Background The contamination of public baths with Legionella pneumophila contamination has become a growing public health concern in recent years. However, research on its association with bacterial community characteristics in water samples remains limited. The integration of 16S rRNA sequencing and random forest modeling provides a new approach to elucidate the bacterial community characteristics of public bath water and their association with Legionella pneumophila contamination. Objective To investigate the bacterial community structure and diversity of public bath water in Shanghai, explore the association between Legionella pneumophila contamination and bacterial community characteristics, and identify key bacterial genera associated with contamination, thereby providing a scientific basis for formulating hygiene management regulations for public bath water. Methods From February to March 2023, water samples were collected from ten public baths in Shanghai which were selected based on business scale, regional distribution, and functional differences. Water quality parameters were evaluated, and the samples were categorized into Legionella-positive and Legionella-negative groups based on the detection results of Legionella pneumophila. The bacterial community structure, α-diversity, and β-diversity were analyzed using 16S rRNA sequencing. Redundancy analysis (RDA) was employed to examine the relationship between physicochemical factors and bacterial community diversity. A random forest model was employed to identify key bacterial genera distinguishing the two groups, with the importance of genera being evaluated based on the mean decrease accuracy (MDA). Results The oxygen consumption in the Legionella-positive group was significantly lower than that in the Legionella-negative group (mean values: 1.85 mg·L⁻¹ vs. 6.81 mg·L⁻¹, P< 0.05), while no significant differences were observed in other physicochemical indicators. The sequencing results revealed a total of 27 bacterial phyla and 454 bacterial genera, with Proteobacteria (63.00%) being the dominant phylum. The dominant genera included Pelomonas (8.50%), Acidovorax (8.13%), Mycobacterium (7.93%), and Acinetobacter (6.59%). The α-diversity analysis indicated that bacterial community richness (Chao1 and ACE indices) was significantly higher in the Legionella-positive group than in the Legionella-negative group (P<0.01). The β-diversity analysis showed no significant difference in the bacterial community structure between the two groups (P>0.05). The RDA analysis demonstrated that the bacterial community diversity was positively correlated with pH and negatively correlated with oxygen consumption and free residual chlorine. The RDA1 and RDA2 explained 23.92% and 21.30% of the bacterial community diversity, respectively. The random forest model identified 20 key genera significantly influencing the microbial community distribution between the two groups, including unclassified_Bradyrhizobiaceae (MDA=2.42), Meiothermus (MDA=2.37), and Flavihumibacter (MDA=2.26). Conclusion The diversity of bacterial communities in public bath water is influenced by pH, oxygen consumption, and free residual chlorine. Samples contaminated with Legionella pneumophila exhibit greater microbial richness and contain characteristic key bacterial genera that contribute to community differences. Machine learning random forest technology helps identify these distinctive key bacterial genera. The findings provide a basis for carrying out risk early warning strategies in such settings.

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

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

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

Body weight abnormalities, including overweight, obesity, and underweight, have become a dual public health challenge in Chinese adults: overweight and obesity lead to a variety of chronic complications, while underweight increases the risks of malnutrition, sarcopenia, and organ dysfunction. To systematically address these issues, multidisciplinary experts in endocrinology, sports science, nutrition, and psychiatry from various regions have held multiple weight management seminars. Based on the latest epidemiological data and clinical evidence, they expanded the guideline to include assessment and intervention strategies for underweight, in addition to the core content of obesity management. This guideline outlines the etiological mechanisms, evaluation methods, and multidimensional management strategies for overweight and obesity, covering key areas such as diagnosis and assessment, medical nutrition therapy, exercise prescription, pharmacological intervention, and psychological support. It is intended to provide a scientific and standardized approach to weight management across the adult population, aiming to curb the rising prevalence of obesity, mitigate complications associated with abnormal body weight, and improve nutritional status and overall quality of life.

