Objective To explore the safety of Yttrium-90 resin microsphere selective internal radiation therapy (⁹⁰Y-SIRT) on malignant liver tumors. Methods A retrospective analysis was conducted on 64 patients with malignant liver tumors who underwent ⁹⁰Y-SIRT from February 2023 to November 2024 at Weifang People’s Hospital. The clinical characteristics of the patients and the occurrence of adverse reactions after treatment were analyzed to assess the safety of ⁹⁰Y-SIRT. Results Among the 64 patients, there were 52 males (81.25%) and 12 females (18.75%); the average age was (56.29±11.08) years. Seven patients (10.94%) had tumors with maximum diameter of less than 5 cm, 38 patients (59.38%) had tumors with maximum diameter of 5-10 cm, and 19 patients (29.68%) had tumors with maximum diameter of greater than 10 cm. There were 47 cases (73.44%) of solitary lesions and 17 cases (26.56%) of multiple lesions; 53 cases (82.81%) were primary liver cancers and 11 cases (17.19%) were metastatic liver cancers. Of the 64 patients, 63 successfully completed the Technetium-99m macroaggregated albumin (^99mTc-MAA) perfusion test and received the ⁹⁰Y-SIRT; one patient received ⁹⁰Y-SIRT after the second ^99mTc-MAA perfusion test due to a work error. The most common adverse reactions included grade 1 alanine aminotransferase (ALT) elevation in 26 cases (40.62%) and grade 2 in 2 cases (9.37%), grade 1 aspartate aminotransferase (AST) elevation in 27 cases (42.18%) and grade 2 in 7 cases (10.93%); grade 1 nausea in 17 cases (26.56%) and grade 2 in 6 cases (9.37%); grade 1 abdominal pain in 12 cases (18.75%), grade 2 in 5 cases (7.81%), and grade 3 in 1 case (1.56%); grade 1 vomiting in 11 cases (17.18%), grade 2 in 5 cases (7.81%), and grade 3 in 1 case (1.56%). Conclusion The adverse reactions of ⁹⁰Y-SIRT for treating malignant liver tumors are mild, indicating good safety.

Advancements in artificial intelligence (AI) and emerging technologies are rapidly expanding the exploration of chemical space, facilitating innovative drug discovery. However, the transformation of novel compounds into safe and effective drugs remains a lengthy, high-risk, and costly process. Comprehensive early-stage evaluation is essential for reducing costs and improving the success rate of drug development. Despite this need, no comprehensive tool currently supports systematic evaluation and efficient screening. Here, we present druglikeFilter, a deep learning-based framework designed to assess drug-likeness across four critical dimensions: 1) physicochemical rule evaluated by systematic determination, 2) toxicity alert investigated from multiple perspectives, 3) binding affinity measured by dual-path analysis, and 4) compound synthesizability assessed by retro-route prediction. By enabling automated, multidimensional filtering of compound libraries, druglikeFilter not only streamlines the drug development process but also plays a crucial role in advancing research efforts towards viable drug candidates, which can be freely accessed at https://idrblab.org/drugfilter/.

Drug development encompasses multiple processes, wherein protein subcellular localization is essential. It promotes target identification, treatment development, and the design of drug delivery systems. In this research, a deep learning framework called LocPro is presented for predicting protein subcellular localization. Specifically, LocPro is unique in (a) combining protein representations from the pre-trained large language model (LLM) ESM2 and the expert-driven tool PROFEAT, (b) implementing a hybrid deep neural network architecture that integrates convolutional neural network (CNN), fully connected (FC) layer, and bidirectional long short-term memory (BiLSTM) blocks, and (c) developing a multi-label framework for predicting protein subcellular localization at multiple granularity levels. Additionally, a dataset was curated and divided using a homology-based strategy for training and validation. Comparative analyses show that LocPro outperforms existing methods in sequence-based multi-label protein subcellular localization prediction. The practical utility of this framework is further demonstrated through case studies on drug target subcellular localization. All in all, LocPro serves as a valuable complement to existing protein localization prediction tools. The web server is freely accessible at https://idrblab.org/LocPro/.

