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*

OBJECTIVE: To assess the relationship between blood pressure reactivity index (BPRI) and in-hospital mortality risk in patients with sepsis-associated acute kidney injury (SA-AKI). METHODS: A retrospective cohort study was conducted to collect data from patients admitted to the intensive care unit (ICU) and clinically diagnosed with SA-AKI between 2008 and 2019 in the Medical Information Mart for Intensive Care-IV (MIMIC-IV) database in the United States. The collected data included demographic characteristics, comorbidities, vital signs, laboratory parameters, sequential organ failure assessment (SOFA) and simplified acute physiology scoreII(SAPSII) within 48 hours of SA-AKI diagnosis, stages of AKI, treatment regimens, mean BPRI during the first and second 24 hours (BPRI_0_24, BPRI_24_48), and outcome measures including primary outcome (in-hospital mortality) and secondary outcomes (ICU length of stay and total hospital length of stay). Variables with statistical significance in univariate analysis were included in LASSO regression analysis for variable selection, and the selected variables were subsequently incorporated into multivariate Logistic regression analysis to identify independent predictors associated with in-hospital mortality in SA-AKI patients. Restricted cubic spline (RCS) analysis was employed to examine whether there was a linear relationship between BPRI within 48 hours and in-hospital mortality in SA-AKI patients. Basic prediction models were constructed based on the independent predictors identified through multivariate Logistic regression analysis, and receiver operator characteristic curve (ROC curve) was plotted to evaluate the predictive performance of each basic prediction model before and after incorporating BPRI. RESULTS: A total of 3 517 SA-AKI patients admitted to the ICU were included, of whom 826 died during hospitalization and 2 691 survived. The BPRI values within 48 hours of SA-AKI diagnosis were significantly lower in the death group compared with the survival group [BPRI_0_24: 4.53 (1.81, 8.11) vs. 17.39 (5.16, 52.43); BPRI_24_48: 4.76 (2.42, 12.44) vs. 32.23 (8.85, 85.52), all P < 0.05]. LASSO regression analysis identified 20 variables with non-zero coefficients that were included in the multivariate Logistic regression analysis. The results showed that respiratory rate, temperature, pulse oxygen saturation (SpO₂), white blood cell count (WBC), hematocrit (HCT), activated partial thromboplastin time (APTT), lactate, oxygenation index, SOFA score, fluid balance (FB), BPRI_0_24, and BPRI_24_48 were all independent predictors for in-hospital mortality in SA-AKI patients (all P < 0.05). RCS analysis revealed that both BPRI showed "L"-shaped non-linear relationships with the risk of in-hospital mortality in SA-AKI patients. When BPRI_0_24 ≤ 14.47 or BPRI_24_48 ≤ 24.21, the risk of in-hospital mortality in SA-AKI increased as BPRI values decreased. Three basic prediction models were constructed based on the identified independent predictors: Model 1 (physiological indicator model) included respiratory rate, temperature, SpO₂, and oxygenation index; Model 2 (laboratory indicator model) included WBC, HCT, APTT, and lactate; Model 3 (scoring indicator model) included SOFA score and FB. ROC curve analysis showed that the predictive performance of the basic models ranked from high to low as follows: Model 3, Model 2, and Model 1, with area under the curve (AUC) values of 0.755, 0.661, and 0.655, respectively. The incorporation of BPRI indicators resulted in significant improvement in the discriminative ability of each model (all P < 0.05), with AUC values increasing to 0.832 for Model 3+BPRI, 0.805 for Model 2+BPRI, and 0.808 for Model 1+BPRI. CONCLUSIONS BPRI is an independent predictor factor for in-hospital mortality in SA-AKI patients. Incorporating BPRI into the prediction model for in-hospital mortality risk in SA-AKI can significantly improve its predictive capability.
