Timely Pulmonary Tuberculosis Diagnosis Based on the Epidemiological Disease Spectrum: Population-Based Prospective Cohort Study in the Republic of Korea.

BACKGROUND: Timely pulmonary tuberculosis (PTB) diagnosis is a global health priority for interrupting transmission and optimizing treatment outcomes. The traditional dichotomous time-divided approach for addressing time delays in diagnosis has limited clinical application because the time delay significantly varies depending on each community in question. OBJECTIVE: We aimed to reevaluate the diagnosis time delay based on the PTB disease spectrum using a novel scoring system that was applied at the national level in the Republic of Korea. METHODS: The Pulmonary Tuberculosis Spectrum Score (PTBSS) was developed based on previously published proposals related to the disease spectrum, and its validity was assessed by examining both all-cause and PTB-related mortality. In our analysis, we integrated the PTBSS into the Korea Tuberculosis Cohort Registry. We evaluated various time delays, including patient, health care, and overall delays, and their system-associated variables in line with each PTBSS. Furthermore, we reclassified the scores into distinct categories of mild (PTBSS=0-1), moderate (PBTBSS=2-3), and severe (PBTBSS=4-6) using a multivariate regression approach. RESULTS: Among the 14,031 Korean patients with active PTB whose data were analyzed from 2018 to 2020, 37% (n=5191), 38% (n=5328), and 25% (n=3512) were classified as having a mild, moderate, and severe disease status, respectively, according to the PTBSS. This classification can therefore reflect the disease spectrum of PTB by considering the correlation of the score with mortality. The time delay patterns differed according to the PTBSS. In health care delays according to the PTBSS, greater PTB disease progression was associated with a shorter diagnosis period, since the condition is microbiologically easy to diagnose. However, with respect to patient delays, the change in elapsed time showed a U-shaped pattern as PTB progressed. This means that a remarkable patient delay in the real-world setting might occur at both apical ends of the spectrum (ie, in both mild and severe cases of PTB). Independent risk factors for a severe PTB pattern were age (adjusted odds ratio 1.014) and male sex (adjusted odds ratio 1.422), whereas no significant risk factor was found for mild PTB. CONCLUSIONS: Timely PTB diagnosis should be accomplished. This can be improved with use of the PTBSS, a simple and intuitive scoring system, which can be more helpful in clinical and public health applications compared to the traditional dichotomous time-only approach.

Effect of complicated, untreated and uncontrolled diabetes and pre-diabetes on treatment outcome among patients with pulmonary tuberculosis.

BACKGROUND AND OBJECTIVE: Patients with tuberculosis and diabetes have a higher risk of unfavourable anti-tuberculosis treatment outcomes. In the present study, we aimed to evaluate the effects of various diabetes statuses on the outcomes of patients with pulmonary tuberculosis. METHODS: Among the patients with pulmonary tuberculosis enrolled in the Korea Tuberculosis Cohort (KTBC) registry and the multicentre prospective cohort study of pulmonary tuberculosis (COSMOTB), those with diabetes and complicated diabetes were identified. The primary and secondary outcomes were unfavourable outcomes and mortality, respectively. The effect of diabetes and complicated diabetes on the outcomes was assessed using multivariable logistic regression analysis. Using COSMOTB, subgroup analyses were performed to assess the association between various diabetes statuses and outcomes. RESULTS: In the KTBC, diabetes (adjusted odds ratio [aOR] = 1.93, 95% CI = 1.64-2.26) and complicated diabetes (aOR = 1.96, 95% CI = 1.67-2.30) were significantly associated with unfavourable outcomes, consistent with the COSMOTB data analysis. Based on subgroup analysis, untreated diabetes at baseline was an independent risk factor for unfavourable outcomes (aOR = 2.72, 95% CI = 1.26-5.61). Prediabetes and uncontrolled diabetes increased unfavourable outcomes and mortality without statistical significance. CONCLUSION: Untreated and complicated diabetes at the time of tuberculosis diagnosis increases the risk of unfavourable outcomes and mortality.

Long term management of people with post-tuberculosis lung disease.

