The Lung Cancer Prediction Model "Stress Test": Assessment of Models' Performance in a High-Risk Prospective Pulmonary Nodule Cohort.

BACKGROUND: Pulmonary nodules represent a growing health care burden because of delayed diagnosis of malignant lesions and overtesting for benign processes. Clinical prediction models were developed to inform physician assessment of pretest probability of nodule malignancy but have not been validated in a high-risk cohort of nodules for which biopsy was ultimately performed. RESEARCH QUESTION: Do guideline-recommended prediction models sufficiently discriminate between benign and malignant nodules when applied to cases referred for biopsy by navigational bronchoscopy? STUDY DESIGN AND METHODS: We assembled a prospective cohort of 322 indeterminate pulmonary nodules in 282 patients referred to a tertiary medical center for diagnostic navigational bronchoscopy between 2017 and 2019. We calculated the probability of malignancy for each nodule using the Brock model, Mayo Clinic model, and Veterans Affairs (VA) model. On a subset of 168 patients who also had PET-CT scans before biopsy, we also calculated the probability of malignancy using the Herder model. The performance of the models was evaluated by calculating the area under the receiver operating characteristic curves (AUCs) for each model. RESULTS: The study cohort contained 185 malignant and 137 benign nodules (57% prevalence of malignancy). The malignant and benign cohorts were similar in terms of size, with a median longest diameter for benign and malignant nodules of 15 and 16 mm, respectively. The Brock model, Mayo Clinic model, and VA model showed similar performance in the entire cohort (Brock AUC, 0.70; 95% CI, 0.64-0.76; Mayo Clinic AUC, 0.70; 95% CI, 0.64-0.76; VA AUC, 0.67; 95% CI, 0.62-0.74). For 168 nodules with available PET-CT scans, the Herder model had an AUC of 0.77 (95% CI, 0.68-0.85). INTERPRETATION: Currently available clinical models provide insufficient discrimination between benign and malignant nodules in the common clinical scenario in which a patient is being referred for biopsy, especially when PET-CT scan information is not available.

Revolutionizing Healthcare with ChatGPT: An Early Exploration of an AI Language Model's Impact on Medicine at Large and its Role in Pediatric Surgery.

BACKGROUND: ChatGPT, a natural language processing model, has shown great promise in revolutionizing the field of medicine. This paper presents a comprehensive evaluation of the transformative potential of OpenAI's ChatGPT on healthcare and scientific research, with an exploration on its prospective capacity to impact the field of pediatric surgery. METHODS: Through an extensive review of the literature, we illuminate ChatGPT's applications in clinical healthcare and medical research while presenting the ethical considerations surrounding its use. RESULTS: Our review reveals the exciting work done so far evaluating the numerous potential uses of ChatGPT in clinical medicine and medical research, but it also shows that significant research and advancements in natural language processing models are still needed. CONCLUSION: ChatGPT has immense promise in transforming how we provide healthcare and how we conduct research. Currently, further robust research on the safety, effectiveness, and ethical considerations of ChatGPT is greatly needed. LEVEL OF STUDY: V.

Short-term outcomes of robotic-assisted transthoracic diaphragmatic plication.