Traditional Chinese medicine (TCM) represents a paradigmatic approach to personalized medicine, developed through the systematic accumulation and refinement of clinical empirical data over more than 2000 years, and now encompasses large-scale electronic medical records (EMR) and experimental molecular data. Artificial intelligence (AI) has demonstrated its utility in medicine through the development of various expert systems (e.g., MYCIN) since the 1970s. With the emergence of deep learning and large language models (LLMs), AI's potential in medicine shows considerable promise. Consequently, the integration of AI and TCM from both clinical and scientific perspectives presents a fundamental and promising research direction. This survey provides an insightful overview of TCM AI research, summarizing related research tasks from three perspectives: systems-level biological mechanism elucidation, real-world clinical evidence inference, and personalized clinical decision support. The review highlights representative AI methodologies alongside their applications in both TCM scientific inquiry and clinical practice. To critically assess the current state of the field, this work identifies major challenges and opportunities that constrain the development of robust research capabilities-particularly in the mechanistic understanding of TCM syndromes and herbal formulations, novel drug discovery, and the delivery of high-quality, patient-centered clinical care. The findings underscore that future advancements in AI-driven TCM research will rely on the development of high-quality, large-scale data repositories; the construction of comprehensive and domain-specific knowledge graphs (KGs); deeper insights into the biological mechanisms underpinning clinical efficacy; rigorous causal inference frameworks; and intelligent, personalized decision support systems.
Medicine, Chinese Traditional/methods* ; Artificial Intelligence ; Humans ; Precision Medicine ; Decision Support Systems, Clinical

Objective To investigate the application value of systemic inflammatory response index(SIRI)in patients with acute-on-chronic liver failure(ACLF)and co-infection.Methods A retrospective analysis was performed for the clinical data of 579 ACLF patients with co-infection who were diagnosed and treated in The Fifth Medical Center of Chinese PLA General Hospital from January 2014 to March 2016,including demographic features,laboratory markers,and complications,and SIRI,Model for End-Stage Liver Disease(MELD)score,MELD combined with serum sodium concentration(MELD-Na)score,and Child-Pugh score were calculated.According to the results of follow-up on day 90,the patients were divided into survival group with 210 patients and death group with 369 patients.The independent-samples t test was used for comparison of normally distributed continuous data between two groups;the Mann-Whitney U rank sum test was used for comparison of non-normally distributed continuous data between two groups;the chi-square test were used for comparison of categorical data between two groups.The binary logistic regression analysis was used to investigate the independent risk factors for 90-day death.The receiver operating characteristic(ROC)curve and the area under the ROC curve(AUC)were used to assess the performance of SIRI,MELD-Na score,and Child-Pugh score in predicting the prognosis of ACLF patients with co-infection.The Kaplan-Meier survival analysis was performed based on the optimal cut-off value of SIRI.Results Among the 597 ACLF patients with co-infection,384(66.32%)had HBV-related ACLF and 114(19.69%)had alcohol-related ACLF;as for the main infection sites,316(54.58%)had abdominal infection and 133(22.97%)had pulmonary infection;the 90-day mortality rate was 63.73%.The multivariate logistic regression analysis showed that SIRI(odds ratio[OR]=1.177,95%confidence interval[CI]:1.117-1.239,P<0.05),blood ammonia(OR=1.009,95%CI:1.001-1.018,P<0.05),MELD-Na score(OR=1.047,95%CI:1.016-1.080,P<0.05),Child-Pugh score(OR=1.351,95%CI:1.054-1.730,P<0.05),age(OR=1.045,95%CI:1.021-1.070,P<0.05),comorbidity with hepatic encephalopathy(OR=2.269,95%CI:1.305-3.946,P<0.05),and comorbidity with acute kidney injury(OR=1.730,95%CI:0.990-3.023,P<0.05)were independent risk factors for 90-day death in ACLF patients with co-infection.The Pearson correlation analysis showed that SIRI was positively correlated with MELD-Na score(r=0.282,P<0.001)and Child-Pugh score(r=0.168,P<0.001).SIRI,MELD-Na score,and Child-Pugh score had an AUC of 0.855,0.734,and 0.690,respectively,in predicting 90-day death,and SIRI had a higher predictive efficiency than MELD-Na score and Child-Pugh score(Z=4.922 and 6.289,both P<0.001),with a sensitivity of 76.7%and a specificity of 82.9%.In addition,SIRI combined with MELD-Na score or Child-Pugh score improved the predictive efficiency of MELD-Na score(0.854 vs 0.734,Z=6.899,P<0.001)and Child-Pugh score(0.858 vs 0.690,Z=8.725,P<0.001).The patients with high SIRI(≥4.08)had a 90-day survival rate of 11.29%(36/319),which was significantly lower than that in the patients with low SIRI(<4.08)(χ2=225.24,P<0.001).Conclusion SIRI is an independent risk factor for death in ACLF patients with co-infection and has a good clinical value in predicting prognosis,with the advantages of convenience and low costs.

