BACKGROUND: Lung cancer is one of the most common malignant tumors worldwide and a major cause of cancer-related deaths. Early-stage lung cancer is often manifested as pulmonary nodules, and accurate assessment of the malignancy risk is crucial for prolonging survival and avoiding overtreatment. This study aims to construct a model based on image feature parameters automatically extracted by artificial intelligence (AI) to evaluate its effectiveness in predicting the malignancy of part-solid nodule (PSN). METHODS: This retrospective study analyzed 229 PSN from 222 patients who underwent pulmonary nodule resection at Lanzhou University Second Hospital between October 2020 and February 2025. According to pathological results, 45 cases of benign lesions and precursor glandular lesion were categorized into the non-malignant group, and 184 cases of pulmonary malignancies were categorized into the malignant group. All patients underwent preoperative chest computed tomography (CT), and AI software was used to extract imaging feature parameters. Univariate analysis was used to screen significant variables; variance inflation factor (VIF) was calculated to exclude highly collinear variables, and LASSO regression was further applied to identify key features. Multivariate Logistic regression was used to determine independent risk factors. Based on the selected variables, five models were constructed: Logistic regression, random forest, XGBoost, LightGBM, and support vector machine (SVM). Receiver operating characteristic (ROC) curves were used to assess the performance of the models. RESULTS: The independent risk factors for the malignancy of PSN include roughness (ngtdm), dependence variance (gldm), and short run low gray-level emphasis (glrlm). Logistic regression achieved area under the curves ( AUCs) of 0.86 and 0.89 in the training and testing sets, respectively, showing good performance. XGBoost had AUCs of 0.78 and 0.77, respectively, demonstrating relatively balanced performance, but with lower accuracy. SVM showed an AUC of 0.93 in the training set, which decreased to 0.80 in the testing set, indicating overfitting. LightGBM performed excellently in the training set with an AUC of 0.94, but its performance declined in the testing set, with an AUC of 0.88. In contrast, random forest demonstrated stable performance in both the training and testing sets, with AUCs of 0.89 and 0.91, respectively, exhibiting high stability and excellent generalizability. CONCLUSIONS The random forest model constructed based on independent risk factors demonstrated the best performance in predicting the malignancy of PSN and could provide effective auxiliary predictions for clinicians, supporting individualized treatment decisions.
.
Humans ; Male ; Female ; Lung Neoplasms/pathology* ; Middle Aged ; Retrospective Studies ; Artificial Intelligence ; Aged ; Tomography, X-Ray Computed ; Adult ; Solitary Pulmonary Nodule/diagnostic imaging* ; ROC Curve

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

Background A diverse cohort of patients and susceptible individuals congregate in healthcare facilities, where exposure to pathogenic microorganisms associated with respiratory infectious diseases constitutes a significant risk factor for cross-infection. Central air-conditioning ventilation systems improve some indoor environment indicators while exacerbating the risk of transmission of respiratory infectious diseases. Objective To investigate the distribution characteristics of microbial communities in the central air-conditioning ventilation systems of hospitals, providing a scientific basis for the selection of microbial indicators in hygiene standards for hospital central air-conditioning ventilation systems and for hospital risk early warning systems. Methods In October 2023, two central air-conditioning ventilation systems were selected from a Grade 3A hospital in Shanghai: one was an all-air air-conditioning system serving the waiting area on the ground floor, and the other was a fan coil plus fresh air system serving the outpatient area on the third floor. Samples from four different components of the ventilation systems—air outlets, filters, surface coolers, and condensate trays—were collected for high-throughput sequencing of the 16S rRNA gene to analyze bacterial communities. Alpha-diversity and beta-diversity analyses were performed to investigate the microbial community composition and diversity characteristics of the hospital central air-conditioning ventilation systems. Functional analysis was conducted to determine the relative abundance of bacterial functions in these systems.Results A total of 528 operational taxonomic units (OTUs) were identified, encompassing 20 bacterial phyla, 37 classes, 79 orders, 123 families, and 240 genera. The analysis revealed that the bacterial community was predominantly composed of Proteobacteria, Gemmatimonadates, Bacteroidetes, and Actinobacteria. The diversity analysis indicated that bacterial community richness and diversity were highest in the condensate trays, while no statistically significant differences (P > 0.05) were observed in the bacterial community composition among the air outlets, filters, and surface coolers. The functional analysis showed that the bacterial communities in the central air-conditioning ventilation systems primarily exhibited chemoheterotrophic, oxidative energy-dependent heterotrophic, and ureolytic functional characteristics. Conclusion The dominance of Proteobacteria suggests that this phylum exhibits strong adaptability in the central air-conditioning ventilation systems, possibly related to its ability to survive and reproduce under varying environmental conditions. The diversity analysis indicates that the condensate tray is a critical area for bacterial proliferation in the central air-conditioning ventilation systems. The similarity in environmental conditions among the air outlets, filters, and surface coolers result in similar bacterial community structures. The functional analysis reveals that the bacterial communities possess robust energy conversion and metabolic capabilities, potentially contributing to processes such as organic matter decomposition and nitrogen cycling within the central air-conditioning ventilation systems.