Post-tuberculosis lung disease (PTLD) is emerging as a significant area of global interest. As the number of patients surviving tuberculosis (TB) increases, the subsequent long-term repercussions have drawn increased attention due to their profound clinical and socioeconomic impacts. A primary obstacle to its comprehensive study has been its marked heterogeneity. The disease presents a spectrum of clinical manifestations which encompass tracheobronchial stenosis, bronchiectasis, granulomas with fibrosis, cavitation with associated aspergillosis, chronic pleural diseases, and small airway diseases-all persistent consequences of PTLD. The spectrum of symptoms a patient may experience varies based on the severity of the initial infection and the efficacy of the treatment received. As a result, the long-term management of PTLD necessitates a detailed and specific approach, addressing each manifestation individually-a tailored strategy. In the immediate aftermath (0-12 months after anti-TB chemotherapy), there should be an emphasis on monitoring for relapse, tracheobronchial stenosis, and smoking cessation. Subsequent management should focus on addressing hemoptysis, managing infection including aspergillosis, and TB-associated chronic obstructive pulmonary disease or restrictive lung function. There remains a vast expanse of knowledge to be discovered in PTLD. This review emphasizes the pressing need for comprehensive, consolidated guidelines for management of patients with PTLD.

Effects of cervical stabilization with visual feedback on craniovertebral angle and proprioception for the subjects with forward head posture.

BACKGROUND: This study aimed to identify the effect of cervical stabilization exercise with visual feedback on the craniovertebral angle and proprioception in subjects with forward head posture. METHODS: Thirty healthy adults were recruited in the study. Participants were randomly assigned to the stabilization exercise with visual feedback (SE-VF) group (N = 15) or stabilization exercise group (N = 15). The SE-VF group performed cervical stabilization exercise while sitting on a chair without a backrest and checking their side profile in real-time via a monitor 3-m away. The stabilization exercise group performed the same cervical stabilization exercise as the SE-VF group but without visual feedback. Craniovertebral angle (CVA) was measured to quantify forward head posture, and the proprioception of the subjects was evaluated. RESULTS: There was a significant interaction between group and time in CVA and proprioception (P < .05). Additionally, there was no significant difference pre-intervention between the groups (P > .05); however, there was a significant difference post-intervention (P < .05) in CVA and proprioception. CONCLUSION: The findings of this study showed that the cervical stabilization exercise with visual feedback was effective for the proprioception of subjects. Moreover, the results suggest that visual feedback is effective in cervical stabilization exercise.

Characteristics of subclinical tuberculosis compared to active symptomatic tuberculosis using nationwide registry cohort in Korea: prospective cohort study.

Objective: The clinical manifestations of tuberculosis (TB) range from asymptomatic to disseminated depending on the microbiological and immunological status, making the diagnosis challenging. To improve our understanding of the disease progression mechanism, we aimed to identify the characteristics of subclinical TB and important predictors of symptom development. Methods: From July 2018 to June 2019, we systemically collected data from the National Surveillance System of South Korea on patients with pulmonary TB, and compared the characteristics of subclinical and active symptomatic TB patients. Results: A total of 4,636 patients with pulmonary TB were included, and the prevalence of subclinical TB was 37.1% (1,720/4,636). In subclinical TB patients, the positivity rates of acid-fast bacilli (AFB) smear and culture were 16.2 and 50.2%, respectively. Subclinical TB patients were younger (55.6 ± 19.2 vs. 60.7 ± 19.5, P < 0.001), had a higher body mass index (21.7 ± 3.1 vs. 21.0 ± 3.5, P < 0.001), less under Medicaid support, and had lower rates of chronic lung disease, AFB smear and culture positivity, and bilateral disease. Regarding the characteristic differences of individual TB-related symptoms, age was positively associated with dyspnoea and general weakness but negatively associated with chest pain, haemoptysis, and weight loss. Male patients were more prone to weight loss. Chronic lung disease was related to symptoms including cough/phlegm, dyspnoea, and haemoptysis, while autoimmune diseases were associated with fever and weight loss. Conclusions: The development of TB-related symptoms was associated with microbiological burden and clinical characteristics including underlying comorbidities, which should be evaluated carefully.

Risk of loss to follow-up among tuberculosis patients in South Korea: whom should we focus on?

