Predicting antibiotic susceptibility in urinary tract infection with artificial intelligence-model performance in a multi-centre cohort.

Objective: To develop an artificial intelligence model to predict an antimicrobial susceptibility pattern in patients with urinary tract infection (UTI).

Materials And Methods: 26 087 adult patients with culture-proven UTI during 2015-2020 from a university teaching hospital and three community hospitals in Hong Kong were included. Cases with asymptomatic bacteriuria (absence of diagnosis code of UTI, or absence of leucocytes in urine microscopy) were excluded.

Number Needed to Diagnose in Malignant Ascites: Effects of Volume, Repeating Collection, and Primary Malignancy on Diagnostic Performance in Peritoneal Fluid Cytology.

Introduction: Volume recommendations of 80-200 mL have been proposed for peritoneal fluid cytology. While cutoffs are impractical when volume is limited by the amount present and disease factors, collections, however, can be repeated. This study addresses adequacy and number needed to diagnose by comparing diagnostic agreement to volumes in single specimens, total volumes collected daily, and within admissions.

Idiopathic granulomatous mastitis and cystic neutrophilic granulomatous mastitis: two sides of the same coin or distinct entities?

Idiopathic granulomatous mastitis (IGM) is a benign mimic of breast carcinomas. It is defined histologically by the presence of granulomas and inflammation. The closely related cystic neutrophilic granulomatous mastitis (CNGM) shows lipogranulomas, with a reported association with corynebacteria.

Deep learning for computational cytology: A survey.

Computational cytology is a critical, rapid-developing, yet challenging topic in medical image computing concerned with analyzing digitized cytology images by computer-aided technologies for cancer screening. Recently, an increasing number of deep learning (DL) approaches have made significant achievements in medical image analysis, leading to boosting publications of cytological studies. In this article, we survey more than 120 publications of DL-based cytology image analysis to investigate the advanced methods and comprehensive applications.

Identification of Tissue Types and Gene Mutations From Histopathology Images for Advancing Colorectal Cancer Biology.

Colorectal cancer (CRC) patients respond differently to treatments and are sub-classified by different approaches. We evaluated a deep learning model, which adopted endoscopic knowledge learnt from AI-doscopist, to characterise CRC patients by histopathological features. Data of 461 patients were collected from TCGA-COAD database.

A comparative study of diagnostic accuracy in 3026 pleural biopsies and matched pleural effusion cytology with clinical correlation.

Background: Pleural effusion can be caused by a wide range of benign and malignant conditions. Pleural biopsy and effusion cytology represent two key methods of pathological diagnosis. To compare the performance these two methods, a large cohort of matched pleural biopsy and effusion cytology with clinical follow-up was reviewed.

The role of cytokeratin 7/20 coordination revisited-Machine learning identifies improved interpretative algorithms for cell block immunohistochemistry in aspirates of metastatic carcinoma.

Background: Fine-needle aspiration (FNA) is a robust diagnostic technique often used for tissue diagnosis of metastatic carcinoma. For interpretation of FNA cytology, cell block immunohistochemistry (IHC) and clinicocytologic parameters are indispensable. In this review of a large cohort, the current report: 1) describes clinicocytologic parameters and immunoprofiles of aspirates of metastatic carcinoma, 2) compares the predictivity of immunostains and classical approaches for IHC interpretation, and 3) describes machine learning-based algorithms for IHC interpretation.

Fine needle aspiration cytology of metastatic carcinomas with papillary architecture: A systemic assessment of clinical, cytological and immunohistochemical parameters.

Background: Papillary structures are frequently encountered in metastatic carcinomas from various organs and tumours of different histotypes. This study aims to investigate the predictive value of fine needle aspiration cytology (FNAC), immunohistochemistry (IHC) and the clinical parameters which can be examined in the assessment of the primary sites of metastatic carcinomas with papillary architecture.

Methods: FNAC samples of metastatic carcinomas with papillary architecture were evaluated for overall cellularity, epithelial cohesion, background features, papillary architecture, cytology and IHC.

Long-Term Survival and Clinicopathological Implications of DNA Mismatch Repair Status in Endometrioid Endometrial Cancers in Hong Kong Chinese Women.

To investigate the role of DNA mismatch repair status (MMR) in survival of endometrioid endometrial cancer in Hong Kong Chinese women and its correlation to clinical prognostic factors, 238 patients with endometrioid endometrial cancer were included. Tumor MMR status was evaluated by immunohistochemistry. Clinical characteristics and survival were determined.

