With the rapid development of artificial intelligence, computational pathology has been seamlessly integrated into the entire clinical workflow, which encompasses diagnosis, treatment, prognosis, and biomarker discovery. This integration has significantly enhanced clinical accuracy and efficiency while reducing the workload for clinicians. Traditionally, research in this field has depended on the collection and labeling of large datasets for specific tasks, followed by the development of task-specific computational pathology models. However, this approach is labor intensive and does not scale efficiently for open-set identification or rare diseases. Given the diversity of clinical tasks, training individual models from scratch to address the whole spectrum of clinical tasks in the pathology workflow is impractical, which highlights the urgent need to transition from task-specific models to foundation models (FMs). In recent years, pathological FMs have proliferated. These FMs can be classified into three categories, namely, pathology image FMs, pathology image-text FMs, and pathology image-gene FMs, each of which results in distinct functionalities and application scenarios. This review provides an overview of the latest research advancements in pathological FMs, with a particular emphasis on their applications in oncology. The key challenges and opportunities presented by pathological FMs in precision oncology are also explored.
Humans ; Precision Medicine/methods* ; Medical Oncology/methods* ; Artificial Intelligence ; Neoplasms/pathology* ; Computational Biology/methods*

Drug repurposing offers a promising alternative to traditional drug development and significantly reduces costs and timelines by identifying new therapeutic uses for existing drugs. However, the current approaches often rely on limited data sources and simplistic hypotheses, which restrict their ability to capture the multi-faceted nature of biological systems. This study introduces adaptive multi-view learning (AMVL), a novel methodology that integrates chemical-induced transcriptional profiles (CTPs), knowledge graph (KG) embeddings, and large language model (LLM) representations, to enhance drug repurposing predictions. AMVL incorporates an innovative similarity matrix expansion strategy and leverages multi-view learning (MVL), matrix factorization, and ensemble optimization techniques to integrate heterogeneous multi-source data. Comprehensive evaluations on benchmark datasets (Fdataset, Cdataset, and Ydataset) and the large-scale iDrug dataset demonstrate that AMVL outperforms state-of-the-art (SOTA) methods, achieving superior accuracy in predicting drug-disease associations across multiple metrics. Literature-based validation further confirmed the model's predictive capabilities, with seven out of the top ten predictions corroborated by post-2011 evidence. To promote transparency and reproducibility, all data and codes used in this study were open-sourced, providing resources for processing CTPs, KG, and LLM-based similarity calculations, along with the complete AMVL algorithm and benchmarking procedures. By unifying diverse data modalities, AMVL offers a robust and scalable solution for accelerating drug discovery, fostering advancements in translational medicine and integrating multi-omics data. We aim to inspire further innovations in multi-source data integration and support the development of more precise and efficient strategies for advancing drug discovery and translational medicine.

OBJECTIVE To explore the role of clinical pharmacists participating in the standardized perioperative nutritional management process for pancreaticoduodenectomy （PD） on improving postoperative recovery in patients. METHODS The clinical data of 100 patients undergoing PD in the Department of Biliary and Pancreatic Surgery， Drum Tower Hospital Affiliated to Nanjing University School of Medicine from November 2019 to February 2021 were analyzed retrospectively. According to the different perioperative nutrition management plans， they were divided into clinical pharmacist intervention group （n＝51， clinical pharmacists intervened according to the standardized nutrition management process） and control group （n＝49， clinical pharmacists only performed preoperative nutrition evaluation， and clinical physicians took nutrition support according to the patient’s condition）. The differences in postoperative recovery index， economic evaluation index， hospitalization length， postoperative complications， and postoperative enteral nutrition support route were compared between 2 groups. RESULTS The time of postoperative diet， the first postoperative ventilation， the first postoperative defecation， and postoperative drainage time of abdominal drain were significantly earlier in the clinical pharmacist intervention group than in the control group （P＜0.05）； the hospitalization cost， medication cost， nutritional support cost， parenteral nutrition cost， albumin preparation cost， and the length of postoperative hospitalization were significantly lower/shorter in the clinical pharmacist intervention group than in the control group （P＜0.05）； there was no statistically significant difference in the incidence of postoperative complications between the two groups （P＞0.05）； there was statistically significant difference in the perioperative enteral nutrition support pathways between two groups （P＜0.05）. CONCLUSIONS Clinical pharmacists’ participation in perioperative nutritional management for PD can significantly reduce hospitalization costs and nutritional support costs， improve patients’ perioperative nutritional status， and shorten hospital stays. wanglina668@163.com