Objective To evaluate the predictive ability and clinical application value of artificial intelligence (AI) systems in the benign and malignant differentiation and pathological type of pulmonary nodules, and to summarize clinical application experience. Methods A retrospective analysis was conducted on the clinical data of patients with pulmonary nodules admitted to the Department of Thoracic Surgery, Second Hospital of Lanzhou University, from February 2016 to February 2025. Firstly, pulmonary nodules were divided into benign and non-benign groups, and the discriminative abilities of AI systems and clinicians were compared. Subsequently, lung nodules reported as precursor glandular lesions (PGL), microinvasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) in postoperative pathological results were analyzed, comparing the efficacy of AI systems and clinicians in predicting the pathological type of pulmonary nodules. Results In the analysis of benign/non-benign pulmonary nodules, clinical data from a total of 638 patients with pulmonary nodules were included, of which there were 257 males (10 patients and 1 patient of double and triple primary lesions, respectively) and 381 females (18 patients and 1 patient of double and triple primary lesions, respectively), with a median age of 55.0 (47.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis of the two groups of variables showed that, except for nodule location, the differences in the remaining variables were statistically significant (P<0.05). Multivariate logistic regression analysis showed that age, nodule type (subsolid pulmonary nodule), average density, spicule sign, and vascular convergence sign were independent influencing factors for non-benign pulmonary nodules, among which age, nodule type (subsolid pulmonary nodule), spicule sign, and vascular convergence sign were positively correlated with non-benign pulmonary nodules, while average density was negatively correlated with the occurrence of non-benign pulmonary nodules. The area under the receiver operating characteristic curve (AUC) of the malignancy risk value given by the AI system in predicting non-benign pulmonary nodules was 0.811, slightly lower than the 0.898 predicted by clinicians. In the PGL/MIA/IAC analysis, clinical data from a total of 411 patients with pulmonary nodules were included, of which there were 149 males (8 patients of double primary lesions) and 262 females (17 patients of double primary lesions), with a median age of 56.0 (50.0, 61.0) years. Different lesions in the same patient were analyzed as independent samples. Univariate analysis results showed that, except for gender, nodule location, and vascular convergence sign, the differences in the remaining variables among the three groups of PGL, MIA, and IAC patients were statistically significant (P<0.05). Multinomial multivariate logistic regression analysis showed that the differences between the parameters in the PGL group and the MIA group were not statistically significant (P>0.05), and the maximum diameter and average density of the nodules were statistically different between the PGL and IAC groups (P<0.05), and were positively correlated with the occurrence of IAC as independent risk factors. The average AUC value, accuracy, recall rate, and F1 score of the AI system in predicting lung nodule pathological type were 0.807, 74.3%, 73.2%, and 68.5%, respectively, all better than the clinical physicians’ prediction of lung nodule pathological type indicators (0.782, 70.9%, 66.2%, and 63.7% respectively). The AUC value of the AI system in predicting IAC was 0.853, and the sensitivity, specificity, and optimal cutoff value were 0.643, 0.943, and 50.0%, respectively. Conclusion This AI system has demonstrated high clinical value in predicting the benign and malignant nature and pathological type of lung nodules, especially in predicting lung nodule pathological type, its ability has surpassed that of clinical physicians. With the optimization of algorithms and the adequate integration of multimodal data, it can better assist clinical physicians in formulating individualized diagnostic and treatment plans for patients with lung nodules.