Papillary lesions of the breast: A systematic evaluation of cytologic parameters.

Background: The cytologic diagnosis of papillary lesions of the breast is challenging because of the diverse morphology, including epithelial hyperplasia, atypia, low-grade malignancy, and neuroendocrine differentiation; also, traditional malignant features such as necrosis and myoepithelial cell loss can be lacking. Thus, the diagnostic criteria for papillary lesions may differ from those for other breast lesions. This study evaluated various cytologic parameters in a large cohort to identify useful diagnostic features.

NOTCH3, a crucial target of miR-491-5p/miR-875-5p, promotes gastric carcinogenesis by upregulating PHLDB2 expression and activating Akt pathway.

Aberrant Notch activation has been implicated in multiple malignancies and the identification of NOTCH receptors and related pathways is critical for targeted therapy. In this study, we aim to delineate the most prominent dysregulated NOTCH receptor and comprehensively reveal its deregulation in gastric cancer (GC). In the four Notch members, NOTCH3 was found uniformly upregulated and associated with poor clinical outcomes in multiple GC datasets.

Deep learning model for prediction of extended-spectrum beta-lactamase (ESBL) production in community-onset Enterobacteriaceae bacteraemia from a high ESBL prevalence multi-centre cohort.

Adequate empirical antimicrobial coverage is instrumental in clinical management of community-onset Enterobacteriaceae bacteraemia in areas with high ESBL prevalence, while balancing the risk of carbapenem overuse and emergence of carbapenem-resistant organisms. It is unknown whether machine learning offers additional advantages to conventional statistical methods in prediction of ESBL production. To develop a validated model to predict ESBL production in Enterobacteriaceae causing community-onset bacteraemia.

FGF18-FGFR2 signaling triggers the activation of c-Jun-YAP1 axis to promote carcinogenesis in a subgroup of gastric cancer patients and indicates translational potential.

Fibroblast growth factor receptor type 2 (FGFR2) has emerged as a key oncogenic factor that regulates gastric cancer (GC) progression, but the underlying mechanism of FGF-FGFR2 signaling pathway remains largely unknown. To identify the potential molecular mechanisms of the oncogenic FGFR2 in gastric carcinogenesis and convey a novel therapeutic strategy, we profiled the FGFR alterations and analyzed their clinical associations in TCGA and Hong Kong GC cohorts. We found that FGFR2 overexpression in GC cell lines and primary tumors predicted poor survival and was associated with advanced stages of GC.

Virtual multiplex immunohistochemistry: Application on cell block of effusion and aspiration cytology.

Background: With the continuous development of new antibodies, the use of immunohistochemistry (IHC) is becoming more often a requirement. IHC is frequently necessary for establishing cancer diagnosis and making therapeutic decisions. However, cytology specimens such as effusion fluid and fine-needle aspiration are highly variable in cellularity and contain background inflammatory and mesothelial cells.

Noninvasive Detection of Bladder Cancer by Shallow-Depth Genome-Wide Bisulfite Sequencing of Urinary Cell-Free DNA for Methylation and Copy Number Profiling.

Background: The current diagnosis and monitoring of bladder cancer are heavily reliant on cystoscopy, an invasive and costly procedure. Previous efforts in urine-based detection of bladder cancer focused on targeted approaches that are predicated on the tumor expressing specific aberrations. We aimed to noninvasively detect bladder cancer by the genome-wide assessment of methylomic and copy number aberrations (CNAs).

New simple prognostic score for primary biliary cirrhosis: Albumin-bilirubin score.

Background And Aim: Serum albumin and bilirubin are the most significant independent prognostic factors to predict hepatic events in patients with primary biliary cirrhosis (PBC). We aimed to investigate the prognostic significance of a new prognostic score, the albumin-bilirubin (ALBI) score, among PBC patients.

Methods: In a retrospective longitudinal cohort of 61 Chinese PBC patients with follow-up period up to 18.

Evaluation of histological staging systems for primary biliary cirrhosis: correlation with clinical and biochemical factors and significance of pathological parameters in prognostication.

Aims: A new Japanese histological staging system for primary biliary cirrhosis (PBC) has been proposed. We aimed to evaluate the efficacies of the Scheuer, Ludwig and Japanese staging systems, with emphasis on their clinical and biochemical correlations and prognostic significances.

Methods And Results: We conducted a retrospective review of a cohort of 58 Chinese PBC patients, with follow-up of up to 16.