Objective To explore the recognition capabilities of electronic nose combined with machine learning in identifying the breath odor map of benign and malignant pulmonary nodules and Traditional Chinese Medicine (TCM) syndrome elements. MethodsThe study design was a single-center observational study. General data and four diagnostic information were collected from 108 patients with pulmonary nodules admitted to the Department of Cardiothoracic Surgery of Hospital of Chengdu University of TCM from April 2023 to March 2024. The patients' TCM disease location and nature distribution characteristics were analyzed using the syndrome differentiation method. The Cyranose 320 electronic nose was used to collect the odor profiles of oral exhalation, and five machine learning algorithms including random forest (RF), K-nearest neighbor (KNN), logistic regression (LR), support vector machine (SVM), and eXtreme gradient boosting (XGBoost) were employed to identify the exhaled breath profiles of benign and malignant pulmonary nodules and different TCM syndromes. Results(1) The common disease locations in pulmonary nodules were ranked in descending order as liver, lung, and kidney; the common disease natures were ranked in descending order as Yin deficiency, phlegm, dampness, Qi stagnation, and blood deficiency. (2) The electronic nose combined with the RF algorithm had the best efficacy in identifying the exhaled breath profiles of benign and malignant pulmonary nodules, with an AUC of 0.91, accuracy of 86.36%, specificity of 75.00%, and sensitivity of 92.85%. (3) The electronic nose combined with RF, LR, or XGBoost algorithms could effectively identify the different TCM disease locations and natures of pulmonary nodules, with classification accuracy, specificity, and sensitivity generally exceeding 80.00%.ConclusionElectronic nose combined with machine learning not only has the potential capabilities to differentiate the benign and malignant pulmonary nodules, but also provides new technologies and methods for the objective diagnosis of TCM syndromes in pulmonary nodules.
Objective To identify the potential factors for psychological burdens and to better understand how the patients’ psychological status affect their treatment preferences. Methods A questionnaire survey was conducted among 996 patients with pulmonary nodules who visited the Thoracic Surgery Clinic of Guangdong Provincial People's Hospital from January to November 2021, including 381 males and 615 females, aged 47.26±11.53 years. A self-administrated questionnaire was used to investigate the sociodemographic and clinical characteristics of the patients, and the Hospital Anxiety and Depression Scale (HADS) was used to evaluate the psychological status of the patients, with a score>7 points of each subscale indicating potential anxiety or depression. Results Among the 996 patients with pulmonary nodules, the incidence of anxiety was 42.4% and the incidence of depression was 26.4%, while the incidence of both anxiety and depression was 24.7%. There was a significant correlation between anxiety and depression (ρ=0.834, P<0.05). Age, purpose of CT examination, number of pulmonary nodules and symptoms were independent factors for anxiety, while symptoms and number of pulmonary nodules were independent factors for depression (P<0.05). For treatment preferences, there was a statistical difference in educational level, symptoms, nodule size and anxiety level (P<0.05). Conclusion Anxiety and depression are common in patients with pulmonary nodules. Symptoms are associated with anxiety and depression, which also make an impact on treatment preferences.
ObjectiveTo explore the key points and difficulties of intraoperative frozen section diagnosis of pulmonary diseases. MethodsThe intraoperative frozen section and postoperative paraffin section results of pulmonary nodule patients in Beijing Chaoyang Hospital, Capital Medical University from January 2021 to January 2022 were collected. The main causes of misdiagnosis in frozen section diagnosis were analyzed, and the main points of diagnosis and differential diagnosis were summarized. ResultsAccording to the inclusion criteria, a total of 1 263 frozen section diagnosis results of 1 178 patients were included in the study, including 475 males and 703 females, with an average age of 58.7 (23-86) years. In 1 263 frozen section diagnosis results, the correct diagnosis rate was 95.65%, and the misdiagnosis rate was 4.35%. There were 55 misdiagnoses, including 18 (3.44%) invasive adenocarcinoma, 17 (5.82%) adenocarcinoma in situ, 7 (35.00%) mucinous adenocarcinoma, 4 (2.09%) minimally invasive adenocarcinoma, 3 (100.00%) IgG4 related diseases, 2 (66.67%) mucinous adenocarcinoma in situ, 1 (16.67%) atypical adenomatous hyperplasia, 1 (14.29%) sclerosing pulmonary cell tumor, 1 (33.33%) bronchiolar adenoma, and 1 (100.00%) papillary adenoma. ConclusionIntraoperative frozen section diagnosis still has its limitations. Clinicians need to make a comprehensive judgment based on imaging examination and clinical experience.
