Objective:To evaluate the predictive performance of machine learning methods for predicting the risk of death in traumatic hemorrhage, and address the low prediction accuracy of traditional trauma scores, provide a reference for developing a more robust prediction method for severe trauma patients.Methods:Clinical data of severe trauma patients from the National Trauma Medical Center between April 1, 2023, and March 31, 2024 were collected. ElasticNet, Recursive Feature Elimination, and Mutual Information-based feature selection methods were used to screen variables and compared with traditional hypothesis testing methods. Built the prediction models for mortality risk in traumatic hemorrhage using Logistic Regression, ElasticNet, and Support Vector Machine (SVM) and compared the predictive performance.Results:The study included 5,601 trauma patients, the results of the variable screening and importance ranking were consistent with three feature selection methods. The classification accuracy and AUC values for the three models were as follows: Overall accuracy was 83.2%, survival accuracy was 84.0%, death accuracy was 76.3%, and an AUC was 0.86 in logistic regression; Overall accuracy was 78.9%, survival accuracy was 78.5%, death accuracy was 81.7%, and an AUC was 0.88 in ElasticNet; Overall accuracy was 84.7%, survival accuracy was 86.1%, death accuracy was 72.4%, and an AUC was 0.86 in SVM. The prediction performance of three models is quite little.Conclusion:Machine learning methods can effectively improve the prediction of death risk for traumatic hemorrhage,and has wide applications.

Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective:To explore the correlation between long non-coding RNA LOC101927476 (LncRNA LOC101927476), stage-specific embryonic antigen-4 (SSEA-4), and intronic microRNA-28 (hsa-miR-28) and postoperative recurrence/metastasis of ovarian cancer.Methods:A total of 195 patients with ovarian cancer who underwent surgical treatment in The First People’s Hospital of Shangqiu and The First Affiliated Hospital of Zhengzhou University from Jan. 2021 to Oct. 2022 were selected. Patients were divided into occurrence group and non-occurrence group according to whether they had recurrence/metastasis within 2 years after surgery. R package "Match It" and the 1∶1 principle for propensity score matching (PSM) were used to compared the expression of LncRNA LOC101927476, SSEA-4 mRNA, and hsa-miR-28 in different tissues and two groups. Multivariate logistic regression analysis was used to analyze the correlation between various detection indicators in cancer tissues and postoperative recurrence/metastasis of ovarian cancer. The value of LncRNA LOC101927476, SSEA-4 mRNA, hsa-miR-28, and their combined use in predicting recurrence/metastasis in cancer tissues was analyzed using the receiver operating characteristic (ROC) curve. The external calibration curve was used to analyze the combined predicts of the consistency between the incidence of recurrence/metastasis and the actual incidence.Results:In cancer tissues, the expression of LncRNA LOC101927476 and hsa-miR-28 was lower than that in adjacent tissues, while the expression of SSEA-4 mRNA was higher ( P<0.05). The expression of LncRNA LOC101927476 and hsa-miR-28 in the occurrence group was lower than that in the non-occurrence group, while the expression of SSEA-4 mRNA was higher than that in the non-occurrence group ( P<0.05). Multivariate logistic regression analysis showed that the increase of LncRNA LOC101927476, SSEA-4 mRNA, and hsa-miR-28 were independent factors associated with the recurrence/metastasis of ovarian cancer after surgery ( P<0.05). ROC analysis showed that the AUCs of LncRNA LOC101927476, SSEA-4 mRNA, hsa-miR-28, and their combined prediction of ovarian cancer recurrence/metastasis after surgery were 0.730, 0.767, 0.832, and 0.915, respectively ( P<0.001). Comparing the AUC of the combination with that of the individual, it was found that the AUC of the combination was significantly higher than that of LncRNA LOC101927476, SSEA-4 mRNA, and hsa-miR-28 ( Z=3.924, 2.995, 2.078, P=0.000, 0.003, 0.038). The calibration curve of the external dataset showed that the combined prediction of the incidence of recurrence/metastasis was basically consistent with the actual incidence, and the two curves had a high degree of fit. Conclusions:The expression of LncRNA LOC101927476, SSEA-4, and hsa-miR-28 in cancer tissues is associated with postoperative recurrence/metastasis of ovarian cancer, which can provide a reference for early clinical prediction of recurrence/metastasis. The combined application of the three can further improve the predictive value, help to early warn the risk of recurrence/metastasis, and provide important reference information for clinical personalized prevention intervention.

