A deep learning approach to case prioritisation of colorectal biopsies.

AIMS: To create and validate a weakly supervised artificial intelligence (AI) model for detection of abnormal colorectal histology, including dysplasia and cancer, and prioritise biopsies according to clinical significance (severity of diagnosis). MATERIALS AND METHODS: Triagnexia Colorectal, a weakly supervised deep learning model, was developed for the classification of colorectal samples from haematoxylin and eosin (H&E)-stained whole slide images. The model was trained on 24 983 digitised images and assessed by multiple pathologists in a simulated digital pathology environment. The AI application was implemented as part of a point and click graphical user interface to streamline decision-making. Pathologists assessed the accuracy of the AI tool, its value, ease of use and integration into the digital pathology workflow. RESULTS: Validation of the model was conducted on two cohorts: the first, on 100 single-slide cases, achieved micro-average model specificity of 0.984, micro-average model sensitivity of 0.949 and micro-average model F1 score of 0.949 across all classes. A secondary multi-institutional validation cohort, of 101 single-slide cases, achieved micro-average model specificity of 0.978, micro-average model sensitivity of 0.931 and micro-average model F1 score of 0.931 across all classes. Pathologists reflected their positive impressions on the overall accuracy of the AI in detecting colorectal pathology abnormalities. CONCLUSIONS: We have developed a high-performing colorectal biopsy AI triage model that can be integrated into a routine digital pathology workflow to assist pathologists in prioritising cases and identifying cases with dysplasia/cancer versus non-neoplastic biopsies.

Predictive and prognostic biomarkers in gastrointestinal tract tumours.

Tumours of the gastrointestinal tract represent nearly a quarter of all newly diagnosed tumours diagnosed in 2019. Various treatment modalities for gastrointestinal cancers exist, some of which may be guided by biomarkers. Biomarkers act as gauges of either normal or pathogenic processes or responses to an exposure or intervention. They come in many forms. This review explores established and potential molecular/immunohistochemical (IHC) predictive and prognostic biomarkers of the gastrointestinal tract.

Gastrointestinal Stromal Tumours (GISTs) with KRAS Mutation: A Rare but Important Subset of GISTs.

Gastrointestinal stromal tumours (GISTs) are the most common mesenchymal tumours of the GI tract, usually found in the stomach, jejunum, and ileum. Typically, they are KIT or PDGFR-mutated, allowing for targetable treatments with tyrosine kinase inhibitors such as imatinib. Here, we present two KRAS-mutated wild-type gastrointestinal tumours (GISTs). Both cases occurred in the small bowel of females. Immunohistochemical studies on both tumours showed KIT and DOG-1 positivity, with SDHB retained. Molecular analysis revealed a KRAS G12D mutation and a KRAS G13D mutation, respectively. Wild-type GISTs are extremely uncommon. They typically occur in the stomach or the small bowel. KRAS is one of the genes implicated in this subset of GIST, with KRAS G12D being the most frequently encountered mutation. GIST KRAS mutations can arise alone or in conjunction with KIT, PDFRA, or BRAF mutations. Identification of these rare molecular subtypes is clinically important due to their resistance to imatinib therapy.

Distinguishing Gastric/Esophageal Adenocarcinoma from Pancreatic Adenocarcinoma Using Methylation-Based Droplet Digital PCR.

The goal of this study was to develop a methylation-based droplet digital PCR to separate 2 cancer classes that do not have sensitive and specific immunohistochemical stains: gastric/esophageal and pancreatic adenocarcinomas. The assay used methylation-independent primers and methylation-dependent probes to assess a single differentially methylated CpG site; analyses of array data from The Cancer Genome Atlas network showed that high methylation at the cg06118999 probe supports the presence of cells originating from the stomach or esophagus (eg, as in gastric metastasis), whereas low methylation suggests that these cells are rare to absent (eg, pancreatic metastasis). On validation using formalin-fixed paraffin-embedded primary and metastatic samples from our institution, methylation-based droplet digital PCR targeting the corresponding CpG dinucleotide generated evaluable data for 60 of the 62 samples (97%) and correctly classified 50 of the 60 evaluable cases (83.3%), mostly adenocarcinomas from the stomach or pancreas. This ddPCR was created to be easy-to-interpret, rapid, inexpensive, and compatible with existing platforms at many clinical laboratories. We suggest that similarly accessible PCRs could be developed for other differentials in pathology that do not have sensitive and specific immunohistochemical stains.

Sex-related patient-reported brain fog symptoms in non-hospitalised COVID-19 patients.

INTRODUCTION: Previous studies on the prognostic role of sex in post-COVID-associated brain fog have yielded divergent results. Moreover, limited evidence exists regarding the evolution of brain fog symptoms over time, especially in ambulatory patients and separately for women and men. Therefore, the aim of the current study was to assess brain fog symptoms in nonhospitalised patients with COVID-19, according to their sex. MATERIAL AND METHODS: We created a neuropsychological questionnaire including eight questions on the presence of brain fog symptoms in the following four time periods: before COVID-19, and 0-4, 4-12, and > 12 weeks post-infection. The validity and reliability of the questionnaire were assessed. In this cross-sectional study, questionnaires were filled out anonymously and retrospectively once only by patients or through a survey link posted online. Included were patients ≥ 18 years, with > 3 months since the SARS-CoV-2 infection onset confirmed by RT-PCR from a nasopharyngeal swab. RESULTS: The study included 303 patients (79.53% women, 47.52% medical personnel). Median time between COVID-19 onset and questionnaire completion was 208 (IQR 161-248) days. Women, compared to men, reported a higher prevalence of problems with writing, reading, and counting (< 4 weeks, OR 3.05, 95% CI: 1.38-6.72; 4-12 weeks, OR 2.51, 95% CI: 1.02-6.14; > 12 weeks, OR 3.74, 95% CI: 1.12-12.56) and thoughts communication (< 4 weeks, OR 2.53, 95% CI: 1.41-4.54; 4-12 weeks, OR 3.74, 95% CI: 1.93-7.24; > 12 weeks, OR 2.00, 95% CI: 1.01-3.99). The difference between the two sexes in answering questions in an understandable/unambiguous manner was statistically significant between four and 12 weeks after infection (OR 2.63, 95% CI: 1.36-5.10), while a sex difference in recalling new information was found below 12 weeks (OR 2.54, 95% CI: 1.44-4.48 and OR 2.43, 95% CI: 1.37-4.31 for < 4 and 4-12 weeks, respectively). No sex differences in reporting problems with multitasking, remembering information from the past, determining the current date, or field orientation were noted. CONCLUSIONS: Non-hospitalised women and men retrospectively report a different course of COVID-19-associated brain fog.

