An artificial intelligence prediction model outperforms conventional guidelines in predicting lymph node metastasis of T1 colorectal cancer

Background

According to guidelines, a lot of patients with T1 colorectal cancers (CRCs) undergo additional surgery with lymph node dissection after being treated by endoscopic resection (ER) despite the low incidence of lymph node metastasis (LNM).

Aim

The aim of this study was to develop an artificial intelligence (AI) model to more effectively identify T1 CRCs at risk for LNM and reduce the rate of unnecessary additional surgery.

Methods

We retrospectively analyzed 651 patients with T1 CRCs. The patient cohort was randomly divided into a training set (546 patients) and a test set (105 patients) (ratio 5:1), and a classification and regression tree (CART) algorithm was trained on the training set to develop a predictive AI model for LNM. The model used 12 clinicopathological factors to predict positivity or negativity for LNM. To compare the performance of the AI model with the conventional guidelines, the test set was evaluated according to the Japanese Society for Cancer of the Colon and Rectum (JSCCR) and National Comprehensive Cancer Network (NCCN) guidelines. Finally, we tested the performance of the AI model using the test set and compared it with the JSCCR and NCCN guidelines.

Results

The AI model had better predictive performance (AUC=0.960) than the JSCCR (AUC=0.588) and NCCN guidelines (AUC=0.850). The specificity (85.8% vs. 17.5%, p<0.001), balanced accuracy (92.9% vs. 58.7%, p=0.001), and the positive predictive value (36.3% vs. 9.0%, p=0.001) of the AI model were significantly better than those of the JSCCR guidelines and reduced the percentage of the high-risk group for LNM from 83.8% (JSCCR) to 20.9%. The specificity of the AI model was higher than that of the NCCN guidelines (85.8% vs. 82.4%, p=0.557), but there was no significant difference between the two. The sensitivity of the NCCN guidelines was lower than that of our AI model (87.5% vs. 100%, p=0.301), and according to the NCCN guidelines, 1.2% of the 105 test set patients had missed diagnoses.

Conclusion

The AI model has better performance than conventional guidelines for predicting LNM in T1 CRCs and therefore could significantly reduce unnecessary additional surgery.

Posterior Decompression and Fixation for Thoracic Spine Ossification: A 10-Year Follow-Up Study

Ossification of the posterior longitudinal ligament of the thoracic spine (T-OPLL) causes symptoms including leg and back pain, and motor and sensory deficits. This study retrospectively reviewed 32 patients who initially underwent posterior decompression with instrumented fusion (PDF) for T-OPLL between 2001 and 2012, with 20 qualifying for the final analysis after applying exclusion criteria. Exclusions included unknown preoperative neurological findings, follow-up less than 10 years, or prior spinal surgeries at other levels. Outcomes were assessed using the Japanese Orthopedic Association (JOA) score, recovery rate, and kyphotic angle. The average preoperative JOA score of 3.6 improved to 7.4 at 1 year post-surgery and remained at 7.4 at 10 years, with a recovery rate of 52%. The kyphotic angle at T4-12 increased from 26 degrees preoperatively to 29 degrees postoperatively and to 37 degrees at 10 years. At the fused levels, the angle remained at 26 degrees immediately post-operation and increased to 32 degrees at 10 years. Forty percent of patients required additional surgery, primarily for conditions related to cervical OPLL, such as myelopathy, or lumbar OPLL, such as radiculopathy, or cauda equina syndrome. In conclusion, PDF effectively reduces T-OPLL symptoms over the long term, but the high rate of additional surgeries calls for careful patient follow-up.

Long-term outcomes of additional surgery versus non-gastrectomy treatment for early gastric cancer after non-curative endoscopic submucosal dissection: a meta-analysis

BACKGROUND

Endoscopic resection is increasingly used in the treatment for early gastric cancer (EGC); however, about 15% of endoscopic submucosal dissection (ESD) cases report non-curative resection. The efficacy of different remedial interventions after non-curative ESD for EGC remains controversial. This meta-analysis aimed to compare the long-term outcomes of additional surgery and non-gastrectomy treatment for EGC patients who underwent non-curative ESD.

METHODS

All relevant studies published up to October 2021 were systematically searched in the PubMed, Web of Science, and Embase databases. The medical subject headings terms "early gastric cancer," "gastrectomy," "endoscopic submucosal dissection," and their related free keywords were used to search relevant articles without restrictions on regions, publication types, or languages. The Newcastle-Ottawa Quality Assessment Scale was used to evaluate the quality of the included studies. Odds ratios (ORs) with 95% confidence intervals (CIs) of 5-year overall survival (OS), disease-specific survival (DSS), disease-free survival (DFS) and hazard ratios (HRs) with 95% CIs of OS were calculated using a random- or fixed-effects model.

