The rapid development of artificial intelligence (AI), especially generative AI (GenAI), has already brought, and will continue to bring, revolutionary changes to our daily production and life, as well as create new opportunities and challenges for diagnostic and therapeutic practices in the medical field. Haihe Hospital of Tianjin University collaborates with the National Supercomputer Center in Tianjin, Tianjin University, and other institutions to carry out research in areas such as smart healthcare, smart services, and smart management. We have conducted research and development of a full-process disease diagnosis and treatment assistance system based on GenAI in the field of smart healthcare. The development of this project is of great significance. The first goal is to upgrade and transform the hospital's information center, organically integrate it with existing information systems, and provide the necessary computing power storage support for intelligent services within the hospital. We have implemented the localized deployment of three models: Tianhe "Tianyuan", WiNGPT, and DeepSeek. The second is to create a digital avatar of the chief physician/chief physician's voice and image by integrating multimodal intelligent interaction technology. With generative intelligence as the core, this solution provides patients with a visual medical interaction solution. The third is to achieve deep adaptation between generative intelligence and the entire process of patient medical treatment. In this project, we have developed assistant tools such as intelligent inquiry, intelligent diagnosis and recognition, intelligent treatment plan generation, and intelligent assisted medical record generation to improve the safety, quality, and efficiency of the diagnosis and treatment process. This study introduces the content of a full-process disease diagnosis and treatment assistance system, aiming to provide references and insights for the digital transformation of the healthcare industry.
Artificial Intelligence ; Humans ; Delivery of Health Care ; Generative Artificial Intelligence

AIM: To observe the clinical efficacy of Fuzheng Xiaoliu Granules in the treatment of stage II primary liver cancer and to explore its mechanism of action from the perspective of metabolomics. METHODS: Sixty patients with stage II primary liver cancer who achieved complete remission (CR) after comprehensive interventional therapy were randomly divided into treatment group and placebo group, with 30 patients in each group. They were treated for one year and observed for one year. The one-year recurrence rate, traditional chinese medicine (TCM) syndrome score, alpha-fetoprotein and child-pugh grade were compared between the two groups. The serum metabolites of the two groups before and after treatment were screened by ultra-high liquid chromatography-mass spectrometry technology, and the metabolic pathways and related biological pathways were analyzed. RESULTS: The one-year recurrence rate of the treatment group was significantly lower than that of the placebo group, and the overall improvement rate of TCM syndrome score was significantly better than that of the placebo group (P<0.05). There was no statistical significance in the comparison of alpha-fetoprotein and child-pugh grade between the two groups after treatment (P>0.05). Metabolomics results showed that there were 39 and 33 different metabolites in the treatment group before and after treatment and in the two groups after treatment, respectively. After enrichment analysis and topological analysis of the different metabolites, it was found that Fuzheng Xiaoliu Granules could affect amino acid metabolism, fatty acid metabolism and purine metabolism and other metabolic pathways. Before and after treatment in the treatment group and after treatment in the two groups, there were the same differential metabolites and metabolic pathways in the two comparison results. The same differential metabolites with FOLD CHANGE>1 include Stearic acid, Hypoxanthine, Kynurenic acid, Arachidonic acid, and N-Arachidonoyl Dopamine. The same metabolic pathways with Impact>0.1 include Arachidonic acid metabolism and Histidine metabolism. CONCLUSION: Fuzheng xiaoliu granules can effectively reduce the recurrence rate of stage II liver cancer patients after comprehensive intervention and improve the TCM syndrome. It may inhibit the activation of PI3K/Akt and ERK signaling pathways by regulating the content of metabolites involved in metabolic pathways such as amino acids and fatty acids, thereby delaying tumor recurrence.