Objective:To investigate risk factors for adverse pregnancy outcomes(APO) in women with hypertriglyceridemia(HTG) during late pregnancy despite normal thyroid function, focusing on thyroid-stimulating hormone receptor(TSHR) levels.Methods:A total of 242 pregnant women with normal thyroid function who delivered in General Hospital of Central Theater Command from October 2023 to June 2024 were divided into HTG( n=111) and non-HTG groups( n=131). Clinical data, lipid profiles, thyroid function, TSHR levels, and APO were compared, and the influencing factors of APO were analyzed. Results:Compared with non-HTG group, APO, adverse maternal outcomes, and gestational diabetes mellitus(GDM) were significantly more frequent in the HTG group( P<0.05). The HTG group also had higher triglyceride(TG), fasting plasma glucose(FPG), triglyceride glucose index(TyG), triglyceride/high density lipoprotein cholesterol(TG/HDL-C), thyroid stimulating hormone(TSH) and TSHR, with lower free triiodothyronine (FT 3)( P<0.05). TSHR was an independent risk factor for APO, maternal adverse outcomes, and GDM in all pregnant women( OR=1.112, 95% CI 1.007-1.229; OR=1.126, 95% CI 1.020-1.243; OR=1.133, 95% CI 1.025-1.253) and was also an independent risk factor for APO in the HTG group( OR=1.165, 95% CI 1.005-1.351). Conclusion:Pregnant women with normal thyroid function and HTG in late pregnancy are more likely to have APO, manifested as maternal adverse outcomes and GDM. TSHR is an independent risk factor for APO.

Objective:To describe the clinical and pathological features of patients with myofasciitis.Methods:The clinical manifestations and auxiliary examination (laboratory, electromyogram, imaging and muscle biopsy) results of 52 patients with myofasciitis diagnosed by pathology at Peking University First Hospital from August 2002 to December 2024 were collected and analyzed.Results:Among the 52 patients (33 males and 19 females), the age of disease onset was (34.4±16.4) years (6.0-73.0 years) and the disease duration was 17.7 (0.3, 120.0) months; the main symptoms included myalgia in the distal limbs (28 cases, 53.8%), diffuse cutaneous or muscle sclerosis (21 cases, 40.4%), muscle weakness (22 cases, 42.3%) and limited joint activity (23 cases, 44.2%); 12 patients (23.1%) were combined with other diseases. All patients had no history of vaccination. Laboratory examinations showed that 80.8% (21/26) of patients had elevated C-reactive protein, 80.0% (20/25) had elevated erythrocyte sedimentation rate, and 26.5% (9/34) had elevated creatine kinase. Among 19 patients undergoing electromyography, 6 cases showed myogenic changes, 4 cases showed neurogenic changes, 1 case showed both myogenic and neurogenic changes, and 8 cases showed no obvious abnormality. Myofascial edema was observed in all 15 patients who underwent muscle magnetic resonance imaging, with partial involvement of adjacent muscles in some cases. According to myopathological changes, the 52 patients were divided into macrophagic myofasciitis in 41 cases (78.8%), lymphocytic myofasciitis in 7 cases (13.5%), and eosinophilic fasciitis in 4 cases (7.7%). Among the 52 patients, fibroblast proliferation in the myofascia was present in 39 cases (75.0%), subfascial muscle fiber atrophy in 28 cases (53.8%), and scattered muscle fiber necrosis and regeneration in 15 cases (28.8%). Major histocompatibility complex class Ⅰexpression on muscle fibers was positive in 89.5% (34/38) of patients, and membrane attack complex deposition on muscle fibers and/or capillary walls was present in 39.5% (15/38) of patients. Among 25 patients with follow-up, all received low-dose oral glucocorticoids, and 7 additionally received methotrexate, intravenous immunoglobulin, or hydroxychloroquine. During follow-up, 22 patients showed clinical improvement, 1 patient remained stable, and 2 patients died.Conclusions:Non-vaccine-associated macrophagic myofasciitis is the most common pathological subtype of myofasciitis. A few patients are concomitant with other diseases. Muscle magnetic resonance imaging is helpful in the diagnosis of the disease. Most patients respond to immunosuppressive treatment.