Humans ; Acute Kidney Injury/mortality* ; Sepsis/complications* ; Retrospective Studies ; Hospital Mortality ; Prognosis ; Blood Pressure ; Intensive Care Units ; Male ; Female ; Length of Stay ; Middle Aged ; Aged ; Adult ; Logistic Models

Patients with severe trauma require an extremely timely treatment and transfusion plays an irreplaceable role in the emergency treatment of such patients. An increasing number of evidence-based medicinal evidences and clinical practices suggest that patients with severe traumatic bleeding benefit from early transfusion of low-titer group O whole blood or hemostatic resuscitation with red blood cells, plasma and platelet of a balanced ratio. However, the current domestic mode of blood supply cannot fully meet the requirements of timely and effective blood transfusion for emergency treatment of patients with severe trauma in clinical practice. In order to solve the key problems in blood supply and blood transfusion strategies for emergency treatment of severe trauma, Branch of Clinical Transfusion Medicine of Chinese Medical Association, Group for Trauma Emergency Care and Multiple Injuries of Trauma Branch of Chinese Medical Association, Young Scholar Group of Disaster Medicine Branch of Chinese Medical Association organized domestic experts of blood transfusion medicine and trauma treatment to jointly formulate Chinese expert consensus on blood support mode and blood transfusion strategies for emergency treatment of severe trauma patients ( version 2024). Based on the evidence-based medical evidence and Delphi method of expert consultation and voting, 10 recommendations were put forward from two aspects of blood support mode and transfusion strategies, aiming to provide a reference for transfusion resuscitation in the emergency treatment of severe trauma and further improve the success rate of treatment of patients with severe trauma.

Objective:To investigate the effect of repetitive transcranial magnetic stimulation combined with cognitive function training on improving cognitive and psychological and behavioral symptoms in patients with vascular dementia.Methods:A total of 80 patients with vascular dementia who received treatment at The Third People's Hospital of Huzhou from October 2020 to October 2022 were included in this study. They were divided into a control group and an observation group ( n = 40 per group) based on different treatment methods. The control group received repetitive transcranial magnetic stimulation, while the observation group received both repetitive transcranial magnetic stimulation and cognitive function training. Both groups were treated continuously for 4 weeks. The scores of The Mini-Mental State Examination (MMSE), the Behavioral Pathology in Alzheimer's Disease Rating Scale (BE-HAVE-AD), Activities of Daily Living (ADL), and Pittsburgh Sleep Quality Index (PSQI) of the two groups were analyzed before and after treatment. Additionally, serum levels of homocysteine and neuron-specific enolase in both groups were compared before and after treatment. The clinical efficacy of the two groups was evaluated, and the total response rate was calculated. Adverse reactions occurring during the treatment period in both groups were also recorded. Results:Before treatment, the Mini-Mental State Examination (MMSE) scores for the control and observation groups were (14.92 ± 2.43) points and (14.83 ± 2.56) points, respectively. After treatment, the scores were (22.81 ± 3.05) points for the control group and (25.62 ± 4.07) points for the observation group. After treatment, the MMSE scores in both groups were significantly higher than the respective levels before treatment in the corresponding group, and the observation group had a significantly higher score than the control group ( t = 2.25, P < 0.05). Before treatment, the BE-HAVE-AD scores for the control and observation groups were (45.28 ± 6.27) points and (44.95 ± 6.38) points, respectively. After treatment, the scores were (27.54 ± 2.22) points for the control group and (23.07 ± 1.79) points for the observation group. After treatment, the BE-HAVE-AD scores were significantly lower than those before treatment in each group, and the observation group had a significantly lower score than the control group ( t = 9.56, P < 0.05). Before treatment, the ADL scores for