ObjectiveTo observe the effect of video-based mirror therapy on lower limb motor function, walking ability, and balance of stroke patients at recovery stage. MethodsFrom January to October, 2022, 43 stroke patients in Beijing Bo'ai Hospital were randomly divided into control group (n = 22) and mirror therapy group (n = 21). Both groups received routine rehabilitation, and the mirror therapy group received video-based mirror therapy additionally, for four weeks. They were assessed with Fugl-Meyer Assessment-Lower Extremities (FMA-LE), Functional Ambulation Category (FAC) and Berg Balance Scale (BBS) before and after treatment. ResultsAfter treatment, the scores of FMA-LE, FAC and BBS improved significantly in both groups (|t| > 6.205, P < 0.001), and the scores of FMA-LE and BBS were better in the mirror therapy group than in the control group (|t| > 2.164, P < 0.05). ConclusionCombining with video-based mirror therapy could facilitate to improve the lower limb motor function and balance ability of stroke patients at recovery stage.

ObjectiveTo explore the effects of different intensity of wearable lower limb rehabilitation robot-assisted training on walking function, lower limb motor function, balance function and functional independence of stroke patients. MethodsFrom November, 2021 to December, 2022, 60 stroke patients hospitalized in Beijing Bo'ai Hospital were randomly divided into control group (n = 20), observation group 1 (n = 20) and observation group 2 (n = 20). All the groups received routine rehabilitation, while the control group received routine walking training 30 minutes a day, the observation group 1 received wearable lower limb rehabilitation robot-assisted training 30 minutes a day, and the observation group 2 received wearable lower limb rehabilitation robot-assisted training 60 minutes a day, for four weeks. They were assessed with Functional Ambulation Category scale (FAC), Fugl-Meyer Assessment-Lower Extremities (FMA-LE), Berg Balance Scale (BBS) and Rivermead Mobility Index (RMI) before and after treatment. ResultsOne case in the observation group 1 and three cases in the observation group 2 dropped down. The FAC, FMA-LE, BBS and RMI scores improved in all the three groups after treatment (|Z| > 3.448, |t| > 8.102, P < 0.001), and there was no significant difference in all the indexes among the three groups (|H| < 4.643, F = 1.454, P > 0.05); however, the improvement of BBS score was more in the observation group 1 than in the control group (P < 0.05), and the improvement of all the indexes was more in the observation group 2 than in the control group (P < 0.05). ConclusionThe wearable lower limb rehabilitation robot-assisted training may promote the recovery of walking function, lower limb motor function, balance function and functional independence of stroke patients, and high-intensity training seems to be more effective.

MEK is a canonical effector of mutant KRAS; however, MEK inhibitors fail to yield satisfactory clinical outcomes in KRAS-mutant cancers. Here, we identified mitochondrial oxidative phosphorylation (OXPHOS) induction as a profound metabolic alteration to confer KRAS-mutant non-small cell lung cancer (NSCLC) resistance to the clinical MEK inhibitor trametinib. Metabolic flux analysis demonstrated that pyruvate metabolism and fatty acid oxidation were markedly enhanced and coordinately powered the OXPHOS system in resistant cells after trametinib treatment, satisfying their energy demand and protecting them from apoptosis. As molecular events in this process, the pyruvate dehydrogenase complex (PDHc) and carnitine palmitoyl transferase IA (CPTIA), two rate-limiting enzymes that control the metabolic flux of pyruvate and palmitic acid to mitochondrial respiration were activated through phosphorylation and transcriptional regulation. Importantly, the co-administration of trametinib and IACS-010759, a clinical mitochondrial complex I inhibitor that blocks OXPHOS, significantly impeded tumor growth and prolonged mouse survival. Overall, our findings reveal that MEK inhibitor therapy creates a metabolic vulnerability in the mitochondria and further develop an effective combinatorial strategy to circumvent MEK inhibitors resistance in KRAS-driven NSCLC.