[This corrects the article DOI: 10.1016/j.jpha.2023.08.006.].

Background Perfluorinated and polyfluoroalkyl substances (PFAS), a large group of emerging pollutants, are ubiquitous in the ecological environment. Their multiple organ toxic effects on human body are reported. Understanding the exposure level of PFAS in cord serum and associated influencing factors can provide scientific evidence for studying maternal and newborn health effects and risk regulation. Objective To explore the exposure levels of PFAS in cord serum and potential impact factors. Methods This study was based on the maternal and infant database and the cord serum sample bank of the Sheyang Mini Birth Cohort Study (SMBCS) established in 2009. A self-designed questionnaire was used to collect information on sociodemographic characteristics, living environment, and lifestyle of mothers during pregnancy. A total of 1097 cord serum samples were measured utilizing ultra-high performance liquid chromatography-Q-Exactive Orbitrap high-resolution mass spectrometry. Multiple linear regression models were used to identify influencing factors related to PFAS exposure level in cord serum. Results A total of 38 types of PFAS were detected in the cord serum samples, including 20 perfluorocarboxylic acids (PFCA), 14 perfluorosulfonic acids (PFSA), and 4 other types of PFAS. The detection rates of 14 PFAS compounds were above 50%. The detection rates of perfluoro-1-hexanesulfonic acid (PFHxS), perfluoro-1-octanesulfonic acid (PFOS), perfluorononanoic acid (PFNA), perfluorooctanoic acid (PFOA), perfluorodecanoic acid (PFDA), and perfluoroundecanoic acid (PFUdA) were in the range of 99.18%-100.00%. The median concentrations of PFOA and 6∶2 chlorinated polyfluorinated ether sulfonic acid (6∶2CI-PFESA) were higher than those of the other compounds, which were 3.76 µg·L⁻¹ and 2.61 µg·L⁻¹, respectively. The correlation coefficients among cord serum PFAS were in the wide range of 0.0911-0.8429 (P < 0.05). The associations between PFHxS and perfluoro-1-heptanesulfonic acid (PFHpS) (r=0.8429, P < 0.05), PFOS and PFHpS (r=0.7012, P < 0.05), and PFUdA and perfluorododecanoic acid (PFDoA) (r=0.7875, P < 0.05) were positive. The proportions of PFCA and PFSA in the cord serum samples were 60.1% and 38.4%, respectively. PFOA and 6∶2 Cl-PFESA were the predominant compounds in the cord serum samples, whose proportions were 37.8% and 19.3%, respectively. The concentrations of specific types of cord serum PFAS had varied associations with the following demographic variables of pregnant women: age, parity, education level, gestational age, and occupation. The multiple linear regression analysis found that the concentrations of 8 PFAS (PFHxS, PFHpS, PFNA, PFOS, PFDA, PFUdA, PFDoA, and 6∶2 CI-PFESA) in umbilical cord serum were lower in pregnant women aged 25 years and older than in those under the age of 25 years; compared to pregnant women with education levels at or below junior middle school, those with education levels at or above high school had lower concentrations of perfluoroheptanoic acid (PFHpA); the concentration of PFHpA in cord serum was negatively correlated with household annual income; multiparous women had higher concentrations of PFNA, PFUdA, and PFDoA than primiparous women; compared to mothers engaged in manual labor, the concentration of perfluoro-1-butanesulfonic acid (PFBS) in umbilical cord serum was lower in mothers engaged in mental labor, while the concentrations of PFBS and PFOA were lower and the concentrations of perfluorotridecanoic acid (PFTrDA) and 8∶2 chlorinated polyfluorinated ether sulfonic acid (8∶2CI-PFESA) were higher in mothers of other occupational types; the concentrations of umbilical cord serum PFOA, PFOS, PFUdA, and PFDoA were positively correlated with the gestational age of pregnant women, while N-methylperfluoro-1-octanesulfonamido acetic acid (N-MeFOSAA) was negatively correlated with the gestational age of pregnant women; PFTrDA was negatively correlated with the birth weight of newborns; compared with those with insufficient gestational weight gain, those with adequate gestational weight gain had lower PFDoA, while those with excess gestational weight gain had higher N-MeFOSAA. Conclusion PFAS compounds exposure is common in the mothers and infants in the study area. PFOA and 6∶2 CI-PFESA are the two main compounds in cord serum. Cord serum PFAS are associated with several demographic characteristics of the pregnant women. Future research needs to pay more attention to PFAS alternatives and other emerging contaminants.