OBJECTIVE: To assess the value of the Prostate Imaging Reporting and Data System version 2.1 (PI-RADS v2.1) score combined with PSA density (PSAD) in the diagnosis of clinically significant prostate cancer (CSPCa) in the PSA grey zone by MRI-TRUS cognitive fusion-guided transperineal targeted prostate biopsy. METHODS: This retrospective study included 327 male patients with total PSA (tPSA) levels of 4-10 μg/L undergoing MRI-TRUS cognitive fusion-guided transperineal targeted prostate biopsy in our hospital between January 2021 and December 2023. According to the pathological results, we divided the patients into a CSPCa (n = 44) and a non-CSPCa group (n = 283), collected their clinical and imaging data, and subjected them to statistical analysis. RESULTS: The age, tPSA level, PSAD and PI-RADS score were significantly higher, while the free PSA (fPSA) level, f/tPSA ratio and prostate volume remarkably lower in the CSPCa than in the non-CSPCa group (P<0.05). The areas under the curve (AUCs) of PSAD, PI-RADS score and their combination were 0.772, 0.730 and 0.801, with sensitivities of 63.63%, 70.45% and 72.73%, and specificities of 84.10%, 75.62% and 83.75%, respectively (P<0.01). With PSAD 0.2 μg/(ml·cm3) as the best cut-off value and based on the PI-RADS scores, the patients were divided into two groups for analysis. In the patients with PI-RADS scores 2 and 5, the AUCs were 0.534 and 0.643, with sensitivities of 16.67% and 63.64%, and specificities of 85.14% and 64.29%, with no statistically significant differences (P= 0.784, P= 0.228), and in those with PI-RADS scores 3 and 4, the AUCs were 0.794 and 0.843, with sensitivities of 57.14% and 80.00%, and specificities of 87.14% and 81.82%, with statistically significant differences (P= 0.009, P<0.001). CONCLUSION PI-RADS v2.1 score combined with PSAD can effectively improve the diagnostic efficiency of CSPCa in the PSA grey zone by MRI-TRUS cognitive fusion-guided transperineal targeted prostate biopsy and serve as a guide for selection of prostate biopsy.
Humans ; Male ; Prostatic Neoplasms/diagnostic imaging* ; Retrospective Studies ; Prostate-Specific Antigen ; Magnetic Resonance Imaging ; Image-Guided Biopsy ; Prostate/pathology* ; Aged ; Middle Aged

[This corrects the article DOI: 10.1016/j.apsb.2022.05.019.].

Delirium is a common cause and complication of hospitalization in the elderly and is associated with higher risk of future dementia and progression of existing dementia, of which 70% is Alzheimer's disease (AD). AD and delirium, which are known to be aggravated by one another, represent significant societal challenges, especially in light of the absence of effective treatments. The intricate biological mechanisms have led to numerous clinical trial setbacks and likely contribute to the limited efficacy of existing therapeutics. Artificial intelligence (AI) presents a promising avenue for overcoming these hurdles by deploying algorithms to uncover hidden patterns across diverse data types. This review explores the pivotal role of AI in revolutionizing drug discovery for AD and delirium from target identification to the development of small molecule and protein-based therapies. Recent advances in deep learning, particularly in accurate protein structure prediction, are facilitating novel approaches to drug design and expediting the discovery pipeline for biological and small molecule therapeutics. This review concludes with an appraisal of current achievements and limitations, and touches on prospects for the use of AI in advancing drug discovery in AD and delirium, emphasizing its transformative potential in addressing these two and possibly other neurodegenerative conditions.

