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.

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

Background and objective Lung cancer is the cancer with the highest incidence and mortality rates in China,and non-small cell lung cancer(NSCLC)accounts for 80％-85％of all malignant lung tumors.Currently,surgical treat-ment remains the primary treatment modality for lung cancer.In recent years,the effectiveness of immune checkpoint inhibi-tors for NSCLC has become a consensus,and neoadjuvant immunochemotherapy(nICT)has shown promising efficacy and safety in early to intermediate stage NSCLC.However,there are fewer studies related to nICT for locally advanced NSCLC.This study aims to evaluate the efficacy and safety of nICT therapy in locally advanced resectable NSCLC.Methods 85 con-firmed resectable stage ⅢA and ⅢB patients treated in the Department of Thoracic Surgery,Second Hospital of Lanzhou University,from January 2021 to April 2024,were divided into the nICT group(n=32)and the surgery alone group(n=53).Clinical baseline data,perioperative indicators,postoperative complications,imaging response rate,pathological response rate,incidence of adverse events,and quality of life were compared between the two groups.Results There were no statisti-cally significant differences in clinical baseline data between the two groups(P＞0.05).Incidence of choosing thoracotomy was higher in the nICT group than in the surgery alone group(P=0.002).There were no significant differences in surgical time,intraoperative blood loss,number of dissected lymph nodes,duration of chest tube placement,postoperative hospital stay,and R0 resection rate between the two groups(P＞0.05).The overall incidence of postoperative complications was 31.25％in the nICT group and 22.64％in the surgery alone group,with no statistically significant difference(P=0.380).In the nICT group,the objective response rate(ORR)was 84.38％,with 5 cases of complete response(CR)(15.63％),22 cases of partial response(PR)(68.75％),15 cases of pathological response rate(pCR)(46.88％),and 11 cases of major pathological reaponse(MPR)(34.38％).During nICT treatment,12 cases(37.50％)experienced grade 3 treatment-related adverse events,no death induced by adverse events or immune related adverse events.Moreover,the symptoms of the patients were improved after nICT treat-ment.Conclusion Neoadjuvant immunochemotherapy shows promising efficacy in locally advanced resectable NSCLC,with manageable treatment-related adverse events.It is a safe and feasible neoadjuvant treatment modality for locally advanced resectable NSCLC.

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.

Objective:To describe functional disability rate of anxiety disorders in Chinese community adults and explore related risk factors of functional disability.Methods:To conduct in-depth data analysis on China Mental Health Survey(CMHS).The diagnostic tool for anxiety disorders was the Composite International Diagnostic Inter-view-3.0,according to the Diagnostic and Statistical Manual for Mental Disorders,Fourth Edition(DSM-Ⅳ).The World Health Organization Disability Assessment Schedule,2nd edition,was the functional disability assessment standard for anxiety disorders.Weighted 12-month functional disability rate of DSM-Ⅳ anxiety disorder with co-morbidities and only anxiety disorder in population and those in patients,as well as days of partial disability were calculated.The effects of anxiety disorders comorbid other mental disorders and physical diseases and demographic factors on the severity and occurrence of functional disability were analyzed by multiple linear regression and logis-tic regression.Results:The functional disability rate of anxiety disorder with comorbidities in population was 1.7％,and 42.2％in patients,in which constituent rate of grade-four disability was the highest as 84.1％.The functional disability rate of only anxiety disorder in population was 0.3％,and 17.8％in patients.The medians of days of partial disability days in the past 30 days were from 0 to 14.42.Multiple linear regression showed a positive association between comorbid anxiety disorder with other mental disorders and physical diseases(β=0.24),comor-bid other mental disorders and physical diseases(β=0.21),physical diseases(β=0.18),comorbid anxiety disor-der and physical diseases(β=0.15),comorbid anxiety disorder with other mental disorders(β=0.08),other men-tal disorders(β=0.07),only anxiety disorder(β=0.06),lower education level(β=0.12),lower economic status(β=0.08),older age(β=0.06),non-marital status(β=0.06),male(β=0.02)and the severity of functional dis-ability.Logistic regression showed that comorbid anxiety with other mental disorders and physical diseases(OR=64.07),comorbid anxiety disorders with other mental disorders(OR=36.75),comorbid other mental disorders with physical diseases(OR=20.60),comorbid anxiety with physical diseases(OR=18.88),anxiety disorder(OR=9.20),other mental disorders(OR=6.65),physical diseases(OR=4.00),65 years old and over(OR=4.40),50 to 64 years old(OR=2.33),low economic status(OR=2.10),illiterate and below primary school educational level(OR=1.89),middle economic status(OR=1.70),elementary school educational level(OR=1.59),non-marital status(OR=1.47),male(OR=1.16)were the risk factors of the occurrence of functional disability.Conclusion:Comorbidity of anxiety disorders and other mental disorders,and physical diseases increases severity and occurrence of functional disability.Comorbidity,male,gender,older age,lower economic and educa-tional level and non-marital are risk factors of anxiety disorder functional disability.