Gene of the month: PALB2.

The partner and localiser of BRCA2 (PALB2) gene, located on chromosome 16, functions as a tumour suppressor that plays a critical role in homologous recombination repair after DNA double-strand breaks. It encodes proteins involved in the BRCA2 and BRCA1, and RAD51 pathways. Heterozygous germline mutations in PALB2 have been implicated in the development of breast, pancreatic and ovarian cancers. Whereas biallelic mutations of PALB2 have been associated with Fanconi anaaemia. Currently, 604 distinct PALB2 variants have been discovered. However, only 140 variants are thought to be pathogenic and approximately 400 are variants of unknown significance. Further studies are needed before the presence of PLAB2 mutations can be implemented as a routine clinical biomarker.

Analysis of Side Effects Following Vaccination Against COVID-19 Among Individuals With Multiple Sclerosis Treated With DMTs in Poland.

Background and Objectives: Since vaccination against COVID-19 is available for over a year and the population of immunized individuals with autoimmune disorders is higher than several months before, an evaluation of safety and registered adverse events can be made. We conducted a large study of side effects following the COVID-19 vaccine among patients with multiple (MS) sclerosis treated with disease-modifying therapies (DMTs) and analyzed factors predisposing for particular adverse events. Methods: We gathered data of individuals with MS treated with DMTs from 19 Polish MS Centers, who reported at least one adverse event following COVID-19 vaccination. The information was obtained by neurologists using a questionnaire. The same questionnaire was used at all MS Centers. To assess the relevance of reported adverse events, we used Fisher's exact test, t-test, and U-Menn-Whutney test. Results: A total of 1,668 patients with MS and reports of adverse events after COVID-19 vaccination were finally included in the study. Besides one case marked as "red flag", all adverse events were classified as mild. Pain at the injection site was the most common adverse event, with a greater frequency after the first dose. Pain at the injection site was significantly more frequent after the first dose among individuals with a lower disability (EDSS ≤2). The reported adverse events following immunization did not differ over sex. According to age, pain at the injection site was more common among individuals between 30 and 40 years old, only after the first vaccination dose. None of the DMTs predisposed for particular side effects. Conclusions: According to our findings, vaccination against COVID-19 among patients with MS treated with DMTs is safe. Our study can contribute to reducing hesitancy toward vaccination among patients with MS.

The Quality of Sex Life Among Patients Before and After Lung Transplantation: A Single-Center Study.

BACKGROUND: Lung transplantation (LTx) is the only effective method of treatment for patients with end-stage lung diseases; LTx prolongs and increases the quality of life (QoL). An important aspect of QoL that changes in the course of severe diseases is the quality of sex life. This aspect is yet to be discussed in relationship to LTx. We aim to compare patients' quality of sex life at the qualification process with patients' who underwent LTx. METHODS: The studied group consisted of 100 patients (24 women before and 16 after LTx, 39 men before and 21 after LTX) who were admitted to the lung transplantology department for qualification or to control the function after LTx. To assess the patients' quality of sex life, we used The Changes in Sexual Functioning Questionnaire (CSFQ) and World Health Organization (WHO) QoL-BREF. To assess lung function, patients underwent a 6-Minute-Walk-Test (6MWT). RESULTS: Patients after LTx obtained higher results-compared to patients qualified for LTx-in the WHO QoL-BREF in every domain (somatic, psychological, social, and environment). Men after LTx got more points in every domain and better total score (53 ± 5.62 vs 44.23 ± 10.28 point; P < .05) in CSFQ. Women before and after LTx obtained comparable results in CSFQ. Results of 6-Minute-Walk-Test were better among patients after LTx than in qualified patients (523.62 ± 95.71 vs 333.14 ± 145.38 and 524.12 ± 56.17 vs 317.20 ± 141.6, respectively for men and women). CONCLUSIONS: Patients after LTx show better pulmonary function and quality of sex life than qualified. Preliminary results encourage us to conduct research on a larger group.

Gene of the month: ERG.

The ERG gene belongs to the erythroblastosis transformation specific family of transcription factors and encodes for the transcription regulator protein ERG. It is located on chromosome 22q22 and is a nuclear transcription factor. In normal physiology, ERG protein is expressed in endothelial cells and is involved in processes including, but not limited to, angiogenesis and haematopoiesis. Of diagnostic value in clinical practice, ERG immunohistochemistry is a useful marker of endothelial differentiation for both benign and malignant vascular lesions. It is also reliable for identifying ERG gene translocated malignancies such as EWS/FUS::ERG Ewing's sarcoma and TMPSSR2::ERG prostatic carcinoma.