Lung cancer is a leading cause of cancer-related morbidity and mortality worldwide. Coupled with the substantial workload, the clinical management of lung cancer is challenged by the critical need to efficiently and accurately process increasingly complex medical information. In recent years, large language models (LLMs) technology has undergone explosive development, demonstrating unique advantages in handling complex medical data by leveraging its powerful natural language processing capabilities, and its application value in the field of lung cancer diagnosis and treatment is continuously increasing. The paper systematically analyzes that the exceptional potential of LLMs in lung cancer auxiliary diagnosis, tumor feature extraction, automatic staging, progression/outcome analysis, treatment recommendations, medical documentation generation, and patient education. However, they face critical technical and ethical challenges including inconsistent performance in complex integrated decision-making (e.g., TNM staging, personalized treatment suggestions) and "black box" opacity issues, along with dilemmas such as training data biases, model hallucinations, data privacy concerns, and cross-lingual adaptation challenges ("data colonization"). Future directions should prioritize constructing high-quality multimodal corpora specific to lung cancer, developing interpretable and compliant specialized models, and achieving seamless integration with existing clinical workflows. Through dual drivers of technological innovation and ethical standardization, LLMs should be prudently advanced for holistic lung cancer management processes, ultimately promoting efficient, standardized, and personalized diagnosis and treatment practices.

ObjectiveTo analyze the epidemiological characteristics of 8 major respiratory pathogens in influenza-like illness (ILI) cases with acute respiratory infections at fever clinics in Huangpu District, Shanghai from 2015 to 2024, and to provide a scientific basis for the prevention and treatment of respiratory diseases. MethodsA retrospective study was conducted in Huangpu District. Individuals meeting the case definition of ILI from 2015 to 2024 was registered. Their nasopharyngeal swabs were collected for pathogen detection. A total of 8 respiratory viruses were tested, including Influenza A virus (Flu A), Influenza B virus (Flu B), adenovirus (ADV), enterovirus/human rhinovirus (EV/HRV), human parainfluenza virus (HPIV), human coronavirus (HCoV), respiratory syncytial virus (RSV), and human metapneumovirus (HMPV). ResultsFrom 2015 to 2019, a total of 344 ILI cases were tested, of which 192 out of 344 cases (55.81%) were tested positive for single respiratory pathogen. From 2023 to 2024, 1 557 ILI cases were tested, with 572 out of 1 557 cases (36.74%) being positive for single pathogen. From 2023 to 2024, the positive rate of single pathogen in ILI cases was significantly lower than that in 2015‒2019 (χ²=42.66, P<0.001). Specifically, the positive rate of Flu A (χ²=74.43, P<0.001) decreased, while that of HPIV (χ²=8.66, P=0.003) increased, both with statistically significant differences. According to the seasonal pattern, the epidemic intensity of Flu A decreased in summer, while that of HPIV increased in summer and autumn. Demographic results showed statistically significant differences in the positive rates of EV/HRV between genders (χ²=22.38, P<0.001), with males exhibiting a higher positive rate than females. No statistically significant differences were identified in the positive rates of single pathogen among different age groups (χ²=4.42, P=0.110). Nevertheless, statistically significant differences were noted when comparing the positive rates of EV/HRV, Flu A, Flu B and HPIV across different age groups (P<0.05). EV/HRV was more commonly detected in the 15‒<25 age group (10.93%), while Flu A and HPIV had the highest positive rates in the ≥60 age group (21.24% and 4.77%). Flu B had the highest positive rate in the 25‒<60 age group (11.26%). 52.63% of cases with co-infections occurred during winter, with the primary pathogens involved being EV/HRV (9 cases) and HCoV (6 cases). The most prevalent combination of co-infection was Flu A with EV/HRV. ConclusionThe prevalence of respiratory pathogens among ILI cases from 2023 to 2024 exhibited notable fluctuations compared to that from 2015 to 2019. Therefore, influenza surveillance should be strengthened, and attention should also be paid to the prevalence of respiratory pathogens such as HPIV. These findings have profound implications for future research, surveillance, vaccine planning, and public health policy making.

