Use of artificial intelligence to predict response to neoadjuvant chemotherapy in breast cancer

:Breast cancer is the object of thousands of studies worldwide. Nevertheless, few tools are available to corroborate prediction of response to neoadjuvant chemotherapy. Artificial intelligence is being researched for its potential utility in several fields of knowledge, including oncology. The development of a standardized Artificial intelligence-based predictive model for patients with breast cancer may help make clinical management more personalized and effective. We aimed to apply Artificial intelligence models to predict the response to neoadjuvant chemotherapy based solely on clinical and pathological data. Methods: Medical records of 130 patients treated with neoadjuvant chemotherapy were reviewed and divided into two groups: 90 samples to train the network and 40 samples to perform prospective testingand validate the results obtained by the Artificial intelligence method. Results: Using clinicopathologic data alone, the artificial neural network was able to correctly predict pathologic complete response in 83.3% of the cases. It also correctly predicted 95.6% of locoregional recurrence, as well as correctly determined whether patients were alive or dead at a given time point in 90% of the time. To date, no published research has used clinicopathologic data to predict the response to neoadjuvant chemotherapy in patients with breast cancer, thus highlighting the importance of the present study. Conclusions: Artificial neural network may become an interesting tool for predicting response to neoadjuvant chemotherapy, locoregional recurrence, systemic disease progression, and survival in patients with breast cancer (AU)

Leucoencefalopatia com substância branca evanescente: um relato de caso / Leukoencephalopathy with evanescent white matter: a case report

RESUMO Objetivo: Descrever uma criança diagnosticada com leucoencefalopatia com substância branca evanescente (LSBE), uma doença genética rara que possui padrão de herança autossômico recessivo. Descrição do caso: Criança do sexo masculino, com 5 meses de idade, que mostrava recusa da amamentação e sonolência, começou a apresentar quadro de desidratação, com boca seca, aumento da temperatura corporal e adipsia. Com o passar dos dias, os sintomas agravaram-se. O lactente apresentou-se muito sonolento e foi transferido para a unidade de tratamento intensivo (UTI), onde permaneceu por uma semana. Nesse período, foi identificada, na ressonância magnética de crânio, uma alteração de sinal com predomínio hiperatenuado T2, comprometendo particularmente a substância branca, de aspecto difuso e simétrico. O lactente apresentou crises convulsivas desde então. Aos 11 meses foi diagnosticado com tonsilite, demonstrando quadros recorrentes de picos febris e sonolência excessiva. Na evolução do quadro, o lactente entrou em estado comatoso progredindo a óbito. O diagnóstico de LSBE foi confirmado em exames realizados após o óbito, e tardiamente foi identificada uma doença genética decorrente de mutações em um dos cinco genes que são responsáveis pela codificação do complexo fator de iniciação da tradução de eucariontes 2B (eIF2B), envolvido com o controle da tradução de proteínas, sendo descrita como patogênica em indivíduos com LSBE. Comentários: A LSBE é uma doença cerebral hereditária com início na infância. A doença apresenta-se de maneira crônica e progressiva, com episódios adicionais de rápida deterioração, como evidenciado no presente relato de caso.

ABSTRACT Objective: To describe the case of a child diagnosed with leukoencephalopathy with vanishing white matter (LVWM), a rare genetic disease with autosomal recessive inheritance pattern. Case description: A 5-month-old male child started to refuse breast-feeding, showing somnolence and signs of dehydration,with dry mouth, increasing body temperature and adipsy. As days went by, the symptoms got worse. The infant was very sleepy and was transferred to the intensive care unit, where he stayed for one week. At this time, a signal alteration with hyper attenuated T2 predominance was identified in the magnetic resonance imaging, compromising the white matter, which had diffuse and symmetrical aspect. At this time, the infant started to present seizures. When the infant was 11 months old, he was diagnosed with tonsillitis and presented recurrent fever peaks and extreme sleepiness. After hospital admission, the infant progressed to a comatose state and died. The diagnosis of LVWM was confirmed in examinations performed after death. As a late diagnosis, a genetic disease was identified with a mutation in one of the five genes responsible for the codification of complex eukaryotic translation initiation factor 2B (eIF2B), involved with the control of the protein translation and which is described as pathogenic in individuals with LVWM. Comments: LVWM is a hereditary brain disease that occurs primarily in children. The disease is chronic and progressive, with additional episodes of rapid deterioration, as shown in the present case report.

Expression analysis of transglutaminase 2 in premalignant lesions of the cervix

Background: The medical management of low-grade squamous intraepithelial lesions (LSIL) is variable, thus a biomarker could assist with the clinical conduct. Type 2 transglutaminase (TG2) has been proposed as a cellular-interfering factor in HPV infection and carcinogenesis. Therefore, this study has the objective of evaluating TG2 expression in LSIL and highgrade squamous intraepithelial lesions (HSIL) and of relating it to the different HPV viral types. Methods: This study included 146 patients with suspected LSIL or HSIL detected in routine conventional Papanicolaou tests. The presence of HPV DNA and viral typing was defined by the polymerase chain reaction method (PCR). TG2 Immunohistochemistry (IHC) was conducted according to the manufacturer's instructions; IHC was carried out in an Autosteiner-Link 48 Dako equipment. IHC quantitation was performed by relative expression and by using the software Image J. Qualitative variables, such as frequencies and proportions, were compared by using the χ2 test for independent samples. For comparison of the qualitative to the quantitative data, nonparametric Mann-Whitney test was used. Results: The association between histopathological examination and TG2 was statistically significant (p <0.05). Results showed that patients with normal cervical histopathology and LSIL are locally associated with TG2 expression levels >50% (p <0.05), and patients with HSIL are associated with no TG2 expression (p <0.05). The analysis of the samples with the Image J software shows a significant (p <0,001) decrease in TG2 immunostaining in HSIL if compared to normal and to LSIL samples. This demonstrates a correlation between the relative quantification and the results provided by Image J. Analysis of HPV types showed a significant association with HPV11 (p = 0.031). This indicates that patients with HPV type 11 had higher TG2 values than patients with different types. Image J analysis showed no significant association between TG2 and HPV viral types. Conclusion: The present data suggest that TG 2 has a high expression in LSIL and normal tissues, and decreased in HSIL. We also observed that its expression is associated with HPV11 (AU)