Search

The article discusses two groundbreaking studies published in Nature and Cell that introduce innovative AI models, PathChat and TriPath, designed to revolutionize pathology by enhancing diagnostic accuracy and prognostic outcomes. PathChat integrates a vision-language model to aid pathologists in diagnostic workflows, while TriPath focuses on analyzing 3D pathology samples for risk prediction. These AI technologies aim to streamline diagnostic processes, reduce variability in diagnoses, and improve patient outcomes by leveraging multimodal information and weakly supervised AI techniques. The integration of PathChat and TriPath into clinical practice offers significant potential to address challenges in pathology, optimize workflow, and enhance diagnostic accuracy. Future research should focus on refining these models, incorporating diverse datasets, and exploring real-world applications to further improve patient care and advance disease understanding. [Extracted from the article]

Background Serum homocysteine (Hcy) and vitamin B12 (VitB12) were investigated as serological markers for the prediction of pemetrexed induced haematological toxicity in patients with adenocarcinoma of the lung.

Background: R‐CHOP (rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisone) is a standard first‐line treatment for diffuse large B‐cell lymphoma (DLBCL). However, 20%–40% of patients survive less than 5 years. Novel prognostic biomarkers remain in demand. Methods: Baseline plasma autoantibodies (AAbs) were assessed in 336 DLBCLs. In the discovery phase (n = 20), a high‐density antigen microarray (∼21,000 proteins) was used to expound AAb profiles. In the verification phase (n = 181), with a DLBCL‐focused microarray, comparative results based on event‐free survival at 24 months (EFS24) and lasso Cox regression models of progression‐free survival (PFS) and overall survival (OS) were integrated to identify potential biomarkers. They were further validated by enzyme‐linked immunosorbent assay in validation phase 1 (n = 135) and a dynamic cohort (n = 12). In validation phase 2, a two‐AAb‐based risk score was established. They were further validated in an immunohistochemistry cohort (n = 55) and four independent Gene Expression Omnibus datasets (n = 1598). Results: Four AAbs (CREB1, N4BP1, UBAP2, and DEAF1) were identified that showed associations with EFS24 status (p <.05) and superior PFS and OS (p <.05). A novel risk score model based on CREB1 and N4BP1 AAbs was developed to predict PFS with areas under the curve of 0.72, 0.71, 0.76, and 0.82 at 1, 3, 5, and 7 years, respectively, in DLBCL treated with R‐CHOP independent of the International Prognostic Index (IPI) and provided significant additional recurrence risk discrimination (p <.05) for the IPI. CREB1 and N4BP1 proteins and messenger RNAs were also associated with better PFS and OS (p <.05). Conclusions: This study identified a novel prognostic panel of CREB1, N4BP1, DEAF1, and UBAP2 AAbs that is independent of the IPI in DLBCL. Autoantibodies (AAbs) have the potential for personalized monitoring of tumor recurrence. Serological AAbs against N4BP1, CREB1, DEAF1, and UBAP2 were independent of International Prognostic Index traditional risk factors for diffuse large B‐cell lymphoma (DLBCL) treated with rituximab plus cyclophosphamide, doxorubicin, vincristine, and prednisone. Notably, two of these biomarkers, CREB1 and N4BP1, exhibited prognostic significance at multiple levels, including messenger RNA, protein, and AAb. These findings suggest that monitoring AAb levels during treatment may be a useful tool for predicting prognosis and guiding personalized treatment strategies for patients with DLBCL. [ABSTRACT FROM AUTHOR]

Aim: This study aimed to analyze the clinical features, treatment, survival, and prognostic factors of Chinese patients with peripheral T‐cell lymphoma (PTCL) excluding natural killer/T‐cell lymphoma (NKTCL). Methods: Data on patients with newly diagnosed PTCLs between January 1, 2006 and December 31, 2017 at our hospital were retrospectively reviewed. Patients with NKTCL were excluded. Results: A total of 240 patients were included. PTCL, not otherwise specified (PTCL‐NOS), was the most frequent subtype (42.5%), followed by angioimmunoblastic T‐cell lymphoma (AITL) (21.3%), anaplastic lymphoma kinase (ALK)‐negative anaplastic large‐cell lymphoma (ALK‐ALCL) (16.7%), ALK‐positive ALCL (ALK+ALCL) (10.8%) and others (8.8%). With a median follow‐up of 81.1 months, the 5‐year progression‐free survival (PFS) and overall survival (OS) rates for all patients were 30.4% (95% CI 25.0%–37.0%) and 48.8% (95% CI 42.6%–55.7%), respectively. On multivariate analysis, no consolidative autologous stem cell transplantation (ASCT) and not achieving complete response after first‐line chemotherapy retained independently prognostic value for inferior PFS and OS. Besides, bone marrow involvement and serum albumin level were independent factors for PFS, and Eastern Cooperative Oncology Group performance status ≥2 was significantly predictive of inferior OS. Compared with PTCL‐NOS, significantly superior PFS and OS were observed for ALK+ALCL and ALK‐ALCL. Conclusion: The survival outcomes with current treatment for most PTCL subtypes are still unsatisfactory. Prospective randomized studies are needed to establish the value of consolidative ASCT in PTCL, and novel therapeutic approaches should be explored. [ABSTRACT FROM AUTHOR]

The present study aimed to assess the efficacy and safety of immune checkpoint inhibitor (ICI)-based therapy in patients with metastatic breast cancer (MBC). Therefore, eligible patients with histologically confirmed MBC, treated with ICI-based therapy, were enrolled. The primary endpoint was progression-free survival (PFS) and the secondary endpoints included objective response rate (ORR), disease control rate (DCR), overall survival (OS) and safety. A total of 90 patients with MBC, treated with ICI-based therapy, with different treatment lines, were included in the present study. The median age was 50 years (range, 27–76). The predominant tumor subtypes were triple negative (53.3%) and luminal (31.1%) breast cancer. The majority of patients (61.1%) were heavily pretreated (lines of treatment, ≥3). Approximately half of the patients (46.7%) had ≥3 metastatic sites. The overall ORR was 36.7% (33/90 patients), while a DCR of 78.9% (71/90 patients) was also recorded. With a median follow-up of 16.0 months, the median PFS and OS were 4.9 months [95% confidence interval (CI), 3.8–6.1] and 13.9 months (95% CI, 9.5–18.2), respectively. Patients treated with ICIs as first-line therapy exhibited notable improvement, with a median PFS of 11.0 months (95% CI, 6.0–16.0) and a median OS of 24.3 months (95% CI, 11.4–37.2). In addition, the pretreatment blood platelet-to-lymphocyte ratio was an independent risk factor for PFS [hazard ratio (HR)=2.406; 95% CI, 1.325–4.370; P=0.004] and OS (HR=2.376; 95% CI, 1.059–5.328; P=0.036). The most common adverse events were nausea (44.4%), neutropenia (42.0%) and alanine aminotransferase/aspartate aminotransferase elevation (22.2%). Furthermore, three (3.3%) patients developed grade 1/2 immuno-related toxicity and recovered after supportive care. Overall, the present study suggested that the ICI-based therapy exhibited encouraging clinical outcomes with manageable toxicity in patients with MBC in real-world settings, with the most favorable efficacy in first-line treatment. [ABSTRACT FROM AUTHOR]