Clinical Evaluation of an Artificial Intelligence-Based Decision Support System for the Diagnosis and American College of Radiology Thyroid Imaging Reporting and Data System Classification of Thyroid Nodules

Background: This study aimed to evaluate the clinical impact of an artificial intelligence (AI)-based decision support system (DSS), Koios DS, on the analysis of ultrasound imaging and suspicious characteristics for thyroid nodule risk stratification. Methods: A retrospective ultrasound study was conducted on all thyroid nodules with histological findings from June 2021 to December 2022 in a thyroid nodule clinic. The diagnostic performance of ultrasound imaging was evaluated by six readers on the American College of Radiology Thyroid Imaging Reporting and Data System (ACR TI-RADS) before and after the use of the AI-based DSS and by AI itself. Results: A total of 172 patients (83.1% women) with a mean age of 52.3 ± 15.3 years were evaluated. The mean maximum nodular diameter was 2.9 ± 1.2 cm, with 11.0% being differentiated thyroid carcinomas. Among the nodules initially classified as ACR TI-RADS 3 and 4, AI reclassified 81.4% and 24.5% into lower risk categories, respectively. Receiver operating characteristic (ROC) curve analysis was performed to evaluate the diagnostic performance of the readers and the AI-based DSS versus histological diagnosis. There was an increase in the area under the ROC curve (AUROC) after the use of AI (0.776 vs. 0.817, p < 0.001). The AI-based DSS improved the mean sensitivity (Sens) (82.3% vs. 86.5%) and specificity (Spe) (38.3% vs. 54.8%), produced a high negative predictive value (94.5% vs. 96.4%), and increased the positive predictive value (PPV) (14.0% vs. 16.1%) and diagnostic precision (43.0% vs. 49.3%). Based on the ACR TI-RADS score, there was significant improvement in interobserver agreement after the use of AI (r = 0.741 for ultrasound imaging alone vs. 0.981 for ultrasound imaging and the AI-based DSS, p < 0.001). Conclusions: The use of an AI-based DSS was associated with overall improvement in the diagnostic efficacy of ultrasound imaging, based on the AUROC, as well as an increase in Sens, Spe, negative and PPVs, and diagnostic accuracy. There was also a reduction in interobserver variability and an increase in the degree of concordance with the use of AI. AI reclassified more than half of the nodules with intermediate ACR TI-RADS scores into lower risk categories.

Impact of flash glucose monitoring on quality of life and glycaemic control parameters in adults with type 1 diabetes mellitus⋆

INTRODUCTION

Flash glucose monitoring (FGM) improves some glycaemic control variables and quality of life parameters.

OBJECTIVE

Our aim was to evaluate the quality of life and glycaemic control parameters after initiating FGM in patients with type 1 diabetes (DM1) in clinical practice.

MATERIAL AND METHODS

A prospective observational study in DM1 patients that started using FGM between June 2019 and April 2020. We analysed their scores on the Diabetes Quality of Life (DQOL) questionnaire, Diabetes Distress Scale (DDS), Diabetes Treatment Satisfaction Questionnaire (DTSQ) and glycaemic control parameters at baseline and 3 months after the FGM onset.

RESULTS

We recruited 114 patients, 56% male, mean age 37.2 (standard deviation, SD 12.4), with 18.7 (SD 11.5) years of DM1, 24.6% of which used continuous subcutaneous insulin infusion. Differences were observed (baseline vs. 3 months) in the DTSQ score (22 [15.5-27] vs. 25 [22-28], P < 0.001) and in the DQOL score (88 [74-104] vs. 84 [70-101], P = 0.017) but not in the DDS score. HbA1c was 7.8% (SD 1.3) vs. 7.4% (SD 1.1) (P < 0.001), without improvement in other glycaemic control variables, except for the mean number of hypoglycaemic events/14 days: 14 (SD 9) at baseline vs. 11.5 (SD 7) at 3 months (P < 0.001).

CONCLUSIONS

The initiation of FGM, combined with a structured educational programme, was associated with improvement in quality of life and patient satisfaction in DM1 patients. An improvement in HbA1c and a reduction in the number of hypoglycaemia events was observed, but not in the rest of glycaemic control parameters.

Germline mutations of AIP gene in somatotropinomas resistant to somatostatin analogues

OBJECTIVE

Most cases of familial isolated pituitary adenomas with mutated aryl hydrocarbon receptor-interacting protein (AIP:HGNC:358) gene develop somatotropinomas. They are characterised by an aggressive clinical phenotype including early age at diagnosis, large tumours and frequent invasiveness. There is little information on AIP gene mutations' prevalence in isolated somatotropinomas characterised by poor response to somatostatin analogue treatment. The aim of this study was to investigate the prevalence of AIP mutations in non-familial cases of somatotropinomas with poor response to conventional treatment.

DESIGN AND METHODS

Fifty patients with acromegaly (22 males/28 females, age 51±18 years) and 60 controls were included in this study performed at eight University Hospitals in Spain. None had family history of pituitary adenomas or other endocrine tumors. All patients failed to respond to conventional treatment including surgery and somatostatin analogues. Some patients received adjuvant radiotherapy and most cases required pegvisomant (PEG) treatment for normalisation of IGF1. AIP analysis was performed in DNA extracted from peripheral leucocytes, using standardised PCR protocol in which the coding regions of exons 1, 2, 3, 4, 5 and 6 were amplified. Possible deletions/duplications were studied using multiplex ligation-dependent probe amplification.

RESULTS

SEQUENCE CHANGES OF POTENTIAL DIFFERENT SIGNIFICANCE THAT COULD BE CONSIDERED AS MUTATIONS OR VARIATIONS OF UNKNOWN SIGNIFICANCE (VUS) OF THE AIP GENE WERE FOUND IN FOUR PATIENTS (8%). IN TWO CASES, TWO DIFFERENT MUTATIONS PREVIOUSLY DESCRIBED WERE FOUND: p.Arg9Gln and p.Phe269Phe. Two other VUS were also found: c.787+24C>T in intron 5 and c.100-18C>T in intron 1. Age at diagnosis ranged from 21 to 50 years old, and in all patients, the tumor was a macroadenoma depicting IGF1 normalisation under PEG treatment.

CONCLUSIONS

AIP germline mutations show a low, but non-negligible, prevalence in non-familial acromegaly patients with tumors resistant to treatment with somatostatin analogues.