Solitary pulmonary nodule (SPN) is defined as a rounded opacity≤3 cm in diameter surrounded by lung parenchyma. The majority of smokers who undergo thin-section CT have SPNs, most of which are smaller than 7 mm. In the past, multiple follow-up examinations over a two-year period, including CT follow-up at 3, 6, 12, 18, and 24 months, were recommended when such nodules are detected incidentally. This policy increases radiation burden for the affected population. Nodule features such as shape, edge characteristics, cavitation, and location have not yet been found to be accurate for distinguishing benign from malignant nodules. When SPN is considered to be indeterminate in the initial exam, the risk factor of the patients should be evaluated, which includes patients' age and smoking history. The 2005 Fleischner Society guideline stated that at least 99% of all nodules 4 mm or smaller are benign; when nodule is 5-9 mm in diameter, the best strategy is surveillance. The timing of these control examinations varies according to the nodule size (4-6, or 6-8 mm) and the type of patients, specifically at low or high risk of malignancy concerned. Noncalcified nodules larger than 8 mm diameter bear a substantial risk of malignancy, additional options such as contrast material-enhanced CT, positron emission tomography (PET), percutaneous needle biopsy, and thoracoscopic resection or videoassisted thoracoscopic resection should be considered.
ObjectiveBy applying the mutual corroboration in the diagnosis, we aimed to improve the accuracy of preoperative imaging diagnosis, select the appropriate timing of operation and guide the follow-up time for patients with pulmonary nodules.MethodsClinical data of 1 368 patients with pulmonary nodules undergoing surgical treatment in our department from July 2016 to October 2019 were summarized. There were 531 males and 837 females at age of 44 (21-67) years. The intraoperative findings, images and pathology were classified and analyzed. The imaging pathology and pathological changes of pulmonary nodules were shown as a dynamic process through mutual collaboration and interaction.ResultsOf 1 368 patients with pulmonary nodules, 376 (27.5%) were pure ground-glass nodules, 729 (53.3%) were mixed ground-glass nodules and 263 (19.2%) were solid nodules. Among the pure ground-glass nodules, adenocarcinoma in situ (AIS) accounted for the highest proportion (156 patients), followed by microinvasive adenocarcinoma (MIA, 90 patients), atypical adenomatous hyperplasia (AAH, 85 patients), and benign tumors (20 patients). Among mixed ground-glass nodules, 495 patients were invasive adenocarcinoma (IA) and 207 patients of MIA. In solid nodules, patients were characterized by pathology of either IA (213 patients) or benign tumors (50 patients), and no patient was featured by AAH, AIS or MIA.ConclusionThe mutual collaboration and interaction can improve the accuracy of preoperative diagnosis of pulmonary nodules, and it supports the choice of operation timing and the judgment of follow-up time.
