGS: The design and scale-up of multidisciplinary care models that engage, retain, and treat individuals with HIV, HCV, and OUD are critical to preventing continued spread of HIV and HCV. We identified 17 models within primary care (N = 3), HIV specialty care (N = 5), opioid treatment programs (N = 6), transitional clinics (N = 2), and community-based harm reduction programs (N = 1), as well as two emerging models. Key components of such models are the provision of (1) medication-assisted treatment for OUD, (2) HIV and HCV treatment, (3) HIV pre-exposure prophylaxis, and (4) behavioral health services. Research is needed to understand differences in effectiveness between co-located and fully integrated care, combat the deleterious racial and ethnic legacies of the "War on Drugs," and inform the delivery of psychiatric care. Increased access to harm reduction services is crucial.