Penalized deep partially linear cox models with application to CT scans of lung cancer patients.

Lung cancer is a leading cause of cancer mortality globally, highlighting the importance of understanding its mortality risks to design effective patient-centered therapies. The National Lung Screening Trial (NLST) employed computed tomography texture analysis, which provides objective measurements of texture patterns on CT scans, to quantify the mortality risks of lung cancer patients. Partially linear Cox models have gained popularity for survival analysis by dissecting the hazard function into parametric and nonparametric components, allowing for the effective incorporation of both well-established risk factors (such as age and clinical variables) and emerging risk factors (eg, image features) within a unified framework. However, when the dimension of parametric components exceeds the sample size, the task of model fitting becomes formidable, while nonparametric modeling grapples with the curse of dimensionality. We propose a novel Penalized Deep Partially Linear Cox Model (Penalized DPLC), which incorporates the smoothly clipped absolute deviation (SCAD) penalty to select important texture features and employs a deep neural network to estimate the nonparametric component of the model. We prove the convergence and asymptotic properties of the estimator and compare it to other methods through extensive simulation studies, evaluating its performance in risk prediction and feature selection. The proposed method is applied to the NLST study dataset to uncover the effects of key clinical and imaging risk factors on patients' survival. Our findings provide valuable insights into the relationship between these factors and survival outcomes.

Long-term Survival After Lung Cancer Resection in the National Lung Screening Trial.

BACKGROUND: This study sought to evaluate the long-term survival and causes of death after surgery among patients with pathologic stage IA non-small cell lung cancer (NSCLC) in the National Lung Screening Trial (NLST). METHODS: Patients who underwent surgery and who had a diagnosis of pathologic stage IA NSCLC in the NLST were identified for analysis. The 5- and 10-year overall survival and lung cancer-specific survival, stratified by operation type, were evaluated. Among patients who underwent lobectomy, the causes of death and the cumulative incidence of lung cancer death were assessed. RESULTS: A total of 380 patients (n = 329, 86.6% lobectomy; n = 20, 5.3% segmentectomy; n = 31, 8.1% wedge resection) met inclusion criteria. Median follow-up time from the date of surgery was 7.8 years (interquartile range, 4.8-10.7 years). The 10-year overall survival rate was 58.3% (95% CI, 52.4%-63.8%) for lobectomy, 59.9% (95% CI, 33.2%-78.8%) for segmentectomy, and 45.2% (95% CI, 20.8%-66.9%) for wedge resection. The 10-year lung cancer-specific survival rate was 74.3% (95% CI, 68.6%-79.1%) for lobectomy, 81.3% (95% CI, 51.3%-93.8%) for segmentectomy, and 84.8% (95% CI, 64.0%-94.1%) for wedge resection. Lung cancer was the leading cause of death, accounting for 55.8% of deaths after lobectomy. The 10-year cumulative incidence of lung cancer death after lobectomy was 22.5% (95% CI, 18.3%-27.1%). CONCLUSIONS: The 10-year overall survival rate after lobectomy among patients with pathologic stage IA NSCLC in the NLST was 58%. Lung cancer was the leading cause of death, accounting for more than 55% of deaths.

Persistent race- and sex-based disparities in lung cancer screening eligibility.

OBJECTIVE: To evaluate race- and sex-based disparities in lung cancer screening eligibility under the 2013 US Preventive Services Task Force, 2021 US Preventive Services Task Force, and National Comprehensive Cancer Network lung cancer screening guidelines. METHODS: Participants in the Southern Community Cohort Study with a smoking history diagnosed with lung cancer from 2002 to 2021 were identified for analysis. Differences in age at lung cancer diagnosis and smoking characteristics were evaluated among 4 groups: Black men, Black women, White men, and White women. RESULTS: A total of 2011 patients with lung cancer met study inclusion criteria, of whom 968 (48.1%) were women and 1248 (62.1%) were Black. Under the 2013 guideline, Black men with lung cancer were significantly less likely to be eligible for screening when compared with White men with lung cancer (37.7% vs 62.4%; P < .001), and Black women with lung cancer were significantly less likely to be eligible for screening when compared with White women with lung cancer (27.8% vs 56.7%; P < .001). Under the 2021 guideline, 62.6% of Black and 73.8% of White men (P < .001) with lung cancer would have been eligible for screening, resulting in an 11.2 percentage point difference in screening eligibility between Black and White men. Under the 2021 guideline, 50.3% of Black and 74.9% of White (P < .001) women with lung cancer would have been eligible for screening; notably, there remained a 24.6 percentage point difference in screening eligibility between Black and White women. In multivariable-adjusted analysis, under the 2021 USPSTF guideline, Black men with lung cancer had 46% lower odds of being eligible for screening compared with White men with lung cancer (multivariable-adjusted odds ratio [aOR], 0.54; 95% CI, 0.39-0.76; P < .001) and Black women with lung cancer had 66% lower odds of being eligible for screening compared with White women with lung cancer (aOR, 0.34; 95% CI, 0.25-0.46; P < .001). The National Comprehensive Cancer Network guideline increased the proportion of patients with lung cancer eligible for screening in each group. CONCLUSIONS: In this analysis of patients with lung cancer in the Southern Community Cohort Study, there remained a large gap in lung cancer screening eligibility between Black and White men and women under the 2021 US Preventive Services Task Force guideline. Only 50% of Black women and 63% of Black men diagnosed with lung cancer would have qualified for screening.

Recurrence After Complete Resection for Non-Small Cell Lung Cancer in the National Lung Screening Trial.