Objective:To describe disability rates of dementia in community residents aged 65 years and over in China,and explore related risk factors of disability.Methods:This study conducted an in-depth data analysis of the China Mental Health Survey.World Health Organization Disability Assessment Schedule 2.0(WHODAS 2.0)was used to assess dementia disability,Community Screening Interview for Dementia(CSID)and Geriatric Mental Status Examination(GMS)were used for dementia screening and diagnosing.Univariate analysis was used to calcu-late the weighted disability rates of dementia in population and in patients,and their population distribution.Multiple linear regression and logistic regression were used to analyze the risk factors of the occurrence of dementia disability and its severity.Results:The weighted disability rate of dementia was 2.1％in population,and 38.6％in pa-tients.The disability rates of comorbid dementia in population and in patients were higher than those of patients with only dementia.Female,older age,lower education level,lower economic status,and lower cognitive test scores in CSID had higher disability rates of dementia in population.Female and urban resident had higher disability rates of dementia in patients.Multiple linear regression showed economic status(β=0.11),gender(β=0.11),age(β=0.10),and treatment in the last 12 months(β=-0.20)were statistically associated with WHODAS 2.0 scores.Multiple logistic regression showed female(OR=2.81)and treatment in the last 12 months(OR=2.38)were statistically associated with disability.Conclusions:Persons with low economic status,female and elderly peo-ple are the high-risk groups for dementia disability.It should be paid attention to prevent dementia and its conse-quential disabilities.

Objective:To investigate the efficacy and safety of selective dorsal rhizotomy with small incision under electrophysiological monitoring in lower limb spasticity.Methods:Twenty patients with lower limb spasticity due to craniocerebral injury admitted to Department of Neurosurgery,Tianjin Huanhu Hospital from January 2019 to December 2023 were selected. Target muscles (Ashworth Scale graded 1 + or higher) were identified preoperatively. Intraoperatively, the lower L 1 spinous process and the upper L 2 spinous process were resected to expose the cauda equina nerves. A bipolar stimulator was applied to electrically stimulate the cauda equina nerves root by root to identify the sensory nerves of the target muscles; subsequently, strings of electrical stimulation were given, 50% cauda equina nerves were cut off if no contraction of the contralateral muscles was seen, and 75% were cut off if contraction of the contralateral muscles was noted. Motor function and muscle tension were assessed and compared before and 6 months after surgery by Gross Motor Function Measure (GMFM)-66, Gross Motor Function Classification System (GMFCS), and Ashworth spasticity scale. Complications early after surgery and 6 months after surgery were observed. Results:The most common targeted muscles in these 20 patients included the gastrocnemius (the medial and lateral side, n=20), followed by the biceps femoris ( n=12) and the adductor muscles of thigh ( n=9). Number of nerves intraoperatively cut in patients with GMFCS grading 1-4 was 5.40±1.84, 9.50±6.36, 11.67±5.86, and 14.00±5.66, respectively, with significant differences ( F=5.506 , P=0.009). Grading of Ashworth spasticity scale of the target muscles before surgery in these 20 patients showed significant difference compared with that at 6 months after surgery ( P<0.05), and average rank indicated that Ashworth spasticity scale of target muscles 6 months after surgery was graded obviouly better than that before surgery. In addition, the GMFM-66 total scores and major joint motion scores of the patients 6 months after surgery were significantly higher than those before surgery ( P<0.05). Fifteen patients had fever early after surgery, 18 patients had incisional pain, and 1 patient developed reversible hypesthesia of the lower extremities; these symptoms disappeared 0.5-4.0 years after surgery. No patients developed lower limb hypokinesia, urinary and defecation disorders, or spinal deformities. Conclusion:Selective dorsal rhizotomy with small incision under electrophysiological monitoring used in this study can effectively reduce surgical trauma and relieve lower limb spasticity due to craniocerebral injury, enjoying high surgical safety.

{L-End}Objective To investigate the current status of sleep quality and its influencing factors among coal miners in a company in Shanxi Province. {L-End}Methods A total of 1 047 coal miners from a coal mine company in Shanxi Province were selected as the study subjects by convenient sampling method. The occupational stress, occupational burnout and sleep quality of the study subjects were investigated using Occupational Stress Core Scale, Maslach Burnout Inventory-General Survey and Pittsburg Sleep Quality Index Scale. {L-End}Results The detection rates of occupational stress, occupational burnout, sleep disorder were 58.9%, 59.1% and 57.9%, respectively. The result of multivariate logistic regression analysis showed that education level, alcohol consumption, work shift, duration of dust-exposure, phase of respiratory symptoms, self-assessment of health, occupational stress and occupational burnout were independent influencing factors of sleep disorders in the coal miners (all P<0.05). Among them, the risk of sleep disorders in drinkers was higher than that in non-drinkers (P<0.05); the risk of sleep disorders was higher in miners working in a rotating work shift with two shifts than in those with three shifts (P<0.05); the higher the education level, the longer the duration of dust-exposure, the more serious the phase of respiratory symptoms, the worse the self-assessment of health, the higher the degree of occupational stress and the higher the degree of occupational burnout, the higher the risk of sleep disorders (all P<0.05). {L-End}Conclusion The incidence of sleep disorders in coal miners in this company is relatively high. Occupational stress, occupational burnout, education level, alcohol consumption, work shift, duration of dust-exposure, respiratory symptoms and health status are risk factors for sleep disorders in coal miners.

Myocardial infarction (MI) has the characteristics of high mortality rate, strong suddenness and invisibility. There are problems such as the delayed diagnosis, misdiagnosis and missed diagnosis in clinical practice. Electrocardiogram (ECG) examination is the simplest and fastest way to diagnose MI. The research on MI intelligent auxiliary diagnosis based on ECG is of great significance. On the basis of the pathophysiological mechanism of MI and characteristic changes in ECG, feature point extraction and morphology recognition of ECG, along with intelligent auxiliary diagnosis method of MI based on machine learning and deep learning are all summarized. The models, datasets, the number of ECG, the number of leads, input modes, evaluation methods and effects of different methods are compared. Finally, future research directions and development trends are pointed out, including data enhancement of MI, feature points and dynamic features extraction of ECG, the generalization and clinical interpretability of models, which are expected to provide references for researchers in related fields of MI intelligent auxiliary diagnosis.
Humans ; Electrocardiography ; Myocardial Infarction/diagnosis* ; Recognition, Psychology