Introduction: In South Korea, public-private mix (PPM) has been a key strategy in national tuberculosis (TB) control program. This study aimed to identify rate of loss to follow-up (LTFU) among TB patients in nationwide PPM institutions and their risk factors. Methods: A nationwide prospective observational study including drug susceptible TB patients diagnosed from the 1st day to the 10th day of every month between July 2018 and December 2020 in PPM institutions was designed. Multivariable survival models in which death and failure were designated as events with competing risk were used to investigate risk factors for LTFU. Results: A total of 14,942 patients were included. Of them, 356 (2.4%) had an LTFU. Risk factors for LTFU were: underweight patients (adjusted hazard ratio (aHR): 1.47, 95% CI: 1.12-1.92), patients living alone (aHR: 1.43, 95% CI: 1.16-1.76), heavy drinkers (aHR: 1.67, 95% CI: 1.16-2.39), those with malignancy (aHR: 1.49, 95% CI: 1.07-2.05), foreigners (aHR: 5.96, 95% CI: 4.51-7.89), and those with previous TB history reported as an unfavorable outcome (aHR: 4.43, 95% CI: 2.77-7.08). Effect of age on LTFU was not significant. Brief interruption of anti-TB treatment (less than two months) in current session was associated with subsequent LTFU [adjusted odds ratio: 13.09 (10.29-16.66)]. Conclusion: Identifying vulnerability of patients such as living alone, being heavy alcoholics, being foreigners or having previous TB history reported as an unfavorable outcome is required. Thorough case management for these vulnerable groups could be feasible with collaboration between public and private sectors.

Effects of underweight and overweight on mortality in patients with pulmonary tuberculosis.

Background: Poor nutrition increases disease severity and mortality in patients with tuberculosis (TB). There are gaps in our understanding of the effects of being underweight or overweight on TB in relation to sex. Methods: We generated a nationwide TB registry database and assessed the effects of body mass index (BMI) on mortality in patients with pulmonary TB. The cause of death was further classified as TB-related or non-TB-related deaths. First, logistic regression analysis was performed to assess the association between BMI (a continuous variable) and mortality, and subgroup analyses of the multivariable logistic regression model were performed separately in male and female patients. Second, we categorized BMI into three groups: underweight, normal weight, and overweight, and assessed the impact of being underweight or overweight on mortality with reference to normal weight. Results: Among 9,721 patients with pulmonary TB, the mean BMI was 21.3 ± 3.4; 1,927 (19.8%) were underweight, and 2,829 (29.1%) were overweight. In multivariable logistic regression analysis, mortality was significantly increased with the decrement of BMI (adjusted odds ratio [aOR] = 0.893, 95% confidence interval [CI] = 0.875-0.911). In subgroup analyses, underweight patients had significantly higher odds of mortality, especially TB-related deaths (aOR = 2.057, 95% CI = 1.546-2.735). The association with mortality and male patients was higher (aOR = 2.078, 95% CI = 1.717-2.514), compared with female patients (aOR = 1.724, 95% CI = 1.332-2.231). Being overweight had a significant protective effect against TB-related death only in females (aOR = 0.500, 95% CI = 0.268-0.934), whereas its effect on non-TB-related death was observed only in males (aOR = 0.739, 95% CI = 0.587-0.930). Conclusion: Being underweight was linked to high mortality, whereas being overweight had beneficial effects in patients with pulmonary TB.

Deaths from tuberculosis: differences between tuberculosis-related and non-tuberculosis-related deaths.

Objective: Tuberculosis (TB) is a major cause of ill health and one of the leading causes of death worldwide. The first step in developing strategies to reduce TB mortality is to identify the direct causes of death in patients with TB and the risk factors for each cause. Methods: Data on patients with TB systemically collected from the National Surveillance System of South Korea from January 2019 to December 2020 were included in this study. We analyzed the clinical characteristics associated with TB and non-TB-related deaths, including TB-related symptoms, comorbidities, and radiographic and microbiological findings. Results: Of the total of 12,340 patients with TB, 61% were males with a mean age of 61.3 years. During the follow-up period, the overall mortality rate was 10.6%, with TB-related deaths accounting for 21.3% of all TB deaths. The median survival time in the TB-related death group was 22 days. TB-related death was associated with older age, lower body mass index (BMI), dyspnea, fever, general weakness, bilateral radiographic patterns, and acid-fast bacilli (AFB)-positive smears. Non-TB-related deaths were associated with older age, male sex, lower BMI, comorbidities of heart, liver, kidney, and central nervous system (CNS) diseases, CNS TB involvement, the presence of dyspnea, general weakness, and bilateral radiographic patterns. Conclusion: Patients with high-risk TB must be identified through cause-specific mortality analysis, and the mortality rate must be reduced through intensive monitoring of patients with a high TB burden and comorbidities.

Clinical significance of normalized airflow obstruction in patients with chronic obstructive pulmonary disease.