BACKGROUND: The objective of this study was to evaluate patterns, predictors, and long-term outcomes of recurrent disease after complete resection for early-stage non-small cell lung cancer (NSCLC) using the National Lung Screening Trial (NLST). METHODS: The frequency of recurrence in patients with pathologic stage I-II NSCLC who underwent complete resection (lobectomy or bilobectomy) in the NLST was evaluated. Predictors of increased risk of recurrence were assessed by Fine-Gray competing risks regression. RESULTS: Of the 497 patients meeting study inclusion criteria, 94 experienced a recurrence-a rate of 4.9 (95% CI, 4.0-6.0) per 100 person-years. The 5-year cumulative incidence of recurrence was 20.1% (95% CI, 16.5%-23.9%). Most patients experienced recurrences at distant sites alone (n = 47 [50.0%]) or at both locoregional and distant sites (n = 30 [31.9%]). The median time from resection to recurrence was 18.8 (10.6-30.7) months. The incidence rate of recurrence was significantly lower among patients with lung cancer detected by low-dose computed tomography screening during one of the three screening rounds of the NLST when compared with patients with lung cancer detected by chest radiography screening and patients with lung cancer not detected by any form of screening (ie, those diagnosed after a negative or missed screening exam and those diagnosed during follow-up after the three screening rounds of the NLST were completed) (P < .001). Median survival (from the date of recurrence) of patients with pathologic stage I and stage II disease who had recurrences at locoregional, distant, or both sites was 63.0, 23.1, and 9.8 months and 28.9, 8.7, and 10.2 months, respectively. CONCLUSIONS: In this analysis of NLST participants with completely resected stage I-II NSCLC, the 5-year cumulative incidence of recurrence was 20%. Nearly 82% of recurrences were at distant sites and associated with poor survival.

Incidence, Timing, and Factors Associated With Suicide Among Patients Undergoing Surgery for Cancer in the US.

Importance: The risk and timing of suicide among patients who undergo surgery for cancer remain largely unknown, and, to our knowledge, there are currently no organized programs in place to implement regular suicide screening among this patient population. Objective: To evaluate the incidence, timing, and factors associated with suicide among patients undergoing cancer operations. Design, Setting, and Participants: This retrospective population-based cohort study used data from the Surveillance, Epidemiology, and End Results Program database to examine the incidence of suicide, compared with the general US population, and timing of suicide among patients undergoing surgery for the 15 deadliest cancers in the US from 2000 to 2016. A Fine-Gray competing risks regression model was used to identify factors associated with an increased risk of suicide among patients in the cohort. Data were analyzed from September 2021 to January 2022. Exposures: Surgery for cancer. Main Outcomes and Measures: Incidence, compared with the general US population, timing, and factors associated with suicide after surgery for cancer. Results: From 2000 to 2016, 1 811 397 patients (74.4% female; median [IQR] age, 62.0 [52.0-72.0] years) met study inclusion criteria. Of these patients, 1494 (0.08%) committed suicide after undergoing surgery for cancer. The incidence of suicide, compared with the general US population, was statistically significantly higher among patients undergoing surgery for cancers of the larynx (standardized mortality ratio [SMR], 4.02; 95% CI, 2.67-5.81), oral cavity and pharynx (SMR, 2.43; 95% CI, 1.93-3.03), esophagus (SMR, 2.25; 95% CI, 1.43-3.38), bladder (SMR, 2.09; 95% CI, 1.53-2.78), pancreas (SMR, 2.08; 95% CI, 1.29-3.19), lung (SMR, 1.73; 95% CI, 1.47-2.02), stomach (SMR, 1.70; 95% CI, 1.22-2.31), ovary (SMR, 1.64; 95% CI, 1.13-2.31), brain (SMR, 1.61; 95% CI, 1.12-2.26), and colon and rectum (SMR, 1.28; 95% CI, 1.16-1.40). Approximately 3%, 21%, and 50% of suicides were committed within the first month, first year, and first 3 years after surgery, respectively. Patients who were male, White, and divorced or single were at greatest risk of suicide. Conclusions and Relevance: In this cohort study, the incidence of suicide among patients undergoing cancer operations was statistically significantly elevated compared with the general population, highlighting the need for programs to actively implement regular suicide screening among such patients, especially those whose demographic and tumor characteristics are associated with the highest suicide risk.

A national analysis of open versus minimally invasive thymectomy for stage I-III thymic carcinoma.

OBJECTIVES: The oncological efficacy of minimally invasive thymectomy for thymic carcinoma is not well characterized. We compared overall survival and short-term outcomes between open and minimally invasive surgical (video-assisted thoracoscopic and robotic) approaches using the National Cancer Database. METHODS: Perioperative outcomes and overall survival of patients who underwent open versus minimally invasive thymectomy for Masaoka stage I-III thymic carcinoma from 2010 to 2015 in the National Cancer Database were evaluated using propensity score-matched analysis and multivariable Cox proportional hazards modelling. Outcomes by surgical approach were assessed using an intent-to-treat analysis. RESULTS: Of the 216 thymectomies that were evaluated, 43 (20%) were performed with minimally invasive techniques (22 video-assisted thoracoscopic and 21 robotic). The minimally invasive approach was associated with a shorter median length of stay when compared to the open approach (3 vs 5 days, P < 0.001). In the propensity score-matched analysis of 30 open and 30 minimally invasive thymectomies, the minimally invasive group did not differ significantly in median length of stay (3 vs 4.5 days, P = 0.27), 30-day readmission (P = 0.13), 30-day mortality (P = 0.60), 90-day mortality (P = 0.60), margin positivity (P = 0.39) and 5-year survival (78.6% vs 54.6%, P = 0.15) when compared to the open group. CONCLUSIONS: In this national analysis, minimally invasive thymectomy for stage I-III thymic carcinoma was found to have no significant differences in short-term outcomes and overall survival when compared to open thymectomy.