Purpose: Platelet-related indices, including mean platelet volume (MPV) and plateletocrit (PCT), have been reported as new prognostic factors of overall survival (OS) in many cancers, but not yet in biliary tract cancer (BTC). We intended to assess these indices in predicting OS in BTC patients with the aim to build a new prognostic model for patients with BTC after surgical resection. Materials and Methods: Survival analysis and time receiver operating characteristic analysis were applied to screen the platelet indices. Univariate and multivariate Cox analyses were used to identify independent prognostic factors and develop a new prognostic model. Harrell’s C-statistics, calibration curves, and decisive curve analysis were used to assess the model. Results: MPV and platelet distribution width (PDW)/PCT showed the best prognostic accuracy among the platelet indices. In multivariable analysis, factors predictive of poor OS were presence of nodal involvement, Non-radical surgery, poor tumor differentiation, carbohydrate antigen 19-9 > 100 U/mL, MPV > 8.1 fl, and PDW/PCT > 190. The new model was found to be superior to the TNM staging system and our new staging system showed higher discriminative power. Conclusion MPV and PDW/PCT have high prognostic value in BTC patients, and the novel staging system based on these two indices showed good discrimination and accuracy compared with the American Joint Committee on Cancer 7th TNM staging system.

Purpose: Platelet-related indices, including mean platelet volume (MPV) and plateletocrit (PCT), have been reported as new prognostic factors of overall survival (OS) in many cancers, but not yet in biliary tract cancer (BTC). We intended to assess these indices in predicting OS in BTC patients with the aim to build a new prognostic model for patients with BTC after surgical resection. Materials and Methods: Survival analysis and time receiver operating characteristic analysis were applied to screen the platelet indices. Univariate and multivariate Cox analyses were used to identify independent prognostic factors and develop a new prognostic model. Harrell’s C-statistics, calibration curves, and decisive curve analysis were used to assess the model. Results: MPV and platelet distribution width (PDW)/PCT showed the best prognostic accuracy among the platelet indices. In multivariable analysis, factors predictive of poor OS were presence of nodal involvement, Non-radical surgery, poor tumor differentiation, carbohydrate antigen 19-9 > 100 U/mL, MPV > 8.1 fl, and PDW/PCT > 190. The new model was found to be superior to the TNM staging system and our new staging system showed higher discriminative power. Conclusion MPV and PDW/PCT have high prognostic value in BTC patients, and the novel staging system based on these two indices showed good discrimination and accuracy compared with the American Joint Committee on Cancer 7th TNM staging system.

Objective:To analyze the risk factors of renal function recovery in patients with severe acute pancreatitis (SAP) combined with acute kidney injury (AKI).Methods:A retrospective study was conducted in 105 SAP patients with AKI who were admitted to ICU or EICU of the Affiliated Hospital of Qingdao University from January 2013 to October 2019. According to the recovery of renal function at 28 days, the patients were divided into the renal function recovery group and the poor recovery group. Multivariate logistic regression analysis was used to analyze the clinical data of the two groups and to determine the risk factors related to renal function recovery.Results:According to the recovery of renal function, 105 patients were divided into the renal function recovery group ( n=73) and the poor recovery group ( n=32). Compared with the renal function recovery group, patients in the poor recovery group were older, had a higher prevalence of diabetes and coronary heart disease and a higher score on the acute physiology and chronic health evaluation Ⅱ(APACHE Ⅱ); More patients had abdominal necrosis infection and abdominal hemorrhage. The proportion of patients who applied mechanical ventilation was higher in the poor recovery group. Multivariate logistic regression analysis showed that abdominal necrosis infection ( OR=5.088, 95% CI:1.041-24.871, P=0.044) and mechanical ventilation ( OR=4.615, 95% CI:1.126-18.904, P=0.034) were the independent risk factors of renal function recovery in SAP patients with AKI. Conclusions:Abdominal necrosis infection and mechanical ventilation are the independent risk factors for renal function recovery in patients with SAP and AKI.