the control and observation groups were (23.17 ± 1.43) points and (22.83 ± 1.64) points, respectively. After treatment, the scores were (38.27 ± 3.25) points for the control group and (41.52 ± 4.26) points for the observation group. After treatment, the ADL scores in each group were significantly higher than their respective levels before treatment, and the observation group had a significantly higher score than the control group ( t = 3.83, P < 0.05). Before treatment, the PSQI scores for the control and observation groups were (16.423 ± 1.51) points and (15.86 ± 1.49) points, respectively. After treatment, the scores were (9.16 ± 1.12) points for the control group and (7.07 ± 1.07) points for the observation group. After treatment, the PSQI scores were significantly lower than those before treatment in each group, and the observation group had a significantly lower score than the control group ( t = 8.53, P < 0.05). Before treatment, the serum levels of homocysteine in the control and observation groups were (54.27 ± 8.21) ng/L and (55.13 ± 7.64) ng/L, respectively, while the serum levels of neuron-specific enolase in these two groups were (59.66 ± 9.51) μg/L and (60.97 ± 10.29) μg/L, respectively. After treatment, the serum levels of homocysteine in the control and observation groups were (30.63 ± 1.95) ng/L and (25.57 ± 2.06) ng/L, respectively, and the serum levels of neuron-specific enolase in these two groups were (49.23 ± 6.12) μg/L and (37.21 ± 7.01) μg/L, respectively. After treatment, the serum levels of homocysteine and neuron-specific enolase in each group were significantly lower than the respective levels before treatment in the corresponding group; the observation group exhibited significantly lower serum levels of homocysteine and neuron-specific enolase than the control group ( t = 11.28, 8.16, both P < 0.05). The total response rate in the observation group was 95.00% (38/40), which was significantly higher than that in the control group [72.50% (29/40), P < 0.05]. The incidence of adverse reactions in the observation group was 5.00% (2/40), which was significantly lower than that in the control group [20.00% (8/40), χ2 = 7.44, P < 0.05]. Conclusion:Repetitive transcranial magnetic stimulation combined with cognitive function training can more effectively improve cognitive and psychological and behavioral symptoms in patients with vascular dementia, has better efficacy, and is safer compared with repetitive transcranial magnetic stimulation alone.

Objective To explore the expression levels of serum spalt-like transcription factor 4(SALL4)mRNA,ol-factomedin 4(OLFM4)mRNA,and activin-A in patients with rheumatoid arthritis(RA),and analyze their correlation with clinical characteristics and their predictive value on joint deformities.Methods A total of 130 RA patients admitted to the Third Affiliated Hospital of Henan University of Traditional Chinese Medicine from January 2021 to April 2023 were selected as the RA group,and 102 healthy volunteers who underwent physical examinations in the outpatient during the same period were selected as the control group.The serum Activin-A level was measured by using the enzyme-linked immunosorbent assay,and the serum SALL4 and OLFM4 mRNA levels were measured by using the reverse transcription polymerase chain reaction on the second day of admission for patients in the RA group and on the day of physical examination for patients in the control group.The serum SALL4 mRNA,OLFM4 mRNA and Activin-A levels were compared between the RA group and the control group and among the RA patients with different clinical characteristics.The influencing factors of RA combined with joint deformities were identified by using univariate and multivariate logistic regression.The receiver operating characteristic curve was used to analyze the value of SALL4 mRNA,OLFM4 mRNA and Activin-A in predicting joint deformities in RA.Results The relative expression levels of serum SALL4 mRNA and OLFM4 mRNA and the level of Activin-A of patients in the RA group were significantly higher than those in the control group(P＜0.05).The relative expression levels of serum SALL4 mRNA and OLFM4 mRNA and the level of Activin-A of patients with severe disease activity were significantly higher than those of patients with moderate and mild disease activity,and