Background: Patients who are symptomatic from diaphragmatic dysfunction may benefit from diaphragmatic plication. We recently modified our plication approach from open thoracotomy to robotic transthoracic. We report our short-term outcomes. Methods: We conducted a single-institution retrospective review of all patients who underwent transthoracic plications from 2018, when we began using the robotic approach, to 2022. The primary outcome was short-term recurrence of diaphragm elevation with symptoms noted before or during the first planned postoperative visit. We also compared proportions of short-term recurrences in patients that underwent plication with extracorporeal knot-tying device alone versus those that used intracorporeal instrument tying (alone or supplemental). Secondary outcomes included subjective postoperative improvement of dyspnea at follow-up visit and by postoperative patient questionnaire, chest tube duration, length of stay (LOS), 30-day readmission, operative time, estimated blood loss (EBL), intraoperative complications, and perioperative complications. Results: Forty-one patients underwent robotic-assisted transthoracic plication. Four patients experienced recurrent diaphragm elevation with symptoms before or during their first routine postoperative visit, occurring on POD 6, 10, 37, and 38. All four recurrences occurred in patients whose plications were performed with the extracorporeal knot-tying device without supplemental intracorporeal instrument tying. Proportion of recurrences in the group that used extracorporeal knot-tying device alone was significantly greater than the recurrences in the group that used intracorporeal instrument tying (alone or supplemental) (P=0.016). The majority (36/41) reported clinical improvement postoperatively and 85% of questionnaire respondents also agreed they would recommend the surgery to others with similar condition. The median LOS and of chest tube duration were 3 days and 2 days, respectively. There were two patients with 30-day readmissions. Three patients developed postoperative pleural effusion necessitating thoracenteses and 8 patients (20%) had postoperative complications. No mortalities were observed. Conclusions: While our study shows the overall acceptable safety and favorable outcomes in patients undergoing robotic-assisted transthoracic diaphragmatic plications, the incidence of short-term recurrences and its association with the use of extracorporeally knot-tying device alone in diaphragm plication warrant further investigation.

Longitudinal lung cancer prediction convolutional neural network model improves the classification of indeterminate pulmonary nodules.

A deep learning model (LCP CNN) for the stratification of indeterminate pulmonary nodules (IPNs) demonstrated better discrimination than commonly used clinical prediction models. However, the LCP CNN score is based on a single timepoint that ignores longitudinal information when prior imaging studies are available. Clinically, IPNs are often followed over time and temporal trends in nodule size or morphology inform management. In this study we investigated whether the change in LCP CNN scores over time was different between benign and malignant nodules. This study used a prospective-specimen collection, retrospective-blinded-evaluation (PRoBE) design. Subjects with incidentally or screening detected IPNs 6-30 mm in diameter with at least 3 consecutive CT scans prior to diagnosis (slice thickness ≤ 1.5 mm) with the same nodule present were included. Disease outcome was adjudicated by biopsy-proven malignancy, biopsy-proven benign disease and absence of growth on at least 2-year imaging follow-up. Lung nodules were analyzed using the Optellum LCP CNN model. Investigators performing image analysis were blinded to all clinical data. The LCP CNN score was determined for 48 benign and 32 malignant nodules. There was no significant difference in the initial LCP CNN score between benign and malignant nodules. Overall, the LCP CNN scores of benign nodules remained relatively stable over time while that of malignant nodules continued to increase over time. The difference in these two trends was statistically significant. We also developed a joint model that incorporates longitudinal LCP CNN scores to predict future probability of cancer. Malignant and benign nodules appear to have distinctive trends in LCP CNN score over time. This suggests that longitudinal modeling may improve radiomic prediction of lung cancer over current models. Additional studies are needed to validate these early findings.

Expansion coverage and preferential utilization of cancer surgery among racial and ethnic minorities and low-income groups.

BACKGROUND: The Affordable Care Act Medicaid expansion demonstrated inconsistent effects on cancer surgery utilization rates among racial and ethnic minorities and low-income Americans. This quasi-experimental study examines whether Medicaid expansion differentially increased the utilization of surgical cancer care for low-income groups and racial minorities in states that expanded their Medicaid programs. METHODS: A cohort of more than 81,000 patients 18 to 64 years of age who underwent cancer surgery were examined in Medicaid expansion versus nonexpansion states. This evaluation utilized merged data from the State Inpatient Database, American Hospital Association, and the Area Resource File for the years 2012 to 2015. Poisson interrupted time series analysis were performed to examine the impact of Medicaid expansion on the utilization of cancer surgery for the uninsured overall, low-income persons, and racial minorities, adjusting for age, sex, Elixhauser comorbidity score, population-level characteristics, and provider-level characteristics. RESULTS: For persons from low-income ZIP codes, Medicaid expansion was associated with an immediate 24% increase in utilization (P = .002) relative to no significant change in nonexpansion states. No significant trends, however, were observed after the Affordable Care Act expansion for racial and ethnic minorities in expansion versus nonexpansion states. CONCLUSION: Medicaid expansion was associated with greater utilization of cancer surgery by low-income Americans but provided no preferential effects for racial minorities in expansion states. Beyond the availability of coverage, these findings highlight the need for additional investigation to uncover other factors that contribute to race-ethnic disparities in surgical cancer care.