Objective:To investigate the longitudinal patterns and influencing factors of platelet counts among healthy adults in Sichuan Province from 2010 to 2021, and to inform the establishment of region-specific reference intervals for platelet counts.Methods:This study is a retrospective study. A total of 7 808 healthy adults who underwent annual physical examinations at West China Hospital, Sichuan University, between January 2010 and December 2021 were included. All participants were permanent Chengdu residents and completed consecutive complete blood count tests. Group-based trajectory modeling (GBTM) was used to identify distinct trajectories of platelet count over the ten-year period. One-way analyses were then conducted to compare baseline demographic characteristics (sex and age) among the different trajectory groups.Results:Among 7 808 participants, 4 589 (58.8%) were male and 3 219 (41.2%) were female. Four platelet count trajectories were identified by GBTM: steadily increasing group [27.4% (2 139/7 808)], early increase-plateau group [44.1% (3 445/7 808)], early decrease-subsequent increase group [5.4% (422/7 808)], and steadily decreasing group [23.1% (1 802/7 808)], with an average growth rate of 3.3%, 1.6%, 0.7%, and -0.6%, respectively. There were statistically significant differences in both sex and age distributions among the four trajectory groups. Sex-distribution differed significantly across the four trajectory groups ( χ2=73.3, P<0.001). The male proportions in the four trajectory groups were 59.6% (1 275/2 139), 62.8% (2 165/3 445), 48.1% (203/422), and 52.5% (946/1 802), respectively. The baseline ages were 45 (36, 55), 43 (35, 53), 50 (40, 60), and 47 (39, 58) years, respectively (H=121.0, P<0.001). Conclusions:Healthy adults in Sichuan Province exhibit four longitudinal trajectories of platelet counts: steadily increasing, early increase-plateau, early decrease-subsequent increase, and steadily decreasing. The two trajectories characterized by rising platelet counts (steadily increasing group and early increase-plateau group) exhibited higher male predominance and lower median ages, whereas the early decrease-subsequent increase group and the steadily decreasing group exhibited lower male proportions and higher median ages. Therefore, while establishing reference intervals and developing health management strategies for platelet counts, it is essential to account for the sex, age characteristics and the population′s dynamic changes.

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.

Objective:To explore the predictive value of dual-energy CT lumbar quantitative measurement combined with serum bone alkaline phosphatase (BALP), osteocalcin (BGP), and β-type I collagen carboxy-terminal peptide ( β-CTx) for the risk of fractures in patients with osteoporosis. Methods:A total of 90 patients with osteoporosis who underwent dual-energy CT lumbar quantitative detection at the First People’s Hospital of Shangqiu from Jan. 2020 to Jan. 2023 were selected as the research subjects. According to the occurrence of fractures within one year of follow-up, the patients were divided into the fracture group ( n=36) and the non-fracture group ( n=54). The clinical data, dual-energy CT lumbar quantitative parameters, and serum BALP, BGP, and β-CTx levels of the two groups were compared. Logistic multivariate regression analysis was used to analyze the risk factors for fractures in patients with osteoporosis, and the receiver operating characteristic (ROC) curve was used to analyze the predictive value of dual-energy CT lumbar quantitative parameters combined with serum BALP, BGP, and β-CTx for fractures in patients with osteoporosis. Results:There were no statistically significant differences in gender, age, body mass index (BMI), smoking history, drinking history, or bone marrow CT value parameters between the fracture group and the non-fracture group ( χ2=0.66, t=1.86, t=1.59, χ2=0.19, χ2=0.98, t=0.40, all P > 0.05). However, there were statistically significant differences in the history of fragility fractures, regular calcium supplementation, lumbar bone mineral density (BMD), calcium CT value, mixed energy image CT value, calcium concentration, fat fraction, BALP, BGP, and β-CTx ( χ2=9.73, χ2=4.17, t=3.14, t=7.06, t=7.92, t=6.50, t=3.26, t=8.12, t=12.66, t=11.37, all P < 0.05). Logistic multivariate regression analysis showed that the history of fragility fractures ( OR=1.863, P=0.023), regular calcium supplementation ( OR=1.728, P=0.031), fat fraction ( OR=1.685, P=0.009), BALP ( OR=1.815, P=0.002), BGP ( OR=1.605, P=0.003), and β-CTx ( OR=1.636, P < 0.001) were risk factors for fractures in patients with osteoporosis, while lumbar bone BMD ( OR=0.456, P=0.025), calcium CT value ( OR=0.486, P=0.005), mixed energy image CT value ( OR=0.490, P < 0.001), and calcium concentration ( OR=0.509, P=0.010) were protective factors. The ROC curve showed that the sensitivity of dual-energy CT lumbar quantitative measurement parameters combined with serum BALP, BGP, and β-CTx in predicting fractures in patients with osteoporosis was 94.68%, the specificity was 92.16%, the Youden index was 0.868, the area under the curve (AUC) was 0.947, and the 95% confidence interval ( CI) was 0.905 to 0.982. Conclusion:Dual-energy CT lumbar quantitative parameters and serum BALP, BGP, and β-CTx levels have certain predictive value for the risk of fractures in patients with osteoporosis, and the combined prediction value is higher.