the relative expression levels of serum SALL4 mRNA and OLFM4 mRNA and the level of Activin-A of patients with moderate disease activity were significantly higher than those of patients with mild disease activity(P＜0.05).The relative expression levels of serum SALL4 mRNA and OLFM4 mRNA and the level of Activin-A of patients with the number of affected joints≥10,duration of synovitis≥6 weeks,and joint deformities were significantly higher than those in patients with the number of affected joints＜10,duration of synovitis＜6 weeks,and no joint deformities(P＜0.05).There was no statistically significant difference in the relative expression levels of serum SALL4 mRNA and OLFM4 mRNA and the level of Activin-A among patients of different ages and genders(P＞0.05).The multivariate logistic regression analysis showed that the severe disease activity and elevated SALL4 mRNA,OLFM4 mRNA and Activin-A levels were risk factors for joint deformities in RA(P＜0.05).The cut-off values of Activin-A,SALL4 mRNA,and OLFM4 mRNA for predicting joint deformities in RA were 15.06 pg·L-1,3.412,and 3.802,respectively,and the areas under the curves were 0.699,0.693,and 0.756,respectively.The area under the curve for the predication of joint deformities in RA based on the combination of SALL4 mRNA,OLFM4 mRNA,and Activin-A was 0.892,which significantly higher than the prediction by the said indexes alone(Z=4.171,2.785,3.626,P＜0.05).Conclusion The increased levels of serum SALL4 mRNA,OLFM4 mRNA and Activin-A in RA patients are associated with RA disease activity,number of affected joints,duration of synovitis,and joint deformities.The combined detection of SALL4 mRNA,OLFM4 mRNA and Activin-A for predicting joint deformities in RA is more effective than the individual detection of the three.

With the rapid development of artificial intelligence technology, its applications in medical imaging have become increasingly extensive. This review aimed to analyze the current development status and future direction of intelligent imaging technology by investigating its application in various medical departments. To achieve this, we conducted a comprehensive search of various data sources up to 2024, including PubMed, Web of Science, and Google Scholar, based on the principle of comprehensive search. A total of 332 articles were screened, and after applying the inclusion and exclusion criteria, 56 articles were selected for this study. According to the findings, intelligent imaging technology exhibits robust image recognition capabilities, making it applicable across diverse medical imaging modalities within hospital departments. This technology offers an efficient solution for the analysis of various medical images by extracting and accurately identifying complex features. Consequently, it significantly aids in the detection and diagnosis of clinical diseases. Its high accuracy, sensitivity, and specificity render it an indispensable tool in clinical diagnostics and related tasks, thereby enhancing the overall quality of healthcare services. The application of intelligent imaging technology in healthcare significantly enhances the efficiency of clinical diagnostics, resulting in more accurate and timely patient assessments. This advanced technology offers a faster and more precise diagnostic approach, ultimately improving patient care and outcomes. This review analyzed the socioeconomic changes brought about by intelligent imaging technology to provide a more comprehensive evaluation. Also, we systematically analyzed the current shortcomings of intelligent imaging technology and its future development directions, to enable future research.
Humans ; Artificial Intelligence ; Diagnostic Imaging/methods* ; Hospitals