RESULTS

This meta-analysis included 17 retrospective cohort studies with 5880 patients, of whom 3167 underwent additional surgery and 2713 underwent non-gastrectomy. We found that patients receiving additional gastrectomy had better 5-year OS (OR = 3.63, 95% CI = 3.05-4.31), DSS (OR = 3.22, 95% CI = 2.22-4.66), and DFS (OR = 4.39, 95% CI = 1.78-10.82) outcomes than those receiving non-gastrectomy treatments. The pooled HR also showed that gastrectomy following non-curative ESD significantly improved OS (HR = 0.40, 95% CI = 0.33-0.48). In addition, elderly patients benefited from additional surgery in consideration of the 5-year OS (HR = 0.54, 95% CI = 0.41-0.72).

CONCLUSIONS

Compared with non-gastrectomy treatments, additional surgery offered better long-term survival outcomes for patients with EGC who underwent non-curative ESD.

Nomogram as a novel predictive tool for lymph node metastasis in T1 colorectal cancer treated with endoscopic resection: A nationwide, multicenter study

BACKGROUND AND AIMS

Since 2009, the Japanese Society for Cancer of the Colon and Rectum (JSCCR) guidelines have been recommending tumor budding and submucosal invasion depth, in addition to lymphovascular invasion and tumor grade, to be included as risk factors for lymph node metastasis (LNM) in T1 colorectal carcinoma (CRC) patients. In this study, a novel nomogram was developed and validated using large-scale real-world data, including the JSCCR risk factors, to accurately evaluate the risk of LNM in T1 CRC.

METHODS

Data from 4,673 T1 CRC patients treated at 27 high-volume institutions between 2009 and 2016 were analyzed for LNM risk. To prepare a nonrandom split sample, the total cohort was divided into development and validation cohorts. Pathological findings were extracted from the medical records of each participating institution. The discrimination ability was measured using the concordance index, and the variability in each prediction was evaluated using calibration curves.

RESULTS

Six independent risk factors for LNM, including submucosal invasion depth and tumor budding, were identified in the development cohort and entered into a nomogram. The concordance index was 0.784 for the clinical calculator in the development cohort and 0.790 in the validation cohort. The calibration curve approached the 45-degree diagonal in the validation cohort.

CONCLUSIONS

This is the first nomogram to include submucosal invasion depth and tumor budding for use in routine pathological diagnosis based on data from a nationwide multi-institutional study. With this nomogram developed with real-world data decision-making for an appropriate treatment strategy for T1 CRC should improve.

Impact of preceding noncurative endoscopic submucosal dissection on patients with early gastric cancer who undergo subsequent surgery: a meta-analysis

BACKGROUND

The influence of preceding noncurative endoscopic submucosal dissection (ESD) on the efficacy of subsequent surgery is still controversial among early gastric cancer (EGC), especially for laparoscopic gastrectomy. The present meta-analysis was conducted to compare clinical outcomes between patients with EGC who underwent noncurative ESD before surgery (ESD group) and those who underwent direct surgery (non-ESD group).

METHODS

Related databases were searched, and articles comparing differences between ESD and non-ESD groups were included for meta-analysis.

RESULTS

Ten retrospective studies with 3465 participants were included in this meta-analysis. Compared with the non-ESD group, the ESD group was older and had more males, smaller tumors, more differentiated tumors and a higher proportion of pT1b, a shorter operation time, fewer dissected lymph nodes, a lower rate of positive lymph nodes and a lower rate of D2 dissection. There was no significant difference in intraoperative blood loss, postoperative complication rate, postoperative hospital stay or long-term prognosis, etc.

CONCLUSION

Preceding noncurative ESD has no negative impact on the short- and long-term results of additional gastrectomy (open surgery or laparoscopic surgery).

Significance of Additional Gastrectomy Including Endoscopic Submucosal Dissection Scar for Gastric Cancer

BACKGROUND/AIM

The aim of the study was to evaluate the necessity of gastrectomy including endoscopic submucosal dissection (ESD) scar with margin-negative early gastric cancer (EGC).

PATIENTS AND METHODS

We analyzed 83 patients with EGC who received additional gastrectomy after non-curative ESD and evaluated the risk factors for residual cancer (RC) and lymph node (LN) metastasis.

RESULTS

In addition to positive ESD margin, ulceration was a risk factor for RC. Among cases with deep submucosal invasion (sm), 3 were diagnosed as having negative margins in ESD specimens, but the surgical specimens were positive for cancer. The rate of LN metastasis was 12.0%. There was no significant difference in LN metastasis between tumor characteristics.

CONCLUSION

LN dissection is recommended after non-curative ESD. Gastrectomy including the ESD scar should be performed not only for cases with positive margin in ESD, but also for cases with invasion deeper than sm2, even though the margin is negative.