Purpose: The systemic inflammation response index (SIRI) has been reported to have prognostic ability in various solid tumors but has not been studied in gallbladder cancer (GBC). We aimed to determine its prognostic value in GBC. Materials and Methods: From 2003 to 2017, patients with confirmed GBC were recruited. To determine the SIRI’s optimal cutoff value, a time-dependent receiver operating characteristic curve was applied. Univariate and multivariate Cox analyses were performed for the recognition of significant factors. Then the cohort was randomly divided into the training and the validation set. A nomogram was constructed using the SIRI and other selected indicators in the training set, and compared with the TNM staging system. C-index, calibration plots, and decision curve analysis were performed to assess the nomogram’s clinical utility. Results: One hundred twenty-four patients were included. The SIRI’s optimal cutoff value divided patients into high (≥ 0.89) and low SIRI (< 0.89) groups. Kaplan-Meier curves according to SIRI levels were significantly different (p < 0.001). The high SIRI group tended to stay longer in hospital and lost more blood during surgery. SIRI, body mass index, weight loss, carbohydrate antigen 19-9, radical surgery, and TNM stage were combined to generate a nomogram (C-index, 0.821 in the training cohort, 0.828 in the validation cohort) that was significantly superior to the TNM staging system both in the training (C-index, 0.655) and validation cohort (C-index, 0.649). Conclusion The SIRI is an independent predictor of prognosis in GBC. A nomogram based on the SIRI may help physicians to precisely stratify patients and implement individualized treatment.

OBJECTIVE: To find the pathogenies and risk factors related to surgical intensive care unit (SICU) readmission for patients who underwent hepatobiliary-pancreatic surgery, and to develop a predictive model for determining patients who are likely to be readmitted to SICU. METHODS: The patients who admitted to SICU of the Affiliated Hospital of Qingdao University from January 2013 to August 2018; who first stayed in SICU after hepatobiliary-pancreatic surgery; who were assessed and discharged from SICU by surgeons and SICU physicians after treatment, and then transferred to SICU again because of the change of their condition were enrolled. The unintended return to SICU within 3 days and 7 days were recorded. Patients who returned to SICU within 7 days were studied for the pathogenies, risk factors and predictive model of returning to SICU, and non-returning patients were enrolled according to 1:1 as the controls. A total of 43 indicators were divided into five categories, including general clinical data, medical history, surgical indicators before first admission of SICU, length of first SICU stay, and other indicators on the day of first discharge from the SICU. Logistic regression was used to screen the risk factors associated with SICU readmission, then the Nomogram diagram was drawn by using the R 3.4.1 software for predicting SICU readmission, and the classification performance of Nomogram was evaluated by self-help sampling test. RESULTS: Of the 763 patients discharged from the SICU, 2.10% (16/763) of them were readmitted within 3 days and 3.28% (25/763) were readmitted within 7 days to the SICU unexpectedly. The pathogenies of SICU readmission within 7 days included infection [56.00% (14/25)], heart failure [16.00% (4/25)], infarction [12.00% (3/25)], bleeding [12.00% (3/25)], and sutures splitting [4.00% (1/25)]. The pathogenies of SICU readmission within 3 days included infection [56.25% (9/16)], heart failure [18.75% (3/16)], infarction [12.50% (2/16)], and bleeding [12.50% (2/16)]. Nomogram analysis showed that the risk factors associated with unplanned SICU readmission were length of first SICU stay, history of hypertension, and activity of daily living (ADL) score, white blood cell count (WBC), arterial partial pressure of oxygen (PaO₂), prothrombin time (PT), fibrinogen (FIB) on the day of first SICU discharge. Self-help sampling test was carried out on the Nomogram map, and the results showed that the coherence index (C-index) was 0.962 [95% confidence interval (95%CI) = 0.869-1.057]. The classification performance of the model was good. CONCLUSIONS The common pathogenies of SICU readmission for patients who underwent hepatobiliary-pancreatic surgery were infection, heart failure, infarction and bleeding. Risk factors of readmission after SICU discharge included the length of first SICU stay, history of hypertension, and ADL score, WBC, PaO₂, PT, FIB on the day of first SICU discharge. The model consisted of above risk factors showed a good performance in predicting the probability of readmission after SICU discharge for patients who underwent hepatobiliary-pancreatic surgery.
Biliary Tract Diseases/surgery* ; Digestive System Surgical Procedures/adverse effects* ; Humans ; Intensive Care Units ; Liver Diseases/surgery* ; Models, Statistical ; Pancreatic Diseases/surgery* ; Patient Readmission/statistics & numerical data* ; Postoperative Complications/therapy* ; Risk Factors