BACKGROUND: There is ongoing debate regarding the diagnostic criteria for chronic obstructive pulmonary disease (COPD); recent studies have focused on the early COPD detection and management. Here, we compared clinical features and prognosis in patients with FEV1/FVC<0.70 at baseline, according to normalized airflow obstruction status during follow-up. METHODS: We used the Korea COPD Subgroup Study (KOCOSS) cohort database, a prospective nationwide observational COPD study. Normalized obstruction (NO) was defined as FEV1/FVC ≥0.7 in the 2-year follow-up period, whereas fixed obstruction (FO) was defined as FEV1/FVC <0.7. Demographic and clinical data, 1-year exacerbation risk and difference in FEV1 decline over 2 years were compared between NO and FO groups. RESULTS: Among the 670 COPD patients with post-bronchodilator FEV1/FVC <0.7 in this study, 95 (14.2%) displayed NO. Compared with the FO group, the NO group had higher FEV1, and DLCO, body mass index, as well as lower Saint George Respiratory Questionnaire, Beck Depression Index, and Beck Anxiety Index. Blood eosinophil count, IgE level, and FeNO did not significantly differ between two groups. There was no significant difference in exacerbation frequency between the two groups, but the NO group had a significant increase in FEV1 compared with the FO group during follow-up. CONCLUSION: Transient airflow obstruction in the NO group may represent a clinical manifestation of early COPD; close monitoring is needed for such patients.

Metabolic Disorders Are Associated With Drug-Induced Liver Injury During Antituberculosis Treatment: A Multicenter Prospective Observational Cohort Study in Korea.

Background: Drug-induced liver injury (DILI) may lead to the discontinuation of antituberculosis (anti-TB) treatment (ATT). Some studies have suggested that metabolic disorders increase the risk of DILI during ATT. This study aimed to identify risk factors for DILI, particularly metabolic disorders, during ATT. Methods: A multicenter prospective observational cohort study to evaluate adverse events during ATT was conducted in Korea from 2019 to 2021. Drug-susceptible patients with TB who had been treated with standard ATT for 6 months were included. The patients were divided into 2 groups depending on the presence of 1 or more metabolic conditions, such as insulin resistance, hypertension, obesity, and dyslipidemia. We monitored ATT-related adverse events, including DILI, and treatment outcomes. The incidence of DILI was compared between individuals with and without metabolic disorders, and related factors were evaluated. Results: Of 684 patients, 52 (7.6%) experienced DILI, and 92.9% of them had metabolic disorders. In the multivariable analyses, underlying metabolic disorders (adjusted hazard ratio [aHR], 2.85; 95% CI, 1.01-8.07) and serum albumin <3.5 g/dL (aHR, 2.26; 95% CI, 1.29-3.96) were risk factors for DILI during ATT. In the 1-month landmark analyses, metabolic disorders were linked to an elevated risk of DILI, especially significant alanine aminotransferase elevation. The treatment outcome was not affected by the presence of metabolic disorders. Conclusions: Patients with metabolic disorders have an increased risk of ATT-induced liver injury compared with controls. The presence of metabolic disorders and hypoalbuminemia adversely affects the liver in patients with ATT.

Delphi Survey on the Current and Future Korean Guidelines for Isoniazid-Monoresistant Tuberculosis.

Purpose: Isoniazid-monoresistant tuberculosis (Hr-TB) has emerged as a global challenge, necessitating detailed guidelines for its diagnosis and treatment. We aim to consolidate the Korean guidelines for Hr-TB management by gathering expert opinions and reaching a consensus. Patients and Methods: A conventional Delphi method involving two rounds of surveys was conducted with 96 experts selected based on their clinical and research experience and involvement in nationwide tuberculosis studies and development of the Korean guidelines on tuberculosis. The survey consisted of three sections of questionnaires on diagnosis, treatment, and general opinions on Hr-TB. Results: Among the 96 experts, 72 (75%) participated in the two rounds of the survey. A majority of experts (96%) strongly agreed on the necessity of molecular drug susceptibility testing (DST) for isoniazid and rifampin resistance in all tuberculosis patients and emphasized the importance of interpreting mutation types (inhA or katG) and additional molecular DST for fluoroquinolones for confirmed isoniazid-resistant cases. Over 95.8% of experts recommended treating Hr-TB with a combination of rifampin, ethambutol, pyrazinamide, and levofloxacin for six months, without exceeding 12 months unless necessary. They also acknowledged the drawbacks of long-term pyrazinamide use due to its side effects and agreed on shortening its duration by extending the duration of the rest of the treatment with a modified combination of choice. Conclusion: This Delphi survey enabled Korean tuberculosis experts to reach a consensus on diagnosing and treating Hr-TB. These findings will be valuable for developing the upcoming revised Korean guidelines for Hr-TB management.