Affordable Care Act's Medicaid Expansion and Use of Regionalized Surgery at High-Volume Hospitals.

BACKGROUND: The Affordable Care Act (ACA)'s Medicaid expansion has increased access to surgical care overall. Whether it was associated with reduced disparities in use of regionalized surgery at high-volume hospitals (HVH) remains unknown. Quasi-experimental evaluations of this expansion were performed to examine the use of regionalized surgery at HVH among racial/ethnic minorities and low-income populations. STUDY DESIGN: Data from State Inpatient Databases (2012 to 2014), the American Hospital Association Annual Survey Database, and the Area Resource File from Health Resources and Services Administration, were used to examine 166,558 nonelderly (ages 18 to 64) adults at 468 hospitals, who underwent 1 of 4 regionalized surgical procedures in 3 expansion (KY, MD, NJ) and 2 nonexpansion states (NC, FL). Thresholds of HVH were defined using the top quintile of visits per year. Interrupted time series were performed to measure the impact of expansion on use rates of regionalized surgery at HVH overall, by race/ethnicity, and by income. RESULTS: Overall, ACA's expansion was not associated with accelerated use rates of regionalized surgical procedures at HVH (odds ratio [OR] 1.016, p = 0.297). Disparities in use of regionalized surgical procedures at HVH among ethnic/racial minorities and low-income populations were unchanged; minority vs white (OR 1.034 p = 0.100); low-income vs high-income (OR 1.034, p = 0.122). CONCLUSIONS: Early findings from ACA's Medicaid expansion revealed no impact on the use rates of regionalized surgery at HVH overall or on disparities among vulnerable populations. Although these results need ongoing evaluation, they highlight potential limitations in ACA's expansion in reducing disparities in use of regionalized surgical care.

The Affordable Care Act's Medicaid expansion and utilization of discretionary vs. non-discretionary inpatient surgery.

BACKGROUND: While pre-Affordable Care Act expansions in Medicaid eligibility led to increased utilization of elective inpatient procedures, the impact of the Affordable Care Act on such preference-sensitive procedures (also known as discretionary procedures) versus time-sensitive non-discretionary procedures remains unknown. As such, we performed a hospital-level quasi-experimental evaluation to measure the differential effects of the Affordable Care Act's Medicaid expansion on utilization of discretionary procedures versus non-discretionary procedures. METHODS: The State Inpatient Database (2012-2014) yielded 476 hospitals providing selected discretionary procedures or non-discretionary procedures performed on 288,446 non-elderly, adult patients across 3 expansion states and 2 non-expansion control states. Discretionary procedures included non-emergent total knee and hip arthroplasty, while non-discretionary procedures included nine cancer surgeries. Mixed Poisson interrupted time series analyses were performed to determine the impact of the Affordable Care Act's Medicaid expansion on the number of discretionary procedures versus non-discretionary procedures provided among non-privately insured patients (Medicaid and uninsured patients) and privately insured patients. RESULTS: Analysis of the number of non-privately insured procedures showed an increase in discretionary procedures of +15.1% (IRR 1.15, 95% CI:1.11-1.19) vs -4.0% (IRR 0.96, 95% CI:0.94-0.99) and non-discretionary procedures of +4.1% (IRR 1.04, 95% CI:1.0-1.1) vs -5.3% (IRR 0.95, 95% CI:0.93-0.97) in expansion states compared to non-expansion states, respectively. Analysis of privately insured procedures showed no statistically meaningful change in discretionary procedures or non-discretionary procedures in either expansion or non-expansion states. CONCLUSION: In this multi-state evaluation, the Affordable Care Act's Medicaid expansion preferentially increased utilization of discretionary procedures versus non-discretionary procedures in expansion states compared to non-expansion states among non-privately insured patients. These preliminary findings suggest that increased Medicaid coverage may have contributed to the increased use of inpatient surgery for discretionary procedures.

