Machine Learning Based Algorithm for the Early Prediction of Postoperative Hypocalcemia Risk After Thyroidectomy.

OBJECTIVE: We used machine learning to develop and validate a multivariable algorithm allowing the accurate and early prediction of postoperative hypocalcemia risk. SUMMARY BACKGROUND: Post-operative hypocalcemia is frequent after total thyroidectomy. An early and accurate individualized prediction of the risk of hypocalcemia could guide the selective prescription of calcium supplementation only to patients most likely to present with hypocalcemia after total thyroidectomy. METHODS: This retrospective study enrolled all patients undergoing total thyroidectomy in a single referral center between November 2019 and march 2022 (derivation cohort) and april 2022 and September 2022 (validation cohort) . The primary study outcome was post-operative hypocalcemia (serum calcium under 80 mg/L). Exposures were multiple clinical and biological variables prospectively collected and analyzed with various machine learning methods, to develop and validate a multi variable prediction algorithm. RESULTS: Among 610 / 118 participants in the derivation / validation cohorts, 100 (16.4%) / 26 (22%) presented post-operative hypocalcemia. The most accurate prediction algorithm was obtained with random forest, and combined intraoperative parathyroid hormone measurements with three clinical variables (age, sex and body mass index), to calculate a postoperative hypocalcemia risk for each patient. After multiple cross validation, the area under the receiver operative characteristic curve was 0.902 (0.829-0.970) in the derivation cohort, and 0.928 (95% CI : 0.86; 0.97) in the validation cohort. Postoperative hypocalcemia risk values of 7% (low threshold) and 20% ( high threshold) had respectively a sensitivity of 92% and a negative likelihood ratio of 0.11, and a specificity of 90% and a positive of 7.6 for the prediction of postoperative hypocalcemia. CONCLUSION: Using machine learning, we developed and validated a simple multivariable model which allowed the accurate prediction of postoperative hypocalcemia. The resulting algorithm could be used at the point of care to guide clinical management after total thyroidectomy.

Survival and Prognostic Factors after Adrenalectomy for Secondary Malignancy: A Combined Analysis of a French University Center Registry (Eurocrine ®) of 307 Patients and a French Nationwide Study of 2,515 Patients.

OBJECTIVE: To provide a nationwide description of postoperative outcomes and analysis of prognostic factors following adrenalectomy for metastases. SUMMARY BACKGROUND DATA: Adrenal glands are a common site of metastases in many malignancies. Diagnosisof adrenal metastases is on the rise, leading to an increasing number of patient candidates for surgery without consensual management. METHODS: We conducted a population-based study between January 2012 and December 2022 using the French national health data system (SNDS) and the Eurocrine® registry (NCT03410394). The first database exhaustively covers all procedures carried out in France, while the second provides more clinical information on procedures and tumor characteristics, based on the experience of 11 specialized centers. RESULTS: From the SNDS, we extracted 2,515 patients who underwent adrenalectomy for secondary malignancy and 307 from the Eurocrine® database. The most common primary malignancies were lung cancer (n=1,203, 47.8%) and renal cancer (n=555, 22.1%). One-year survival was 84.3% (n=2,120). Thirty-day mortality and morbidity rates were, respectively, 1.3% (n=32) and 29.9% (n=753, including planned ICU stays). Radiotherapy within the year before adrenalectomy was significantly associated with higher 30-day major complication rates (P=0.039). In the Eurocrine® database, the proportion of laparoscopic procedures reached 85.3% without impairing resection completeness (R0: 92.9%). Factors associated with poor overall survival were presence of extra-adrenal metastases (HR=0.64; P=0.031) and incomplete resection (≥R1; HR=0.41; P=0.015). CONCLUSION: The number of patients who can receive local treatment for adrenal metastases is rising, and adrenalectomy is more often minimally invasive and has a low morbidity rate. Subsequent research should evaluate which patients would benefit from adrenal surgery.

Genetic Evidence of Causal Relation Between Intestinal Glucose Absorption and Early Postprandial Glucose Response: A Mendelian Randomization Study.

The postprandial glucose response is an independent risk factor for type 2 diabetes. Observationally, early glucose response after an oral glucose challenge has been linked to intestinal glucose absorption, largely influenced by the expression of sodium-glucose cotransporter 1 (SGLT1). This study uses Mendelian randomization (MR) to estimate the causal effect of intestinal SGLT1 expression on early glucose response. Involving 1,547 subjects with class II/III obesity from the Atlas Biologique de l'Obésité Sévère cohort, the study uses SGLT1 genotyping, oral glucose tolerance tests, and jejunal biopsies to measure SGLT1 expression. A loss-of-function SGLT1 haplotype serves as the instrumental variable, with intestinal SGLT1 expression as the exposure and the change in 30-min postload glycemia from fasting glycemia (Δ30 glucose) as the outcome. Results show that 12.8% of the 1,342 genotyped patients carried the SGLT1 loss-of-function haplotype, associated with a mean Δ30 glucose reduction of -0.41 mmol/L and a significant decrease in intestinal SGLT1 expression. The observational study links a 1-SD decrease in SGLT1 expression to a Δ30 glucose reduction of -0.097 mmol/L. MR analysis parallels these findings, associating a statistically significant reduction in genetically instrumented intestinal SGLT1 expression with a Δ30 glucose decrease of -0.353. In conclusion, the MR analysis provides genetic evidence that reducing intestinal SGLT1 expression causally lowers early postload glucose response. This finding has a potential translational impact on managing early glucose response to prevent or treat type 2 diabetes.

Performance of non-invasive tests for liver fibrosis resolution after bariatric surgery.

BACKGROUND & AIMS: The value of non-invasive tests for monitoring the resolution of significant liver fibrosis after treatment is poorly investigated. We compared the performances of six non-invasive tests to predict the resolution of significant fibrosis after bariatric surgery. METHODS: Participants were individuals with obesity submitted to needle liver biopsy at the time of bariatric surgery, and 12 and/or 60 months after surgery. We calculated the fibrosis-4 index (FIB-4), NAFLD fibrosis score (NFS), AST to platelet ratio index (APRI), Hepatic fibrosis score (HFS), Fibrotic NASH index (FNI), and Liver risk score (LRS) at each time point, and compared their performances for predicting significant fibrosis (F ≥ 2) and its resolution following surgery. RESULTS: At baseline, 2436 patients had liver biopsy, including 261 (10.7 %) with significant fibrosis. Overall, 672 patients had pre- and post-operative biopsies (564 at M12 and 328 at M60). The fibrosis stage decreased at M12 and M60 (p < 0.001 vs M0). Resolution of significant fibrosis occurred in 58/121 (47.9 %) at M12 and 32/50 (64 %) at M60. The mean value of all tests decreased after surgery, except for FIB-4. Performances for predicting fibrosis resolution was higher at M60 than at M12 for all tests, and maximal at M60 for FNI and LRS: area under the curve 0.843 (95%CI 0.71-0.95) and 0.92 (95%CI 0.84-1.00); positive likelihood ratio 3.75 (95 % CI 1.33-10.59) and 4.58 (95 % CI 1.65-12.70), respectively. CONCLUSIONS: Results showed the value and limits of non-invasive tests for monitoring the evolution of liver fibrosis after an intervention. Following bariatric surgery, the best performances to predict the resolution of significant fibrosis were observed at M60 with tests combining liver and metabolic traits, namely FNI and LRS.