Objective To clarify the occurrence,location distribution,and risk factors of microperforations in surgical gloves used in dermatovenereology surgeries.Methods A total of 898 sterilized surgical gloves worn by right-handed medical staff during dermatovenereology surgeries in Suqian Hospital of Jiangsu Province Hospital from May 2022 to April 2024 were selected as the research objects.The occurrence and location distribution of microperforations in all sterilized surgical gloves after surgery were collected.Univariate analysis and binary Logistic regression analysis were conducted on the factors that might lead to the occurrence of microperforations.Results Among the 898 gloves selected in this study,61 gloves(6.79%)had microperforations;the incidence of microperforations in the gloves worn on the left hand was significantly higher than that in the gloves worn on the right hand(P<0.05);microperforations were prone to occur on the palmar surfaces of the index finger and thumb of the gloves.The results of univariate and binary Logistic regression analyses showed that the use of special instruments,surgery duration≥60 minutes,ingrown nails surgery,and worn by the chief surgeon were the risk factors for the occur-rence of microperforations in sterilized surgical gloves(OR>1,P<0.05),while wearing double-layer gloves was the protective factor to avoid the occurrence of microperforations(OR<1,P<0.05).Conclusion The sterilized surgical gloves are more likely to occur microperforations if involved special instruments in surgery,surgery duration≥60 minutes,and ingrown nails surgery,and worn by the chief surgeon,while wearing double-layer gloves can reduce the incidence of microperforations.

Objective:To evaluate the value of ultrasound radiomics combined with machine learning for early diagnosis of seronegative Hashimoto’s thyroiditis (SN-HT) .Methods:This retrospective study included 164 patients from Liaoning Provincial People’s Hospital , Lixin County People’s Hospital, Linghai Dalinghe Hospital, Fengcheng Phoenix Hospital, who underwent thyroidectomy for solitary nodules with normal thyroid function between Nov. 2016 and Jan. 2024. Postoperative pathology confirmed Hashimoto’s thyroiditis (HT) in some cases, who were further categorized into antibody-positive and antibody-negative groups based on serum antibody status. Patients without Hashimoto’s thyroiditis served as the control group. A total of 298 ultrasound images were analyzed. Radiomics features were extracted from hypoechoic non-nodular areas within 0.5 cm surrounding the tumor. Two senior pathologists and two senior ultrasound physicians independently assessed lymphocytic infiltration, eosinophilic changes of follicular epithelium, and the proportion of hypoechoic areas in pathology and ultrasound images, respectively. A machine learning model, CCH-NET, was developed using linear regression and t-distributed stochastic neighbor embedding (t-SNE) techniques. The dataset was divided into a training set (80%) and a validation set (20%) to compare the diagnostic accuracy of CCH-NET with that of senior ultrasound physicians. Results:In internal validation, CCH-NET achieved a diagnostic accuracy of 88.89% for both antibody-positive and antibody-negative groups, significantly higher than the 66.67% accuracy of senior ultrasound physicians ( P<0.01). In external validation, CCH-NET achieved 75.00% and 66.67% accuracy for the two groups, compared to 50.00% by senior ultrasound physicians. For the control group, both methods achieved 93.33% accuracy. The AUC of CCH-NET was 0.848, outperforming senior ultrasound physicians (0.681) ,demonstrating superior diagnostic performance. Conclusion:The radiomics-based CCH-NET model, using non-nodular hypoechoic areas as a specific indicator, can accurately identify early SN-HT in euthyroid patients. It significantly outperforms senior ultrasound physicians, improving diagnostic accuracy and reducing missed diagnoses.