Objective To systematically evaluate the effect and safety of neoadjuvant PD-1/PD-L1 inhibitors combined with chemotherapy for resectable non-small cell lung cancer (NSCLC). Methods The PubMed, EMbase, The Cochrane Library, CNKI, and Wanfang data were searched by computer to identify relevant studies on anti PD-1 /PD-L1 combined with chemotherapy for resectable NSCLC from inception to March 2023. Two authors independently screened the literature, extracted the data, and evaluated the risk of bias in the included studies. The single-arm study was evaluated for quality using the methodological index for non-randomized studies (MINORS). Meta-analysis was conducted by RevMan 5.4 software. Results Twenty-six studies with 965 patients were included in this meta-analysis. MINORS scores of single-arm studies were ≥12 points. The meta-analysis results showed that the pooled pathologic complete response, major pathologic response, and objective response rates as well as partial response, surgical rate and R0 surgical resection rate of neoadjuvant PD-1/PD-L1 inhibitors combined with chemotherapy were 39% [RD=0.39, 95%CI (0.31, 0.47) ], 59% [RD=0.59, 95%CI (0.53, 0.65) ], 72% [RD=0.72, 95%CI (0.65, 0.80) ], 62% [RD=0.62, 95%CI (0.56, 0.69) ], 86% [RD=0.86, 95%CI (0.81, 0.92) ], and 94% [RD=0.94, 95%CI (0.92, 0.97) ], respectively. In terms of safety, the rate of adverse events (AEs) was 65% [RD=0.65, 95%CI (0.52, 0.78) ], and the rate of grade 3 to 5 AEs was 16% [RD=0.16, 95%CI (0.10, 0.23) ]. Conclusion The combination of neoadjuvant PD-1/PD-L1 inhibitors with chemotherapy has good efficacy and safety in the treatment of patients with resectable NSCLC.

A major impedance to neuronal regeneration after peripheral nerve injury(PNI)is the activation of various programmed cell death mechanisms in the dorsal root ganglion.Ferroptosis is a form of pro-grammed cell death distinguished by imbalance in iron and thiol metabolism,leading to lethal lipid peroxidation.However,the molecular mechanisms of ferroptosis in the context of PNI and nerve regeneration remain unclear.Ferroportin(Fpn),the only known mammalian nonheme iron export protein,plays a pivotal part in inhibiting ferroptosis by maintaining intracellular iron homeostasis.Here,we explored in vitro and in vivo the involvement of Fpn in neuronal ferroptosis.We first delineated that reactive oxygen species at the injury site induces neuronal ferroptosis by increasing intracellular iron via accelerated UBA52-driven ubiquitination and degradation of Fpn,and stimulation of lipid peroxidation.Early administration of the potent arterial vasodilator,hydralazine(HYD),decreases the ubiquitination of Fpn after PNI by binding to UBA52,leading to suppression of neuronal cell death and significant ac-celeration of axon regeneration and motor function recovery.HYD targeting of ferroptosis is a promising strategy for clinical management of PNI.

