RESUMO
The SARS-COV-2 pandemic has put pressure on intensive care units, so that identifying predictors of disease severity is a priority. We collect 58 clinical and biological variables, and chest CT scan data, from 1003 coronavirus-infected patients from two French hospitals. We train a deep learning model based on CT scans to predict severity. We then construct the multimodal AI-severity score that includes 5 clinical and biological variables (age, sex, oxygenation, urea, platelet) in addition to the deep learning model. We show that neural network analysis of CT-scans brings unique prognosis information, although it is correlated with other markers of severity (oxygenation, LDH, and CRP) explaining the measurable but limited 0.03 increase of AUC obtained when adding CT-scan information to clinical variables. Here, we show that when comparing AI-severity with 11 existing severity scores, we find significantly improved prognosis performance; AI-severity can therefore rapidly become a reference scoring approach.
Assuntos
COVID-19/diagnóstico , COVID-19/fisiopatologia , Aprendizado Profundo , Redes Neurais de Computação , Tomografia Computadorizada por Raios X/métodos , Inteligência Artificial , COVID-19/classificação , Humanos , Modelos Biológicos , Análise Multivariada , Prognóstico , Radiologistas , Índice de Gravidade de DoençaAssuntos
Antineoplásicos/uso terapêutico , Neoplasias Pulmonares/tratamento farmacológico , Carcinomatose Meníngea/tratamento farmacológico , Piperazinas/uso terapêutico , Acrilamidas , Adulto , Compostos de Anilina , Antineoplásicos/farmacologia , Receptores ErbB/genética , Feminino , Humanos , Neoplasias Pulmonares/patologia , Carcinomatose Meníngea/patologia , Mutação , Piperazinas/farmacologiaRESUMO
Circulating tumor cells (CTCs) are rare tumor cells and have been investigated as diagnostic, prognostic and predictive biomarkers in many types of cancer. Although CTCs are not currently used in clinical practice, CTC studies have accumulated a high level of clinical validity, especially in breast, lung, prostate and colorectal cancers. In this review, we present an overview of the current clinical validity of CTCs in metastatic and non-metastatic disease, and the main concepts and studies investigating the clinical utility of CTCs. In particular, this review will focus on breast, lung, colorectal and prostate cancer. Three major topics concerning the clinical utility of CTC are discussed-(1) treatment based on CTCs used as liquid biopsy, (2) treatment based on CTC count or CTC variations, and (3) treatment based on CTC biomarker expression. A summary of published or ongoing phase II and III trials is also presented.