Objective:To explore the correlation between long non-coding RNA LOC101927476 (LncRNA LOC101927476), stage-specific embryonic antigen-4 (SSEA-4), and intronic microRNA-28 (hsa-miR-28) and postoperative recurrence/metastasis of ovarian cancer.Methods:A total of 195 patients with ovarian cancer who underwent surgical treatment in The First People’s Hospital of Shangqiu and The First Affiliated Hospital of Zhengzhou University from Jan. 2021 to Oct. 2022 were selected. Patients were divided into occurrence group and non-occurrence group according to whether they had recurrence/metastasis within 2 years after surgery. R package "Match It" and the 1∶1 principle for propensity score matching (PSM) were used to compared the expression of LncRNA LOC101927476, SSEA-4 mRNA, and hsa-miR-28 in different tissues and two groups. Multivariate logistic regression analysis was used to analyze the correlation between various detection indicators in cancer tissues and postoperative recurrence/metastasis of ovarian cancer. The value of LncRNA LOC101927476, SSEA-4 mRNA, hsa-miR-28, and their combined use in predicting recurrence/metastasis in cancer tissues was analyzed using the receiver operating characteristic (ROC) curve. The external calibration curve was used to analyze the combined predicts of the consistency between the incidence of recurrence/metastasis and the actual incidence.Results:In cancer tissues, the expression of LncRNA LOC101927476 and hsa-miR-28 was lower than that in adjacent tissues, while the expression of SSEA-4 mRNA was higher ( P<0.05). The expression of LncRNA LOC101927476 and hsa-miR-28 in the occurrence group was lower than that in the non-occurrence group, while the expression of SSEA-4 mRNA was higher than that in the non-occurrence group ( P<0.05). Multivariate logistic regression analysis showed that the increase of LncRNA LOC101927476, SSEA-4 mRNA, and hsa-miR-28 were independent factors associated with the recurrence/metastasis of ovarian cancer after surgery ( P<0.05). ROC analysis showed that the AUCs of LncRNA LOC101927476, SSEA-4 mRNA, hsa-miR-28, and their combined prediction of ovarian cancer recurrence/metastasis after surgery were 0.730, 0.767, 0.832, and 0.915, respectively ( P<0.001). Comparing the AUC of the combination with that of the individual, it was found that the AUC of the combination was significantly higher than that of LncRNA LOC101927476, SSEA-4 mRNA, and hsa-miR-28 ( Z=3.924, 2.995, 2.078, P=0.000, 0.003, 0.038). The calibration curve of the external dataset showed that the combined prediction of the incidence of recurrence/metastasis was basically consistent with the actual incidence, and the two curves had a high degree of fit. Conclusions:The expression of LncRNA LOC101927476, SSEA-4, and hsa-miR-28 in cancer tissues is associated with postoperative recurrence/metastasis of ovarian cancer, which can provide a reference for early clinical prediction of recurrence/metastasis. The combined application of the three can further improve the predictive value, help to early warn the risk of recurrence/metastasis, and provide important reference information for clinical personalized prevention intervention.

The etiology of nervous system diseases is complicated, posing significant harm to patients and often resulting in poor prognoses. In recent years, the role of dopaminergic system in nervous system diseases has attracted much attention, and its complex regulatory mechanism and therapeutic potential have been gradually revealed. This paper reviews the role of dopaminergic neurons, the neurotransmitter dopamine, dopamine receptors and dopamine transporters in neurological diseases (including Alzheimer's disease, Parkinson's disease and schizophrenia), with a view to further elucidating the disease mechanism and providing new insights and strategies for the treatment of neurological diseases.
Humans ; Dopamine/metabolism* ; Nervous System Diseases/physiopathology* ; Parkinson Disease/physiopathology* ; Receptors, Dopamine/metabolism* ; Dopaminergic Neurons/physiology* ; Dopamine Plasma Membrane Transport Proteins/metabolism* ; Alzheimer Disease/physiopathology* ; Schizophrenia/physiopathology* ; Animals