Objective To explore the accuracy of machine learning algorithms based on SHOX2 and RASSF1A methylation levels in predicting early-stage lung adenocarcinoma pathological types. Methods A retrospective analysis was conducted on formalin-fixed paraffin-embedded (FFPE) specimens from patients who underwent lung tumor resection surgery at Affiliated Hospital of Nantong University from January 2021 to January 2023. Based on the pathological classification of the tumors, patients were divided into three groups: a benign tumor/adenocarcinoma in situ (BT/AIS) group, a minimally invasive adenocarcinoma (MIA) group, and an invasive adenocarcinoma (IA) group. The methylation levels of SHOX2 and RASSF1A in FFPE specimens were measured using the LungMe kit through methylation-specific PCR (MS-PCR). Using the methylation levels of SHOX2 and RASSF1A as predictive variables, various machine learning algorithms (including logistic regression, XGBoost, random forest, and naive Bayes) were employed to predict different lung adenocarcinoma pathological types. Results A total of 272 patients were included. The average ages of patients in the BT/AIS, MIA, and IA groups were 57.97, 61.31, and 63.84 years, respectively. The proportions of female patients were 55.38%, 61.11%, and 61.36%, respectively. In the early-stage lung adenocarcinoma prediction model established based on SHOX2 and RASSF1A methylation levels, the random forest and XGBoost models performed well in predicting each pathological type. The C-statistics of the random forest model for the BT/AIS, MIA, and IA groups were 0.71, 0.72, and 0.78, respectively. The C-statistics of the XGBoost model for the BT/AIS, MIA, and IA groups were 0.70, 0.75, and 0.77, respectively. The naive Bayes model only showed robust performance in the IA group, with a C-statistic of 0.73, indicating some predictive ability. The logistic regression model performed the worst among all groups, showing no predictive ability for any group. Through decision curve analysis, the random forest model demonstrated higher net benefit in predicting BT/AIS and MIA pathological types, indicating its potential value in clinical application. Conclusion Machine learning algorithms based on SHOX2 and RASSF1A methylation levels have high accuracy in predicting early-stage lung adenocarcinoma pathological types.

BACKGROUND:Scholars at home and abroad consider New Zealand rabbits to be an ideal model animal because of the similar anatomical morphology of the lumbar spine to that of the human lumbar spine.There is a lack of systematic comparison of different ways to establish rabbit intervertebral disc degeneration models under X-ray guidance. OBJECTIVE:To establish a rabbit model of lumbar disc degeneration using X-ray guided acupuncture,end-plate injection and combined method,and to compare the modeling effects of these three methods. METHODS:Eighteen 6-month-old New Zealand white rabbits were randomly selected and divided into four groups:acupuncture group,endplate injection group,combined group and blank control group.In the acupuncture group,three consecutive segments of the intervertebral discs(L2/3,L3/4,L4/5)were needled and modeled;in the endplate injection group,50 μL of anhydrous ethanol was injected at a single point on the endplates of the three consecutive segmental discs;in the combined group,three consecutive segmental intervertebral discs were needled and injected with 50 μL of anhydrous ethanol at four azimuthal points on the endplates of the corresponding segmental discs;and the blank control group received no interventions.X-ray examination was performed to measure the disc height index at 2,4,and 8 weeks after surgery.The intervertebral disc tissues were then taken for anatomical observation and pathological examination. RESULTS AND CONCLUSION:(1)Anatomical examination showed that fibrous annulus rupture,nucleus pulposus degeneration,and total disc structure disorder were the main manifestation in the acupuncture group,endplate injection group,and combined group,respectively.(2)X-ray examination showed that the disc height index showed the most obvious reduction in the acupuncture group at 2 weeks after operation,significant reductions in the endplate injection group at 2 and 4 weeks after operation,and significant reductions in the combined group at 2,4,and 8 weeks after operation.(3)Pathological examination showed that the fibrous ring structure was damaged and the inner annulus fibrosus protruded inward in the acupuncture group;endplate fissure,disordered arrangement and nucleus loss were observed in the endplate injection group;total disc structure disorder with the nucleus pulposus losing water and shrinking and no obvious border with the broken annulus fibrosus was found in the combined group.To conclude,acupuncture,endplate injection and the modified endplate injection method can establish the rabbit intervertebral disc degeneration model.Compared with the single method,the modified endplate injection method can greatly accelerate and aggravate the degeneration of the intervertebral disc,and can effectively shorten the experiment period.