Smoking Status at Time of Diagnosis Affects the Efficacy of Anti-PD-1/L1 Therapy in Patients With Advanced NSCLC.

BACKGROUND/AIM: Programmed death ligand-1 (PD-L1) expression is known to be a predictive biomarker for response to immunotherapy in non-small cell lung cancer (NSCLC). However, PD-L1 is not always a reliable predictive biomarker. In the present study, we aimed to compare responses to immunotherapy according to smoking status in NSCLC patients receiving immunotherapy in second line or further line treatment. PATIENTS AND METHODS: The lung cancer registry database of the Catholic Medical Center, Seoul, Republic of Korea was used. Patients were eligible for this study if they were diagnosed with histologically confirmed NSCLC and received immune checkpoint inhibitors (ICIs) as second-line or further line therapy from January 2017 to December 2021. RESULTS: Overall, 220 patients with NSCLC treated with ICIs were enrolled. There were 40 never smokers, 73 former smokers, and 107 current smokers. In multivariate analysis, smoking status, pathologic type, and PD-L1 expression were significant factors affecting PFS. Sex, ECOG performance status, pathologic type, and PD-L1 expression were significant factors affecting OS. CONCLUSION: Smoking status at diagnosis of lung cancer could be a predictive biomarker for response to ICIs in patients with advanced NSCLC.

Non traumatic acquired acute transdiaphragmatic intercostal hernia induced by coughing.

Transdiaphragmatic intercostal hernia is a rare disease. It is usually caused by trauma and is rarely caused by coughing. Although a few cases of intercostal hernia induced by coughing have been reported, our case of a non traumatic acquired acute transdiaphragmatic intercostal and abdominal hernia induced by coughing is very rare. A 77-year-old woman presented with sudden-onset left lower chest pain after an episode of violent coughing. She had risk factors for intercostal hernia, including obesity, chronic obstructive pulmonary disease, oral steroid use, and diabetes mellitus. Computed tomography showed herniation of the lung and intra-abdominal organs into the thoracic and abdominal wall through a ruptured diaphragm, as well as the intercostal and abdominal muscles. Surgery was completed with interrupted sutures to close the defects after the reduction of the herniated organs. Our experience suggests that careful examinations, including the assessment of risk factors and computed tomography imaging, were essential for establishing an accurate diagnosis, and that the repair of a ruptured diaphragm with simple interrupted sutures without any prosthetic materials seems to be feasible in selected patients with a transdiaphragmatic intercostal hernia.

Identification of predictive factors for early relapse in patients with unresectable stage III non-small cell lung cancer receiving consolidation durvalumab after concurrent chemoradiation therapy.

BACKGROUND: Patients with locally advanced, unresectable, non-small cell lung cancer (NSCLC) receiving definitive concurrent chemoradiation therapy (CCRT) benefit from durvalumab consolidation therapy. However, predictive factors for early relapse during durvalumab maintenance have not yet been identified. METHODS: The present study included the lung cancer cohort of the Catholic Medical Centers at the Catholic University of Korea from January 2018 to December 2021. A total of 51 NSCLC patients treated with durvalumab consolidation therapy after definitive CCRT were included in the analysis. Early relapse was defined as patients experiencing relapse within 6 months of starting initial durvalumab therapy. RESULTS: Among the 51 patients, 15 (29.4%) relapsed during the study period. Median time from initial therapy of durvalumab to progression was 451.00 ± 220.87 days (95% confidence interval [CI]: 18.10-883.90) in overall patients. In multivariate analysis, younger age (adjusted odds ratio [aOR], 0.792; 95% CI: 0.642-0.977; p = 0.030), higher pack-years (aOR, 1.315; 95% CI: 1.058-1.635; p = 0.014), non-COPD (aOR, 0.004; 95% CI: 0.000-0.828; p = 0.004) and anemia (aOR, 234.30; 95% CI: 1.212-45280.24; p = 0.042), were independent predictive factors for early relapse during durvalumab consolidation therapy. CONCLUSION: Younger age, higher number of pack-years, non-COPD, and anemia were independent predictive factors for early relapse during durvalumab consolidation therapy in patients with unresectable stage III NSCLC after definitive CCRT. Careful patient selection and clinical attention are needed for high-risk individuals.