Drug development encompasses multiple processes,wherein protein subcellular localization is essential.It promotes target identification,treatment development,and the design of drug delivery systems.In this research,a deep learning framework called LocPro is presented for predicting protein subcellular localization.Specifically,LocPro is unique in(a)combining protein representations from the pre-trained large language model(LLM)ESM2 and the expert-driven tool PROFEAT,(b)implementing a hybrid deep neural network architecture that integrates convolutional neural network(CNN),fully connected(FC)layer,and bidirectional long short-term memory(BiLSTM)blocks,and(c)developing a multi-label framework for predicting protein subcellular localization at multiple granularity levels.Additionally,a dataset was curated and divided using a homology-based strategy for training and validation.Compar-ative analyses show that LocPro outperforms existing methods in sequence-based multi-label protein subcellular localization prediction.The practical utility of this framework is further demonstrated through case studies on drug target subcellular localization.All in all,LocPro serves as a valuable complement to existing protein localization prediction tools.The web server is freely accessible at https://idrblab.org/LocPro/.

Advancements in artificial intelligence(AI)and emerging technologies are rapidly expanding the exploration of chemical space,facilitating innovative drug discovery.However,the transformation of novel compounds into safe and effective drugs remains a lengthy,high-risk,and costly process.Comprehensive early-stage evaluation is essential for reducing costs and improving the success rate of drug development.Despite this need,no comprehensive tool currently supports systematic evaluation and efficient screening.Here,we present druglikeFilter,a deep learning-based framework designed to assess drug-likeness across four critical dimensions:1)physicochemical rule evaluated by systematic determination,2)toxicity alert investigated from multiple perspectives,3)binding affinity measured by dual-path analysis,and 4)compound synthesizability assessed by retro-route prediction.By enabling automated,multidimensional filtering of compound libraries,druglikeFilter not only streamlines the drug development process but also plays a crucial role in advancing research efforts towards viable drug candidates,which can be freely accessed at https://idrblab.org/drugfilter/.