Medicaid Expansion and Disparity Reduction in Surgical Cancer Care at High-Quality Hospitals.

BACKGROUND: The Affordable Care Act's Medicaid expansion has been heavily debated due to skepticism about Medicaid's ability to provide high-quality care. Particularly, little is known about whether Medicaid expansion improves access to surgical cancer care at high-quality hospitals. To address this question, we examined the effects of the 2001 New York Medicaid expansion, the largest in the pre-Affordable Care Act era, on this disparity measure. STUDY DESIGN: We identified 67,685 nonelderly adults from the New York State Inpatient Database who underwent select cancer resections. High-quality hospitals were defined as high-volume or low-mortality hospitals. Disparity was defined as model-adjusted difference in percentage of patients receiving operations at high-quality hospitals by insurance type (Medicaid/uninsured vs privately insured) or by race (African American vs white). Levels of disparity were calculated quarterly for each comparison pair and then analyzed using interrupted time series to evaluate the impact of Medicaid expansion. RESULTS: Disparity in access to high-volume hospitals by insurance type was reduced by 0.97 percentage points per quarter after Medicaid expansion (p < 0.0001). Medicaid/uninsured beneficiaries had similar access to low-mortality hospitals as the privately insured; no significant change was detected around expansion. Conversely, racial disparity increased by 0.87 percentage points per quarter (p < 0.0001) in access to high-volume hospitals and by 0.48 percentage points per quarter (p = 0.005) in access to low-mortality hospitals after Medicaid expansion. CONCLUSIONS: Pre-Affordable Care Act Medicaid expansion reduced the disparity in access to surgical cancer care at high-volume hospitals by payer. However, it was associated with increased racial disparity in access to high-quality hospitals. Addressing racial barriers in access to high-quality hospitals should be prioritized.

Did Pre-Affordable Care Act Medicaid Expansion Increase Access to Surgical Cancer Care?

BACKGROUND: Although the Affordable Care Act (ACA) expanded Medicaid access, it is unknown whether this has led to greater access to complex surgical care. Evidence on the effect of Medicaid expansion on access to surgical cancer care, a proxy for complex care, is sparse. Using New York's 2001 statewide Medicaid expansion as a natural experiment, we investigated how expansion affected use of surgical cancer care among beneficiaries overall and among racial minorities. STUDY DESIGN: From the New York State Inpatient Database (1997 to 2006), we identified 67,685 nonelderly adults (18 to 64 years of age) who underwent cancer surgery. Estimated effects of 2001 Medicaid expansion on access were measured on payer mix, overall use of surgical cancer care, and percent use by racial/ethnic minorities. Measures were calculated quarterly, adjusted for covariates when appropriate, and then analyzed using interrupted time series. RESULTS: The proportion of cancer operations paid by Medicaid increased from 8.9% to 15.1% in the 5 years after the expansion. The percentage of uninsured patients dropped by 21.3% immediately after the expansion (p = 0.01). Although the expansion was associated with a 24-case/year increase in the net Medicaid case volume (p < 0.0001), the overall all-payer net case volume remained unchanged. In addition, the adjusted percentage of ethnic minorities among Medicaid recipients of cancer surgery was unaffected by the expansion. CONCLUSIONS: Pre-ACA Medicaid expansion did not increase the overall use or change the racial composition of beneficiaries of surgical cancer care. However, it successfully shifted the financial burden away from patient/hospital to Medicaid. These results might suggest similar effects in the post-ACA Medicaid expansion.