Objective:To investigate the correlation between serum thyroglobulin antibody (TG-Ab) and thyroid peroxidase antibody (TPO-Ab) cconcentrations and arteriosclerosis development in middle-aged and older adult patients with depression.Methods:A total of 200 middle-aged and older adult patients with depression who received treatment in the Third People's Hospital of Huzhou from January 2018 to October 2019 were included in this study. They were divided into four groups ( n = 50/group) according to TG-Ab and TPO-Ab test results: TG-Ab-positive (group 1), TPO-Ab-positive (group 2), TG-Ab-positive and TPO-Ab-positive (group 3), TG-Ab-negative and TPO-Ab-negative (control group). Serum thyroid hormone level, ankle-brachial pressure index (ABI), brachial-ankle pulse wave velocity, and the incidences of intima-media thickening and plaque formation in the lower extremity arteries were compared between groups. Results:Total thyroxine concentration in the control group, groups 1, 2 and 3 was (89.96 ± 2.45) nmol/L, (101.29 ± 3.35) nmol/L, (90.09 ± 2.70) nmol/L, (97.55 ± 2.57) nmol/L, respectively. There was a significant difference in total thyroxine concentration between groups ( F = 3.85, P < 0.05). Brachial-ankle pulse wave velocity in the control group, groups 1, 2, and 3 was (1 327.55 ± 67.78) cm/s, (1 510.36 ± 83.05) cm/s, (1 422.71 ± 71.40) cm/s, (1 533.95 ± 87.01) cm/s, respectively. There was a significant difference in brachial-ankle pulse wave velocity between groups ( F = 65.12, P < 0.05). The incidence of intima-media thickening in the control group, groups 1, 2, and 3 was 18% (9/50), 50% (25/50), 32% (16/50), 60% (30/50), respectively. The incidence of plaque formation in the control group, groups 1, 2, and 3 was 22% (11/50), 56% (28/50), 40% (20/50), 70% (35/50), respectively. There were significant differences in intima-media thickening and plaque formation between groups ( χ2 = 21.83, 25.77, all P < 0.001). Logistic multivariate regression analysis showed that age ( OR = 0.953) and TG-Ab ( OR = 1.116) were independent risk factors for developing arteriosclerosis in middle-aged and older adult patients with depression ( P < 0.05). Conclusion:TG-Ab-positive results are an independent risk factor for developing arteriosclerosis in middle-aged and older adult patients with depression. TPO-Ab-positive results have a synergistic effect on the occurrence and development of arteriosclerosis in middle-aged and older adult patients with depression. Monitoring serum TG-Ab and TPO-Ab concentrations is of great clinical significance for the prevention and treatment of arteriosclerosis in middle-aged and older adult patients with depression.

Objective:To explore the diagnosis, surgical methods and therapeutic effect of primary duodenal malignant tumor.Methods:The clinical data of 116 patients with primary duodenal malignant tumor from January 2010 to December 2018 were retrospectively analyzed.Results:Among 116 patients, adenocarcinoma was in 74 cases, interstitial tumor was in 25 cases, carcinoid was in 9 cases, the others was in 8 cases. Before operation, duodenoscopy was performed in 107 cases, and CT examination was performed in 76 cases. There were 57 cases of pancreaticoduodenectomy, 15 cases of duodenal segmental resection, 13 cases of subtotal gastrectomy and duodenal bulbar resection, 13 cases of duodenal partial resection, and 18 cases of palliative short circuit operation. The total incidence of postoperative complication was 31.9% (37/116), including pancreatic fistula in 8 cases (grade B 5 cases, grade C 3 cases), biliary fistula in 6 cases, abdominal infection in 5 cases, pulmonary infection in 4 cases, intestinal fistula in 3 cases, delayed gastric emptying in 3 cases, and hemorrhage in 8 cases. Four cases (3.4%) died during the perioperative period. Single factor Cox regression analysis result showed that the postoperative survival time was related to the tumor differentiation degree, operation method, tumor infiltration degree and lymphatic metastasis ( P<0.05 or <0.01); multi-factor Cox regression analysis results showed that the operation method, tumor infiltration degree and lymphatic metastasis were the independent risk factors for the postoperative survival time of patients with primary duodenal malignant tumor ( P<0.05). The patients were followed up until June 2021, and 9 cases were lost to follow-up. Kaplan-Meier survival curve analysis result showed that the postoperative overall 1-,3- and 5-year survival rates were 82.11%, 57.56% and 33.11%, respectively. Conclusions:Adenocarcinoma is the main primary malignant tumor of duodenum. Duodenoscopy and CT are the main examination methods. Radical resection is the most effective treatment for primary duodenal malignant tumor, and pancreaticoduodenectomy is the first choice. Surgical method, tumor infiltration degree and lymphatic metastasis are the independent risk factors affecting the prognosis of patients.