Objective To develop a preliminary "pulmonary nodule symptom scale" based on the Delphi method, providing a tailored, standardized, normalized, and promotable symptomatic evaluation tool for the efficacy assessment of pulmonary nodule patients treated with traditional Chinese medicine or integrated traditional Chinese and Western medicine interventions. Methods A preliminary pool of scale items was formed through literature review, interviews with doctors and patients, and reference to guidelines and consensus on pulmonary nodules and patient-reported outcome (PRO) scales related to lung cancer. Two rounds of expert consultation were conducted using the Delphi method. Based on the concentration and variation indicators of expert evaluations, and considering experts’ suggestions for specific item deletions and modifications, a core group meeting was held to screen and refine the scale items. Results Invitations were sent to 54 experts, with 51 accepting the consultation. The active coefficient for the first round of consultation was 94.4%, and for the second round, it was 100%. The average authority coefficient for the 51 experts was 0.896. The Kendall’s coefficient of concordance and the average coefficient of variation for the first and second rounds of consultation were 0.215 (P<0.001) and (0.34±0.07), 0.162 (P<0.001) and (0.24±0.05), respectively. Through two rounds of Delphi expert consultation, a preliminary "pulmonary nodule symptom scale" covering 17 items across four dimensions - respiratory symptoms, systemic manifestations, psychological state, and overall assessment - was formed. Conclusion The experts participating in this Delphi consultation had high authority and enthusiasm, and they have a good level of acceptance and consistency for the preliminary "pulmonary nodule symptom scale". Subsequent empirical research will be conducted on a large sample cohort of pulmonary nodule patients to verify the scale’s stability and effectiveness.
ObjectiveTo conduct item analysis on the Pulmonary Nodule Symptom Scale preliminarily developed through Delphi consultation, establish the final version of the scale, and evaluate its reliability and validity. MethodsPatients with pulmonary nodules who visited the outpatient department of the First Affiliated Hospital of Guangzhou University of Chinese Medicine from May to October 2024 were enrolled according to diagnostic criteria for pulmonary nodules and predefined inclusion/exclusion standards. Demographic data, medical history, and imaging characteristics of pulmonary nodules were collected, and participants completed the preliminary Pulmonary Nodule Symptom Scale developed through Delphi consultation. Four item analysis methods, including discrete trend method, critical ration method, correlation coefficient method, and Cronbach’s α coefficient, were employed for final item screening to determine the definitive version of the scale. Reliability and validity were systematically assessed via Cronbach’s α, split-half reliability, content validity, and construct validity. ResultsA total of 153 patients with pulmonary nodules were included, comprising 56 (36.60%) males and 97 (63.40%) females, with a mean age of (53.77±12.61) years. The median disease duration was 6 (1, 20) months, and mean nodule diameter was (7.64±4.37) mm, including 38 (24.84%) solitary patients and 115 (75.16%) multiple patients, as well as 39 (25.49%) solid nodules and 114 (74.51%) ground-glass nodules. Based on comprehensive results from four item analysis methods and core group discussion, two items ("symptom severity" and "quality of life") in the overall evaluation dimension were removed. The final scale comprised 15 items across three dimensions: respiratory symptoms, systemic manifestations, and psychological state. The Cronbach’s α coefficient was 0.84, with a Spearman-Brown coefficient of 0.912. Item-level content validity indices ranged from 0.824 to 1.000, while the scale-level content validity index reached 0.933. Kaiser-Meyer-Olkin (KMO) measure was 0.803, with Bartlett’s test of sphericity showing statistical significance (P<0.001). Exploratory factor analysis extracted three factors explaining 52.48% of total variance, and the rotated component matrix distribution generally aligned with the predefined three dimensions. ConclusionThe definitive version of the Pulmonary Nodule Symptom Scale contains 15 items across three dimensions (respiratory symptoms, systemic manifestations, and psychological state). Reliability and validity evaluations demonstrate good reliability and satisfactory validity for the scale.
Objective To develop an innovative recognition algorithm that aids physicians in the identification of pulmonary nodules. MethodsPatients with pulmonary nodules who underwent thoracoscopic surgery at the Department of Thoracic Surgery, Affiliated Drum Tower Hospital of Nanjing University Medical School in December 2023, were enrolled in the study. Chest surface exploration data were collected at a rate of 60 frames per second and a resolution of 1 920×1 080. Frame images were saved at regular intervals for subsequent block processing. An algorithm database for lung nodule recognition was developed using the collected data. ResultsA total of 16 patients were enrolled, including 9 males and 7 females, with an average age of (54.9±14.9) years. In the optimized multi-topology convolutional network model, the test results demonstrated an accuracy rate of 94.39% for recognition tasks. Furthermore, the integration of micro-variation amplification technology into the convolutional network model enhanced the accuracy of lung nodule identification to 96.90%. A comprehensive evaluation of the performance of these two models yielded an overall recognition accuracy of 95.59%. Based on these findings, we conclude that the proposed network model is well-suited for the task of lung nodule recognition, with the convolutional network incorporating micro-variation amplification technology exhibiting superior accuracy. Conclusion Compared to traditional methods, our proposed technique significantly enhances the accuracy of lung nodule identification and localization, aiding surgeons in locating lung nodules during thoracoscopic surgery.
