Relationship between intraoperative measured parameters of parathyroid gland and pathological patterns in patients with secondary hyperparathyroidism

Development and Validation of an Explainable Machine Learning Model for Identification of Hyper-Functioning Parathyroid Glands from High-Frequency Ultrasonographic Images

OBJECTIVE

To develop and validate a machine learning (ML) model based on high-frequency ultrasound (HFUS) images with the aim to identify the functional status of parathyroid glands (PTGs) in secondary hyper-parathyroidism (SHPT) patients.

METHODS

This retrospective study enrolled 60 SHPT patients (27 female, 33 male; mean age: 51.2 years) with 184 PTGs detected from February 2016 to June 2022. All enrollments underwent single-photon emission computed tomography/computed tomography and contrast-enhanced ultrasound examinations. The PTGs were randomly divided into training (n = 147) and testing datasets (n = 37). Four effective ML classifiers were used and combined models incorporating multi-modal HFUS visual signs and radiomics features was constructed based on the optimal classifier. Model performance was compared in terms of discrimination, calibration and clinical utility. The Shapley additive explanation method was used to explain and visualize the main predictors of the optimal model.

RESULTS

This model, using a random forest classifier algorithm, outperformed other classifiers. Based on optimal classifier features, the model constructed from ultrasound visual and ML features achieved a favorable performance in the prediction of hyper-functioning PTGs. Compared with the traditional visual model, the ultrasound-based ML model achieved significant (p = 0.03) improvement (area under the curve: 0.859 vs. 0.629) and higher sensitivity (100.0% vs. 94.1%) and accuracy (86.5% vs. 67.6%). Among the predictors attributed to model development, large size and high echogenic heterogeneity of PTGs in ultrasonographic images were more often associated with high risk of hyper-functioning PTGs.

CONCLUSION

The ultrasound-based ML model for identifying hyper-functioning PTGs in SHPT patients showed good performance and interpretability using high-frequency ultrasonographic images, which may facilitate clinical management.

Treatment for secondary hyperparathyroidism focusing on parathyroidectomy

Secondary hyperparathyroidism (SHPT) is a major problem for patients with chronic kidney disease and can cause many complications, including osteodystrophy, fractures, and cardiovascular diseases. Treatment for SHPT has changed radically with the advent of calcimimetics; however, parathyroidectomy (PTx) remains one of the most important treatments. For successful PTx, removing all parathyroid glands (PTGs) without complications is essential to prevent persistent or recurrent SHPT. Preoperative imaging studies for the localization of PTGs, such as ultrasonography, computed tomography, and 99mTc-Sestamibi scintigraphy, and intraoperative evaluation methods to confirm the removal of all PTGs, including, intraoperative intact parathyroid hormone monitoring and frozen section diagnosis, are useful. Functional and anatomical preservation of the recurrent laryngeal nerves can be confirmed via intraoperative nerve monitoring. Total or subtotal PTx with or without transcervical thymectomy and autotransplantation can also be performed. Appropriate operative methods for PTx should be selected according to the patients' need for kidney transplantation. In the case of persistent or recurrent SHPT after the initial PTx, localization of the causative PTGs with autotransplantation is challenging as causative PTGs can exist in the neck, mediastinum, or autotransplanted areas. Additionally, the efficacy and cost-effectiveness of calcimimetics and PTx are increasingly being discussed. In this review, medical and surgical treatments for SHPT are described.

Inhibition of autophagy with Chloroquine enhanced apoptosis induced by 5-aminolevulinic acid-photodynamic therapy in secondary hyperparathyroidism primary cells and organoids

Secondary hyperparathyroidism (SHPT), the most common complication in the later stage of chronic kidney disease (CKD), seriously affects quality of life and the survival time of patients. At present, the conventional drugs and surgical methods still cannot fully meet the needs of clinical treatment. It is quite significant to develop effective and minimally invasive treatment methods. 5-Aminolevulinic acid-mediated photodynamic therapy (5-ALA-PDT), an alternative treatment relying on light irradiation, photosensitizer, and oxygen to produce a series of cytotoxic effects on tissue, is a promising technique for treating SHPT. We have successfully cultivated SHPT primary cells and organoids, and further proved that the amount of 5-ALA transformed into protoporphyrin IX in a time- and concentration-dependent manner. Also, 5-ALA-PDT exerted a cytotoxic effect on both primary cells and organoids by the cell counting kit (CCK-8) assay. Mechanically, 5-ALA-PDT increased the number of autophagosomes, and autophagy- and apoptosis-related proteins were upregulated markedly by western-blotting. The autophagy inhibitor Chloroquine (CQ) significantly increased the proportion of apoptotic cells, while the autophagy inducer rapamycin decreased the inhibitory ability of 5-ALA-PDT in SHPT primary cells. In brief, 5-ALA-PDT exhibits a phototoxic effect on SHPT primary cells and organoids. Autophagy and apoptosis are involved in the mechanism, and autophagy plays a role in promoting survival and inhibiting apoptosis. Therefore, the use of autophagy inhibitors can increase the sensitivity of SHPT cells and organoids treated with 5-ALA-PDT.