Recommendation of pharmacokinetics/pharmacodynamics target of ethambutol to suppress tuberculosis resistance: A population pharmacokinetics study on a large prospective cohort.

BACKGROUND: The ability of ethambutol (EMB) to suppress bacterial resistance has been demonstrated in a time-dependent manner. Through the development of a population pharmacokinetics (PK) model, this study aimed to suggest the PK/pharmacodynamics (PD) target and identify the significant covariates that influence interindividual variability (IIV) in the PK of EMB. METHODS: In total, 837 patients from 20 medical centres across Korea were enrolled in this study. The non-linear mixed-effect method was used to establish and validate the population PK model. RESULTS: A two-compartment model with transit compartment absorption was sufficient to describe the PK of EMB. Body weight and renal function were identified as significant covariates that affect IIV of the apparent clearance (CL/F) of EMB. Patients with moderate renal function showed 35% and 55% lower CL/F (CL/F 89.9 L/h) compared with those with mild and normal renal function, respectively. All the renal function groups with simulated doses ranging from 800 to 1200 mg achieved area under the curve over minimum inhibitory concentration (MIC) >119, and maintained T>MIC for >23 h for MIC of 0.5 µg/mL. Based on our simulation result, it is suggested that doses of 800, 1000, and 1200 mg should obtain the T>MIC target of 4, 6, and 8 h, respectively. This model was validated internally and externally. CONCLUSION: This study provides insight into the PK/PD indexes of EMB for three different renal function groups and T>MIC targets for different doses. The results could be used to provide optimal-dose suggestions for EMB.

Differential effects of sex on tuberculosis location and severity across the lifespan.

Disparities exist between sexes regarding tuberculosis (TB) incidence, as well as disease severity and outcome. Using a nationwide TB registry database, we explored the impact of sex and age on extrapulmonary TB (EPTB) among all enrolled patients by (1) calculating the female proportion for every age category according to TB-affected locations, (2) calculating the proportions of EPTB stratified by sex according to age, (3) conducting multivariable analysis to examine the impact of sex and age on EPTB likelihood, and (4) assessing the odds of EPTB for female compared to male as reference in every age category. Further, we explored the impact of sex and age on disease severity among pulmonary TB (PTB) patients. Of all the TB patients, 40.1% were female, with a male-to-female ratio of 1.49. The proportion of females was lowest in their fifties, resembling a U-shape. The male-to-female ratios in PTB and EPTB were 1.67 and 1.03, respectively. Compared to men, women were significantly associated with EPTB in their forties, fifties, and sixties. Female patients with PTB had significantly lower odds of having cavitation and positive smear test results in their fifties. Significant differences were found concerning TB location and severity between sexes, especially during reproductive age.

Prediction of Postoperative Lung Function in Lung Cancer Patients Using Machine Learning Models.

BACKGROUND: Surgical resection is the standard treatment for early-stage lung cancer. Since postoperative lung function is related to mortality, predicted postoperative lung function is used to determine the treatment modality. The aim of this study was to evaluate the predictive performance of linear regression and machine learning models. METHODS: We extracted data from the Clinical Data Warehouse and developed three sets: set I, the linear regression model; set II, machine learning models omitting the missing data: and set III, machine learning models imputing the missing data. Six machine learning models, the least absolute shrinkage and selection operator (LASSO), Ridge regression, ElasticNet, Random Forest, eXtreme gradient boosting (XGBoost), and the light gradient boosting machine (LightGBM) were implemented. The forced expiratory volume in 1 second measured 6 months after surgery was defined as the outcome. Five-fold cross-validation was performed for hyperparameter tuning of the machine learning models. The dataset was split into training and test datasets at a 70:30 ratio. Implementation was done after dataset splitting in set III. Predictive performance was evaluated by R2 and mean squared error (MSE) in the three sets. RESULTS: A total of 1,487 patients were included in sets I and III and 896 patients were included in set II. In set I, the R2 value was 0.27 and in set II, LightGBM was the best model with the highest R2 value of 0.5 and the lowest MSE of 154.95. In set III, LightGBM was the best model with the highest R2 value of 0.56 and the lowest MSE of 174.07. CONCLUSION: The LightGBM model showed the best performance in predicting postoperative lung function.