Objective:To analyze the clinical characteristics, imaging, myopathology and outcomes of patients with COVID-19 related autoimmune myopathy.Methods:The clinical features, serum creatine kinase (CK), myositis antibodies, muscle magnetic resonance imaging, myopathology and therapy of 5 patients with COVID-19 related autoimmune myopathy diagnosed in Peking University First Hospital from December 2022 to April 2023 were collected. The effects of the therapy after a short term follow up were analyzed.Results:Among the 5 patients, there were 3 males and 2 females, with onset age of 42-86 years. All patients presented with proximal muscle weakness in the recovery term of COVID-19. Myalgia was noted in 3 cases, dysphagia in 1, skin damage in 2, interstitial lung disease in 1. The serum CK of the 5 patients was 1 663-16 000 IU/L, 1 patient had anti-3-hydroxy-3-methylglutaryl-CoA reductase autoantibodies and 1 patient had anti-signal recognition particle autoantibodies. The electromyography showed myogenic lesions in all patients. Muscle magnetic resonance imaging showed diffuse muscle edema in all patients, myofascial edema in 3 and subcutaneous-tissue edema in 3. The muscle biopsies in 4 patients revealed necrotic myopathy,with high P62 expression in muscle fibers. The electromicroscopy of 2 patients revealed vacuolated mitochondria and intranuclear tubulofilamentous inclusions in muscle fibers. Four patients were treated with glucocorticoids, of whom 2 patients combined with intravenous immunoglobulin, tacrolimus or cyclophosphamide. One case had close monitoring without drug therapy. They showed significant improvement, but the CK was still abnormal in 4 patients.Conclusions:COVID-19 leads to immune mediated myopathy. The manifestation of patients is characterized by proximal predominant weakness and high creatine kinase level. Muscle magnetic resonance imaging shows diffuse muscle edema. The muscle biopsies reveal necrotic myopathy. The effectiveness of immunosuppression needs to be further studied.

Objective:To study positive rates and typing of oligoclonal bands (OCB) in patients with neurological disorders, and to reveal the clinical significance and applicational value of OCB test.Methods:A retrospective analysis was performed on the detection results of 3 217 patients with neurological disorders who undertook both serum and cerebrospinal fluid OCBs in the First Hospital of Peking University from January 2012 to August 2022. According to the final diagnosis, the patients were divided into 13 groups including multiple sclerosis (479 cases), neuromyelitis optica spectrum disorders (935 cases), autoimmune encephalitis (192 cases), viral encephalitis (94 cases), nervous system complication after HSCT (232 cases), Guillain-Barré syndrome (644 cases), chronic inflammatory demyelinating polyneuropathy (157 cases), etc. Cerebrospinal fluid and serum OCBs were detected using isoelectric focusing electrophoresis combining immunofixation, then classified into Ⅰ-Ⅴ types according to the morphology. Consequently, positive rates and types were analyzed for each group. χ2 test was used for comparison between groups. Results:The positive rates of cerebrospinal fluid OCB in multiple sclerosis, nervous system complication after hematopoietic stem cell transplantation (HSCT), autoimmune encephalitis, viral encephalitis, neuromyelitis optica spectrum disorders, Guillain-Barré syndrome and chronic inflammatory demyelinating polyneuropathy were respectively 66.8% (320/479), 48.7% (113/232), 46.4%(89/192), 19.1% (18/94), 17.6% (165/935), 9.9% (64/644), 5.1% (8/157). For patients with multiple sclerosis, neuromyelitis optica spectrum disorders, viral encephalitis, and autoimmune encephalitis, Type Ⅱ bands took the majority of cerebrospinal fluid OCB-positive cases with the rates of 94.1% (301/320), 78.7% (70/89), 77.8% (14/18), and 77.6% (128/165) respectively, indicating intrathecal IgG synthesis; for patients with nervous system complication after HSCT, Guillain-Barré syndrome and chronic inflammatory demyelinating polyneuropathy, type Ⅳ bands took the majority of cerebrospinal fluid OCB-positive cases with the rates of 94.7% (107/113), 82.8% (53/64) and 100% (8/8), indicating no obvious intrathecal IgG synthesis. The positive rates of cerebrospinal fluid oligoclonal bands were significantly different among all groups (χ 2=1 268.31, P<0.001). Conclusion:The positive rates of cerebrospinal fluid oligoclonal bands are different among different neurological disorders, in which the positive rate of cerebrospinal fluid OCB is higher with type Ⅱ bands as the majority type in multiple sclerosis, which indicates that the detection and typing of cerebrospinal fluid OCB are helpful for the diagnosis of various neurological diseases, especially for multiple sclerosis.