Different porous structures were studied through finite element analysis and then optimal porous structure was selected for the orthopedic applications.The optimal Voronoi structure was designed and fabricated using 3D printing.The mechanical properties and osseointegration ability were both investigated.The mechanical tests showed that the tensile strength,compressive strength and bending strength of Voronoi structures were obviously higher than that of the human bone,and the modulus of Voronoi structures were similar to human bone.In addition,the animal experimental results exhibited that obvious bone ingrowth was found from Month 1 to Month 6.This study provides some theoretical references for the orthopedic application of porous structures.

This study aims at developing a dataset for determining the presence of carotid artery plaques in ultrasound images,composed of 1761 ultrasound images from 1165 participants.A deep learning architecture that combines bilinear convolutional neural networks with residual neural networks,known as the single-input BCNN-ResNet model,was utilized to aid clinical doctors in diagnosing plaques using carotid ultrasound images.Following training,internal validation,and external validation,the model yielded an ROC AUC of 0.99(95%confidence interval:0.91 to 0.84)in internal validation and 0.95(95%confidence interval:0.96 to 0.94)in external validation,surpassing the ResNet-34 network model,which achieved an AUC of 0.98(95%confidence interval:0.99 to 0.95)in internal validation and 0.94(95%confidence interval:0.95 to 0.92)in external validation.Consequently,the single-input BCNN-ResNet network model has shown remarkable diagnostic capabilities and offers an innovative solution for the automatic detection of carotid artery plaques.

Objective:To investigate whether intestinal rehabilitation therapy (IRT)could optimize the effectiveness of IRT in patients with short bowel syndrome (SBS) caused by acute mesenteric ischemia (AMI) with chronic multivessel lesions.Methods:Clinical data of 18 hospitalized patients diagnosed with AMI leading to SBS and undergoing IRT at the Eastern Theater General Hospital of the People's Liberation Army from Jan 2012 to Oct 2023 was retrospectively analyzed.Result:Following IRT, the revascularization group showed significantly greater increases in ASMI and grip strength compared to the control group [(0.28±0.26) kg/m 2vs. (0.02±0.21) kg/m 2, P=0.033, and (0.97±0.33) kg vs. (0.48±0.34) kg, P=0.007, respectively]. Similarly, the increase in EN intake was significantly higher in the revascularization group compared to the control group [(572.5±93.6) ml/d vs. (375.2±176.3) ml/d, P=0.012], accompanied by a greater improvement in intestinal nitrogen absorption rate [(25.06±14.06)% vs. (13.84±4.62)%, P=0.034] and a more substantial decrease in GSRS scores [(-15.88±3.94) vs. (-6.33±5.13), P=0.030]. Moreover, there were significant differences in the composition of EN formulations between the two groups after IRT ( P=0.046). Additionally, SF-36 scores at discharge were significantly higher in the revascularization group than that in the control group for five indicators including BP, GH, VT, SF, and MH ( P<0.05). Conclusions:For patients with SBS resulting from AMI by chronic multivessel lesions, revascularization therapy may not leading to higher growth in weight and hematological nutritional indicators during IRT, but it is beneficial for improving muscle function, improving EN absorption, increasing the likelihood of PN independence, relieving gastrointestinal symptoms, and enhancing overall quality of life.