ObjectiveTo explore the clinical value of three-dimensional computed tomography bronchography and angiography (3D-CTBA) in robotic lung segmentectomy.MethodsA non-randomized control study was performed and continuously enrolled 122 patients who underwent robotic lung segmentectomy in our hospital from January 2019 to January 2020. 3D-CTBA was performed before operations in 53 patients [a 3D-CTBA group, including 18 males, 35 females, with a median age of 52 (26-69) years] and not performed in the other 69 patients [a traditional group, including 23 males, 46 females, with a median age of 48 (30-76) years]. The clinical data of the patients were compared between the two groups.ResultsAll the patients were successfully completed the surgery and recovered from hospital, with no perioperative death. The baseline characteristics of the patients were not significantly different between the two groups (P>0.05). No significant difference was found in the operative time [120 (70-185) min vs. 120 (45-225) min, P=0.801], blood loss [50 (20-300) mL vs. 30 (20-400) mL, P=0.778], complications rate (17.0% vs. 11.6%, P=0.162), postoperative hospital stay [7 (4-19) d vs. 7 (3-20) d, P=0.388] between the two groups. In the 3D-CTBA group, 5 (9.4%) patients did not find nodules after segmentectomy, and only 1 (1.9%) of them needed lobectomy, but in the traditional group, 8 (11.6%) patients did not find nodules and had to carry out lobectomy, the difference was statistically significant (P<0.05). The follow-up time was 10 (1-26) months, and during this period, there was no recurrence, metastasis or death in the two groups.Conclusion3D-CTBA is helpful for accurate localization of nodules and reasonable surgical planning before operations, and reducing wrong resections in segmentectomy, without increasing the operation time, blood loss and complications. It is safe and effective in anatomical lung segmentectomy.
Objective
To explore the efficacy of a novel detection technique of circulating tumor cells (CTCs) to identify benign and malignant lung nodules.
Methods
Nanomagnetic CTC detection based on polypeptide with epithelial cell adhesion molecule (EpCAM)-specific recognition was performed on enrolled patients with pulmonary nodules. There were 73 patients including 48 patients with malignant lesions as a malignant group and 25 patients with benign lesion as a benign group. There were 13 males and 35 females at age of 57.0±11.9 years in the malignant group and 11 males and 14 females at age of 53.1±13.2 years in the benign group. e calculated the differential diagnostic efficacy of CTC count, and conducted subgroup analysis according to the consolidation-tumor ratio, while compared with PET/CT on the efficacy.
Results
CTC count of the malignant group was significantly higher than that of the benign group (0.50/ml vs. 0.00/ml, P<0.05). Subgroup analysis according to consolidation tumor ratio (CTR) revealed that the difference was statistically significant in pure ground glass (pGGO) nodules 1.00/mlvs. 0.00/ml, P<0.05), but not in part-solid or pure solid nodules. For pGGO nodules, the area under the receiver operating characteristic (ROC) curve of CTC count was 0.833, which was significantly higher than that of maximum of standardized uptake value (SUVmax) (P<0.001). Its sensitivity and specificity was 80.0% and 83.3%, respectively.
Conclusion
The peptide-based nanomagnetic CTC detection system can differentiate malignant tumor and benign lesions in pulmonary nodules presented as pGGO. It is of great clinical potential as a noninvasive, nonradiating method to identify malignancies in pulmonary nodules.
