Although machine learning-based prediction models for in-hospital cardiac arrest (IHCA) have been widely investigated, it is unknown whether a model based on vital signs alone (Vitals-Only model) can perform similarly to a model that considers both vital signs and laboratory results (Vitals+Labs model). All adult patients hospitalized in a tertiary care hospital in Japan between October 2011 and October 2018 were included in this study. Random forest models with/without laboratory results (Vitals+Labs model and Vitals-Only model, respectively) were trained and tested using chronologically divided datasets. Both models use patient demographics and eight-hourly vital signs collected within the previous 48 hours. The primary and secondary outcomes were the occurrence of IHCA in the next 8 and 24 hours, respectively. The area under the receiver operating characteristic curve (AUC) was used as a comparative measure. Sensitivity analyses were performed under multiple statistical assumptions. Of 141,111 admitted patients (training data: 83,064, test data: 58,047), 338 had an IHCA (training data: 217, test data: 121) during the study period. The Vitals-Only model and Vitals+Labs model performed comparably when predicting IHCA within the next 8 hours (Vitals-Only model vs Vitals+Labs model, AUC = 0.862 [95% confidence interval (CI): 0.855–0.868] vs 0.872 [95% CI: 0.867–0.878]) and 24 hours (Vitals-Only model vs Vitals+Labs model, AUC = 0.830 [95% CI: 0.825–0.835] vs 0.837 [95% CI: 0.830–0.844]). Both models performed similarly well on medical, surgical, and ward patient data, but did not perform well for intensive care unit patients. In this single-center study, the machine learning model predicted IHCAs with good discrimination. The addition of laboratory values to vital signs did not significantly improve its overall performance.

Background: Overall survival (OS) is the standard endpoint for oncological treatment efficacy, but requires long follow-up. The aim of this study was to evaluate pCR as a surrogate for OS in oesophageal cancer. Methods: An integrated analysis of individual patient data (IPD) from phase III trials comparing perioperative therapies for resectable oesophageal and gastro-oesophageal junction cancer was conducted. Individual-level surrogacy between pCR and OS was assessed using Kendall’s rank correlation coefficient (τ). A τ of 0.8 was considered a threshold for a good surrogate. As no method estimating τ between an ordinal endpoint and OS has been reported, a new method was proposed using the inverse-probability-of-censoring weighted estimator adjusted for tied data. Results: Of 22 eligible trials, 10 provided IPD for 1641 patients, including 624 who received neoadjuvant chemotherapy (NAC; 45 (7.2%) achieved pCR) and 1017 who received neoadjuvant chemoradiotherapy (NACRT; 299 (29.4%) achieved pCR). In the NAC subgroup, patients with pCR had an HR for OS of 0.12 (95% c.i. 0.05 to 0.33), the C-index was 0.54 (95% c.i. 0.52 to 0.56), and τ was 0.256. In the NACRT subgroup, the HR was 0.57 (95% c.i. 0.47 to 0.70), the C-index was 0.56 (95% c.i. 0.54 to 0.58), and τ was 0.174. Hypothetical data suggested that achieving strong surrogacy (τ of 0.8) required an HR of 0.09 (95% c.i. 0.07 to 0.11). Conclusion: Although pCR was correlated with OS, no evidence of individual-level surrogacy with OS was demonstrated, making it inappropriate to consider pCR as a surrogate endpoint for OS in resectable oesophageal cancer.

A precise preoperative tumor monitoring method that reflects tumor burden during neoadjuvant treatment is required to guide individualized perioperative treatment strategies for esophageal squamous cell carcinoma (ESCC). This study examined the clinical significance of preoperative circulating tumor DNA (ctDNA) in the plasma of patients undergoing neoadjuvant chemotherapy (NAC) followed by esophagectomy. Plasma samples were collected longitudinally for ctDNA analysis as well as genomic DNA from primary lesions from patients with histologically confirmed ESCC who received neoadjuvant chemotherapy (NAC) followed by subtotal esophagectomy. Next-generation sequencing was used to identify mutations in both the plasma and primary tumors. We evaluated the relationship between ctDNA alterations and recurrence in patients with locally advanced ESCC. Pretreatment samples from 25 patients (100 %) showed the same mutations in both ctDNA and primary tumors; therefore, they were classified as ctDNA-positive before treatment. In the cohort of 25 patients analyzed, those who tested positive for ctDNA after NAC had a significantly higher risk of recurrence; the 36-month recurrence-free survival rates were 92 % for ctDNA-negative patients and 8 % for ctDNA-positive patients (p < 0.001). Preoperative ctDNA status may be a promising prognostic biomarker that can be assessed before surgery in patients with ESCC who received NAC. Expanded cohort validation will allow for more personalized multidisciplinary treatment approaches for ESCC tailored to ctDNA analysis.

Overall survival is considered as one of the most important endpoints of treatment efficacy but often requires long follow-up. This study aimed to determine the validity of recurrence-free survival as a surrogate endpoint for overall survival in patients with surgically resectable advanced oesophageal squamous cell carcinoma (OSCC). Patients with OSCC who received neoadjuvant cisplatin and 5-fluorouracil, or docetaxel, cisplatin and 5-fluorouracil, at 58 Japanese oesophageal centres certified by the Japan Esophageal Society were reviewed retrospectively. The correlation between recurrence-free and overall survival was assessed using Kendall's τ. The study included 3154 patients. The 5-year overall and recurrence-free survival rates were 56.6 and 47.7% respectively. The primary analysis revealed a strong correlation between recurrence-free and overall survival (Kendall's τ 0.797, 95% c.i. 0.782 to 0.812) at the individual level. Subgroup analysis showed a positive relationship between a more favourable pathological response to neoadjuvant chemotherapy and a higher τ value. In the meta-regression model, the adjusted R² value at the institutional level was 100 (95% c.i. 40.2 to 100)%. The surrogate threshold effect was 0.703. There was a strong correlation between recurrence-free and overall survival in patients with surgically resectable OSCC who underwent neoadjuvant chemotherapy, and this was more pronounced in patients with a better response to neoadjuvant chemotherapy.

Background: Although several oesophageal squamous cell carcinoma (OSCC) studies have reported no definitive overall survival (OS) differences between neoadjuvant chemoradiotherapy (NACRT) and neoadjuvant chemotherapy (NAC), the higher pCR rate with NACRT has been viewed as a potential advantage. Beyond ongoing concerns about the validity of pCR as a surrogate endpoint, it remains uncertain whether survival differs between these modalities among patients with OSCC who achieve pCR. Methods: An integrated analysis of individual patient data (IPD) from phase III trials evaluating perioperative therapies for resectable OSCC was conducted, emphasizing prognostic differences between NAC and NACRT, particularly among patients who achieved pCR. Results: IPD from seven phase III RCTs across six countries included data for 1044 patients with OSCC (83.5% male; mean age of 62.3 years). Of these patients, 605 (58.0%) received NAC and 439 (42.0%) received NACRT, with R0 resection rates of 89.6% versus 84.7% and pCR rates of 6.9% versus 34.2% respectively. Among patients who achieved pCR (192 patients), 5-year OS was 97.5% in the NAC group and 70.4% in the NACRT group, while 5-year recurrence-free survival was 80.8% and 63.7% respectively. Multivariable analysis demonstrated a significant survival advantage for NAC among patients who achieved pCR. Conclusion: Among patients who achieved pCR, postoperative outcomes varied considerably by neoadjuvant treatment modality. The markedly favourable prognosis associated with pCR after NAC suggests that these patients may represent an optimal candidate cohort for future evaluation of surgery-avoidance and watch-and-wait strategies.