Urachal carcinoma (UrC)is a rare urological malignancy. UrC is not obvious in its early symptoms, and is mostly in the advanced stage at diagnosis, with a poor prognosis. Surgical treatment was preferred by partial cystectomy + resection of complete umbilical and umbilical urinary catheter ± pelvic lymph node dissection, and more than 90% of UrC were confirmed as adenocarcinoma through postoperative pathology. Systemic treatment is often based on treatment protocols for bladder adenocarcinoma or colorectal adenocarcinoma.This article reviews recent domestic and international research on UrC, summarizing its incidence, clinical characteristics, diagnosis, and treatment.

Objective To investigate the effects of sugammadex on postoperative pulmonary com-plications(PPCs)and postoperative recovery after thoracoscopic lung resection surgery.Methods A total of 263 patients scheduled for thoracoscopic lung resection surgery between November 2021 and July 2023,112 males and 151 females,aged 18-64 years,BMI 18.5-28.0 kg/m2,ASA physical status Ⅰ-Ⅲ,were randomly divided into three groups:the sugammadex group(group S,n=88),the neostigmine group(group N,n=87),and the control group(group C,n=88).The patient was sent to postanesthesia care unit(PACU)after operation,when the train of four(TOF)count reached 2,group S was given sugamma-dex 2 mg/kg,group N was given neostigmine 0.04 mg/kg+atropine 0.02 mg/kg,and group C was given equal volume of normal saline.The incidence of PPCs from the end of the surgery to the time of discharge was recorded.The time from the end of surgery to extubation,the time from drug administration to recovery of the train of four ratio(TOFr)to 0.9,the TOFr immediately after extubation,the length of stay in PACU,hypoxemia after extubation(SpO2＜90％)were recorded,and the incidence rate of postoperative residual neuromuscular block(PRNB)was calculated.The time of first getting out of the bed for activity,the number of total and effective compressions by the analgesia pump within 48 hours after surgery,the inci-dence of rescue analgesia,the clinical pulmonary infection score(CPIS),the numbers of postoperative nau-sea and vomiting(PONV),total drainage of the chest tube,duration of the chest tube insertion,and the length of postoperative hospital stay were recorded.Results Compared with group C,the incidence of PPCs,PRNB and hypoxemia after extubation were significantly decreased,time from the end of surgery to extubation,time from drug administration to recovery of TOFr to 0.9,the length of stay in PACU,and the first postoperatively out of bed activity time were significantly shortened,the TOFr immediately after extuba-tion was significantly increased,and CPIS was significantly decreased in group S(P＜0.05);the time from the end of surgery to extubation,time from drug administration to recovery of TOFr to 0.9,the length of stay in PACU were significantly shortened,the TOFr immediately after extubation was significantly in-creased,PRNB after extubation were significantly decreased in group N(P＜0.05).Compared with group N,the incidence of PRNB after extubation were significantly decreased,the time from the end of surgery to extubation,the time from drug administration to recovery of TOFr to 0.9,the length of stay in PACU,and the first postoperatively out of bed activity time were significantly shortened,the TOFr immediately after ex-tubation was significantly increased in group S(P＜0.05).There was no significant difference in other in-dexes between the three groups.Conclusion Sugammadex can rapidly antagonize the residual muscle re-laxation,decrease the rate of PPCs and PRNB,and promote rapid recovery of patients after thoracoscopic lung resection surgery.

The access evaluation of new medical technology is an important part of the preclinical application of medical technology and plays a vital role in ensuring the quality and safety of medical services.However,in the con-crete practice of access evaluation,there are still some problems such as imperfect access theoretical framework,imperfect evaluation index system.With the strategic support of health policies,laws,and regulations,the theory and method of HB-HTA are used for reference,core elements such as assessment subject,assessment object,and assessment content are comprehensively considered,the index system is designed from the dimensions of tech-nical characteristics,safety,effectiveness,economy and applicability,and the access evaluation framework of im-ported medical new technologies is constructed.To offer a theoretical framework and evidence-based basis for medi-cal facility medical technology access management.