IntroductionEndocrine system disorders are a serious public health burden and can be caused by deleterious genetic variants in single genes or by the combined effects of multiple variants along with environmental and lifestyle factors.MethodsThe EndoGene database presents the results of next-generation sequencing assays used to genetically profile 5,926 patients who were diagnosed with 450 endocrine and concomitant diseases and were examined and treated at the National Medical Research Center for Endocrinology between November 2017 and January 2024. Among them, 494, 1,785, 692, and 1,941 patients were profiled using four internally developed genetic panels including 220, 250, 376, and 382 genes, respectively, selected based on a literature analysis and clinical recommendations, and 1,245 patients were profiled by whole exome sequencing covering 31,969 genes.Results2,711 genetic variants were reported as clinically relevant by medical geneticists and are presented here along with genomic, technical, and clinical annotations.DiscussionThis publicly accessible database will be useful to those interested in genetics, epidemiology, population statistics, and a better understanding of the molecular basis of endocrine disorders.

Background: Ectopic ACTH syndrome (EAS) is caused by non-pituitary neuroendocrine tumor (NET) that produces adrenocorticotropic hormone (ACTH). Objective: To identify survival predictors and to analyze long-term outcomes in patients with EAS. Methods: Medical records of patients with verified EAS between 1990 and 2024 were analyzed to obtain the initial clinical and biochemical data along with subsequent interventions and survival outcomes. Results: The study included 173 patients (107 women and 66 men), with a median (Q25–Q75) age of 42 years (29; 55). The median follow-up period was 54 months (16; 99) with a maximum of 402 months. Over the observation period, death was registered in 50 (28.9%) cases. The overall 3- and 5-year survival rates were 77 and 70%, respectively. Multivariable analysis revealed the following negative predictive factors for survival: age at diagnosis ≥51 years (hazard ratio (HR) 3.53; 95% confidence interval (CI): 1.67–7.5; P = 0.001), presence of metastases (HR 2.93; 95% CI: 1.35–6.32; P = 0.006), and active hypercortisolism (HR 5.58; 95% CI 1.62–19.24; P = 0.006) along with late night salivary cortisol levels (LNSC) above 130 nmol/L (HR 2.81; 95% CI: 1.30–6.07; P = 0.009). Conclusion: Active hypercortisolism, high LNSC, distant metastases and older age at diagnosis are factors associated with mortality in EAS. As severity of hypercortisolism is the main targetable factors, it should be the focus of intervention and further studies aimed at improving outcomes.

OBJECTIVES:Evaluate how osilodrostat dose and baseline mean urinary free cortisol (mUFC) affect treatment outcomes and provide evidence-based guidance on personalized medical treatment for patients with Cushing's disease. METHODS/DESIGN:Individual-patient data from the Phase II LINC 2 and Phase III LINC 3 and LINC 4 core and extension periods were pooled, excluding periods when patients received placebo (LINC 3 and LINC 4). Outcomes were evaluated in patients with available data across common time points. RESULTS:Two hundred and twenty-nine patients were treated: starting osilodrostat dose 2 mg twice daily, median average dose per patient 6.8 mg/day for a mean of 113.7 weeks (standard deviation 73.1). mUFC control (not exceeding the upper limit of normal) was achieved within 4-12 weeks in most patients and sustained throughout. Median time to first mUFC control was 35 days, longer with increasing baseline mUFC. Most common dose for first mUFC control was 4 mg/day (33.2% of patients; median dose 10 mg/day [range 2-60]). Adverse events (AEs) generally occurred more often during dose titration (baseline to week 12) than long-term treatment (week >12), but could occur at any time. AEs were manageable in most patients; n = 37 (16.2%) discontinued because of AEs. CONCLUSIONS:In this analysis of the largest and longest prospective interventional studies of an adrenal steroidogenesis inhibitor to date, osilodrostat provided rapid and sustained mUFC control, with dose decreases possible over the long term. AE frequency generally decreased over time, with no relationship with osilodrostat dose. Personalized adjustment of osilodrostat dose is important to optimize outcomes for patients with Cushing's disease. CLINICAL TRIAL REGISTRATION NUMBERS:LINC 2 (NCT01331239); LINC 3 (NCT02180217); and LINC 4 (NCT02697734).

Bone Health ECHO (Extension of Community Healthcare Outcomes) is a virtual community of practice that has been connecting healthcare professionals online once weekly for the past 10 years. A key component of each ECHO session is presentation and discussion of patient cases with diagnostic and treatment dilemmas. Here we present two wheelchair-bound female patients aged 47 years (Patient 1) and 34 years (Patient 2), both with type 1 diabetes mellitus (T1DM). They were admitted to our hospital due to multiple fractures and muscle weakness. Since age 8 years, both women suffered from T1DM. Patient 1 had extremely poor glycemic control over the whole period of diabetes with frequent cases of ketoacidosis (glycated hemoglobin [HbA1c] varied 10.0-14.2 %), with multiple end-stage complications of DM including anuria requiring hemodialysis from age 37 years. Patient 2 had minimal DM complications and maintained HbA1c within an individual goal (5.0-6.1 %). Both patients had low fasting phosphate and elevated alkaline phosphatase on laboratory evaluation. In the patient with anuria (Patient 1), after careful evaluation of all possible causes of hypophosphatemia, we found the most likely cause to be the effects of constantly repeated intracellular phosphate depletion due to poorly compensated T1DM. While achieving stable glucose control in hospital care, her phosphate levels gradually returned within the reference range. In the younger patient (Patient 2), tumor-induced osteomalacia (TIO) was diagnosed. After tumor removal her symptoms and laboratory results normalized. These cases illustrate two different causes of hypophosphatemia in patients with similar skeletal presentations in association with T1DM.