Objective: To explore the evaluations and recipient selection methods of extended criteria donor (ECD) kidney donation in the death of citizens and analyze the transplantation outcomes. Methods: From January to September 2019, the clinical data of donor-recipients were retrospectively studied. The recipients of ECD donor kidneys not evaluated for kidney zero puncture assessment from January 2014 to July 2016 were group A1 and those receiving standard donor kidney (SCD) belonged to group A2. From August 2016 to March 2019, all DCD donors were routinely evaluated for kidney zero puncture and those receiving ECD recipients fell into Group B1 and those receiving SCD belonged to Group B2. Analysis was performed for ECD/SCD donor renal zero puncture pathological features and lesion degree and utilization of ECD donor kidney; donor-recipient body surface area (BSA) ratio and lesion degree of ECD donor kidney on recipient selecting and matching. Serum creatinine value, perioperative adverse events and 1-year follow-up of human/kidney survival rate in each group were compared at 1 day, 1 week, 1 month, 3 months, 6 months and 1 year. Results: A total of 108, 264, 306 and 416 recipients were recruited into A1, A2, B1 and B2 groups respectively. The ECD donor renal utilization rate was 88.5% vs 93.3% during two time periods. According to the 2016 Banff standard, glomerular sclerosis (GS), renal interstitial fibrosis (Ci) and intimal fibrosis thickening (Cv), small arterial intimal hyalinization (ah), tubular atrophy (ct) and acute tubular injury (ati) accounted for more than B1 group than B2 group (P<0.05). The severity of ECD donor kidney disease, BSA ratio <1.1 group and ≥1.1 group 1 week, 1 month, 3 months postoperative blood creatinine value was lower than the former while declining amplitude of blood creatinine was higher. A significant difference existed in the degree of moderate lesions in donor kidney (P<0.05). After 1 year, serum creatinine value of B1 group was lower than that of A1 group (P<0.05). Conclusions The quality of ECD donor kidney is obviously inferior to that of SCD donor kidney. The Banff donor kidney criterion is an effective mode of evaluating the quality of ECD donor kidney. Based upon the extent of Banff's nephropathy, the ratio of donor/recipient BSA is an important selecting method for ECD donors to receive kidneys and recipients, ultimately improving graft utilization and recipient transplantation.

Objective To explore the long-term clinical effect of kidney transplantation in children.Methods The clinical data of 53 children with kidney transplantation from March 2008 to September 2014 were retrospectively analyzed.The influence of the dependent factors on the estimated glomerular filtration rate (eGFR) (greater than 90 mL/min/1.73 m2 or ＜90 mL/min/1.73 m2) was estimated in the three years after the operation,and the influencing factors were analyzed by the dual logistic regression equation.Results There were 19 cases of living donors,17 cases of organ donors after death,and 6 others.The 53 patients were followed up for 3-9 years.The level of blood creatinine was decreased from the preoperative (820.1 ± 323.1) μmol/L to (51.6 ± 24.9) μmol/L 3 years after the operation (P＜0.05).eGFR was increased to (103.5 ± 11.4) mL/min/1.73 m2at 3rd year after the operation from the preoperative (17.1 ± 7.8) mL/min/1.73 m2 (P＜0.05).The age of recipients,preoperative dialysis time,number of HLA mismatching and postoperative delayed graft function healing (DGF),rejection and infection were the influencing factors of eGFR at 3rd year postoperation (P＜0.05).The multi-factor binary logistic regression equation analysis showed that only rejection was the risk factor for eGFR at 3rd year p0ostoperation.Eight cases of DGF (8/53,15.1％) recovered rapidly.There were 6 cases of acute rejection (6/47,12.8 ％) and 1 case of chronic rejection (1/47,2.1％).There were 9 cases of infection (9/47,19.1％).There were 6 cases of recurrence after surgery.The 3-year recipient and kidney survival rate was 94.3％ (50/53) and 88.7％ (47/53) respectively.The average height of the patients in the first,second and third year after the surgery was increased by (4.6 ± 1.9) cm (0.5-19.1 cm),(3.7 ± 1.8) cm (0.7-14.3 cm) and (2.8± 1.2) cm (0.3-8.7 cm) respectively.Conclusion The long-term effect of children kidney transplantation is satisfactory.