Objective:To investigate the clinical efficacy of minimally invasive bone plate technology combined with interlocking intramedullary nail fixation in the treatment of Schatzker type V-VI tibial plateau fractures.Methods:This study is a prospective randomized controlled trial involving 102 patients with Schatzker type V-VI tibial plateau fractures admitted to the First People's Hospital of Yuhang District from November 2020 to October 2023. The patients were randomly divided into a control group ( n = 48) and a study group ( n = 54) using the random number table method. The study group received treatment with minimally invasive plate technology combined with interlocking intramedullary nail fixation, while the control group underwent double bone plate fixation through medial and lateral knee incisions. Surgical outcomes and bone healing were compared between the two groups. All participants were followed up for 1 year after surgery, during which knee joint function was assessed at 1, 6, and 12 months using the Hospital for Special Surgery knee score and balance ability was evaluated using the Berg Balance Scale. The incidence of postoperative complications was also compared between the two groups. Results:The study group had significantly shorter surgical time [(69.38 ± 12.64) minutes], intraoperative blood loss [(165.20 ± 17.58) mL], and fracture healing time [(14.51 ± 3.02) weeks] compared with the control group [(91.24 ± 15.18) minutes, (222.19 ± 20.47) mL, (17.04 ± 4.11) weeks, t = 7.93, 15.13, 3.51, all P < 0.05]. At 1, 6, and 12 months after surgery, the Berg Balance Scale scores in the study group were (44.55 ± 4.01), (49.31 ± 3.67), and (53.11 ± 3.18), respectively. These scores were significantly higher than those in the control group [(40.27 ± 3.98), (45.65 ± 3.16), (48.26 ± 3.20), t = -5.40, -5.36, -7.65, all P < 0.05]. At 1, 6, and 12 months after surgery, the Hospital for Special Surgery knee scores in the study group were (68.29 ± 4.25), (76.37 ± 5.25), (83.31 ± 5.01) respectively. These scores were significantly higher than those in the control group [(63.57 ± 4.14), (72.08 ± 4.50), (80.05 ± 4.57), t = -5.67, -4.40, -3.42, all P < 0.05]. There was no significant incidence in the incidence of complications between the study and control groups [12.96% (7/54) vs. 18.75% (9/48), P > 0.05]. Conclusions:The use of minimally invasive bone plate technology combined with interlocking intramedullary nail fixation for the treatment of Schatzker type V-VI tibial plateau fractures has demonstrated significant short-term clinical results, including reduced intraoperative blood loss, shorter fracture healing time, and improved recovery of joint function after surgery.

Objective:To investigate the clinical efficacy of minimally invasive bone plate technology combined with interlocking intramedullary nail fixation in the treatment of Schatzker type V-VI tibial plateau fractures.Methods:This study is a prospective randomized controlled trial involving 102 patients with Schatzker type V-VI tibial plateau fractures admitted to the First People's Hospital of Yuhang District from November 2020 to October 2023. The patients were randomly divided into a control group ( n = 48) and a study group ( n = 54) using the random number table method. The study group received treatment with minimally invasive plate technology combined with interlocking intramedullary nail fixation, while the control group underwent double bone plate fixation through medial and lateral knee incisions. Surgical outcomes and bone healing were compared between the two groups. All participants were followed up for 1 year after surgery, during which knee joint function was assessed at 1, 6, and 12 months using the Hospital for Special Surgery knee score and balance ability was evaluated using the Berg Balance Scale. The incidence of postoperative complications was also compared between the two groups. Results:The study group had significantly shorter surgical time [(69.38 ± 12.64) minutes], intraoperative blood loss [(165.20 ± 17.58) mL], and fracture healing time [(14.51 ± 3.02) weeks] compared with the control group [(91.24 ± 15.18) minutes, (222.19 ± 20.47) mL, (17.04 ± 4.11) weeks, t = 7.93, 15.13, 3.51, all P < 0.05]. At 1, 6, and 12 months after surgery, the Berg Balance Scale scores in the study group were (44.55 ± 4.01), (49.31 ± 3.67), and (53.11 ± 3.18), respectively. These scores were significantly higher than those in the control group [(40.27 ± 3.98), (45.65 ± 3.16), (48.26 ± 3.20), t = -5.40, -5.36, -7.65, all P < 0.05]. At 1, 6, and 12 months after surgery, the Hospital for Special Surgery knee scores in the study group were (68.29 ± 4.25), (76.37 ± 5.25), (83.31 ± 5.01) respectively. These scores were significantly higher than those in the control group [(63.57 ± 4.14), (72.08 ± 4.50), (80.05 ± 4.57), t = -5.67, -4.40, -3.42, all P < 0.05]. There was no significant incidence in the incidence of complications between the study and control groups [12.96% (7/54) vs. 18.75% (9/48), P > 0.05]. Conclusions:The use of minimally invasive bone plate technology combined with interlocking intramedullary nail fixation for the treatment of Schatzker type V-VI tibial plateau fractures has demonstrated significant short-term clinical results, including reduced intraoperative blood loss, shorter fracture healing time, and improved recovery of joint function after surgery.