Traditional Chinese medicine （TCM） offers a rich theoretical foundation and clinical experience for the prevention and treatment of cardiovascular-kidney-metabolic syndrome（CKM）， demonstrating unique advantage. Building on previous work in managing diabetes， its complications， and chronic kidney disease， our team has proposed a five-phase evolution theory of "constraint， heat， deficiency， stasis， and toxin" as the core pathogenesis. These phases correspond to the pathological progression of constraint of phlegm-dampness， constraint transforming into heat， heat damaging qi and yin， stasis accumulated in the collateral vessels， and toxin induced by deficiency and stasis. In the prevention and treatment of CKM by TCM， it is emphasized to integrate the concept of "treating disease before it arises" with constitution theory， and incorporate the "2-5-8" prevention and treatment strategy， which combines prevention with treatment， tailors interventions to different phases， and employs comprehensive treatment modalities. Our goal is to leverage TCM's holistic advantages in preventing and treating CKM.

To summarize the clinical experience of Professor LIU Shangyi in treating pruritus vulvae. It is believed that women have the physiological characteristics of liver and kidney as the root， and their pubic area is easily attacked by wind-dampness pathogenic qi， so the core mechanism of pruritus vulvae is proposed as wind-dampness accumulation and deficiency of liver and kidney. The core treatment method is to dispel wind-dampness and nourish the liver and kidneys， and modify the Danggui Decoction （当归饮子） to form a self-prescribed Yinyang Formula （阴痒方） as the basic prescription to treat pruritus vulvaen.

The growth and development of children is an important stage for health, and its monitoringand intervention are related to the long-term development of individuals. The construction of a standardized and multi-dimensional database of pediatric growth and development-related diseases is an important basis for realizing precise diagnosis and treatment and health management. Based on the needs of clinical practice, this study proposes to establish a specialized database of pediatric growth and development-related diseases that integrates facial phenotypes and clinical diagnosis and treatment information. This study elaborates on the construction process, including data sources, data collection content, and the operation and management of the database; and proposes key points for quality control, including the establishment of quality control nodes, database construction standards, and a full-process quality control framework. The above ensure the integrity, logic and effectiveness of the data, so that the database can provide an objective basis for the screening and diagnosis of pediatric growth and development-related diseases. On the basis of scientific data management and strict quality control, the database will help reveal the patterns of children's growth and development, and promote the level of children's health management.

Enhanced recovery after surgery (ERAS) is a series of perioperative optimization measures based on evidence-based medicine aimed at achieving rapid recovery. Existing studies have shown that ERAS can effectively reduce surgical stress, decrease the incidence of complications, shorten hospital stays, save medical costs, and improve patient satisfaction. Although lung transplantation techniques have become increasingly mature, lung transplant recipients still have a high incidence of complications during perioperative period. To further improve the perioperative survival rate of lung transplant recipients, introducing ERAS concept into the perioperative management strategy of lung transplantation is of great significance for reducing incidence of perioperative complications, promoting rapid recovery and long-term survival of lung transplant recipients. This article discusses the advances in application of ERAS concept in the perioperative management of lung transplantation, aiming to provide references for optimizing the perioperative management of lung transplant recipients and reducing perioperative complications.

The clinical application of binocular endoscope relies primarily on the visual system of physicians to create a three-dimensional effect, but it cannot provide accurate depth information. The utilization of 3D reconstruction technology in binocular endoscopy can facilitate the recovery of image depth information, and the application of deep learning-based 3D reconstruction technology can significantly improve the accuracy and real-time performance of reconstruction results, making it widely applicable in the realm of minimally invasive surgery. This paper aims to explore the key technologies and implementation methods of deep learning based 3D reconstruction for binocular endoscopic images, and seeks to outline strategies for enhancing the quality of 3D reconstruction in endoscopic images, providing guidance for sustainable development of binocular endoscopic image reconstruction technology in clinical settings. This will assist in the application of minimally invasive surgery and contribute to meeting the demands of precision medicine.
Deep Learning ; Imaging, Three-Dimensional/methods* ; Humans ; Endoscopy/methods* ; Image Processing, Computer-Assisted/methods* ; Minimally Invasive Surgical Procedures

[This corrects the article DOI: 10.1016/j.apsb.2019.01.013.].