Background: Phosphaturic mesenchymal tumours secreting fibroblast growth factor 23 (hereinafter referred to as FGF23+ PMT) are rare neoplasms that can cause hypophosphataemic osteomalacia, owing to excessive FGF23 production. Mast cells (MCs) play a key role in tumour biology by modulating proliferative activity of atypical cells, resistance to innate and acquired immunity, angiogenesis, and metastatic behaviour. However, MCs associated with FGF23+ PMT have not previously been investigated. This study, to our knowledge, is the first to characterise features of the tumour microenvironment through spatial phenotyping of the immune and stromal landscape, together with histotopographic mapping of intercellular MC interactions with other subcellular populations in FGF23+ PMT. Methods: Histochemical staining (haematoxylin and eosin, toluidine blue, Giemsa solution, picro-Mallory protocol, silver impregnation), as well as monoplex and multiplex immunohistochemical staining with spatial phenotyping, were performed to detect atypical FGF23-secreting cells, immune cells (CD3, CD4, CD8, CD14, CD20, CD38, CD68, or CD163), stromal components (CD31, α-SMA, or vimentin), and specific MC proteases (tryptase, chymase, or carboxypeptidase A3). Bioinformatics analysis using artificial intelligence technologies was applied for spatial profiling of MC interactions with tumour, immunocompetent, and stromal cells in the tumour microenvironment. Results: Bioinformatic analysis of the entire tumour histological section, comprising over 70,000 cells stained using monoplex and multiplex immunohistochemical protocols, enabled identification of more than half of the cell population. The most abundant were CD14+ (30.7%), CD163+ (23.2%), and CD31+ (17.9%) cells. Tumour-associated MCs accounted for 0.7% of the total pool of immunopositive cells and included both mucosal and connective tissue subpopulations, predominantly of the tryptase + chymase-CPA3-specific protease phenotype. This pattern reflected combined multidirectional morphogenetic processes in the patient’s FGF23+ PMT. More than 50% of MCs were colocalized with neighbouring cells of the tumour microenvironment within 20 μm, most frequently with monocytes (CD14+CD68+), M2 macrophages (CD68+CD163+), and endothelial cells (CD31+). In contrast, colocalization with atypical FGF23-secreting cells was rare, indicating minimal direct effects on tumour cell activity. Interaction with T lymphocytes, including CD8+, was also infrequent, excluding their activation and the development of antitumour effects. Mapping of MC histotopography validated the hypothesis of their inductive role in monocyte differentiation into M2 macrophages and probable polarisation of macrophages from M1 into M2, thereby contributing to slow tumour growth. MCs were further involved in extracellular matrix remodelling and participated in the formation of pro-osteogenic niches within the FGF23+ PMT microenvironment, leading to pathological osteoid development. Conclusions: This study demonstrated active MC participation in the evolution of the FGF23+ PMT microenvironment. The findings may be applied in translational medicine to develop novel algorithms for personalised therapy in patients with FGF23-secreting tumours, offering an alternative when surgical removal of the tumour is not feasible.

Bone Health ECHO (Extension of Community Healthcare Outcomes) is a growing family of online educational programs. Its mission is to enhance delivery of best practice skeletal healthcare worldwide. Each program typically consists of a didactic lecture and discussion of clinical cases with diagnostic and treatment dilemmas. Here we present a Bone Health ECHO case of a 39-year-old man who has received hemodialysis for 12 years. This case is characterized by the development of chronic kidney disease - mineral and bone disorder (CKD-MBD) which was managed using conservative treatment to maintain phosphate and calcium levels within the reference range in spite of severe secondary hyperparathyroidism, after the patient declined parathyroidectomy. Although this patient had multiple vertebral fractures with height loss, his bone mineral density was higher than expected for his age and gradually increased over the period of observation. Whole-exome sequencing showed a heterozygous, likely pathogenic variant in LEMD3 gene (13 exon HG38, chr12:65246271dup, с.2682dup in a heterozygous state), which may explain the high bone mass phenotype. As a result of the ECHO presentation, we decided that successful treatment of CKD-MBD would be the most effective approach to managing his bone fragility. His high bone mass phenotype was most likely associated with LEMD3 gene variant. This patient does not require any specific anti-osteoporotic treatment at this time; however, he is likely to benefit from parathyroid surgery.

Disclosure: S.R. Chacko: None. C.A. Villavicencio Torres: None. K. Yu: None. S.G. Waguespack: None. L. Lu: None. Z. Belaya: None. T. Bandgar: None. A. Sada: None. O. Ragnarsson: None. B. Altieri: None. A. Newman: None. P. Vibhatavata: None. M. Tóth: None. E.V. Varlamov: None. C. Badiu: None. A. Paissan: None. M. St-Jean: None. H. Falhammar: None. N. Imamudeen: None. L. Haberbosch: None. M. Bobrowicz: None. A. Tabarin: None. R. Shah: None. M.R. Gadelha: None. A. Peersen: None. W.F. Young: None. J. Kaplan: None. J. Varghese: None. M.A. Habra: None. O. Golounina: None. G.A. Melnichenko: None. A.R. Lila: None. C. Yamichannaiah: None. I. Bancos: None. Context: Cushing syndrome (CS) due to ectopic ACTH secretion (EAS) is a rare condition, associated with severe hypercortisolism and consequent morbidity and mortality. Its varied and often emergent presentation make diagnosis and treatment challenging. Objectives: 1.Characterize clinical and biochemical presentation of EAS. 2.Describe the scope of hypercortisolism-related complications, overall and CS-specific mortality. 3.Identify factors associated with CS-specific mortality. Methods: We conducted a multicenter retrospective cohort study in patients with EAS at 37 centers. Outcomes were clinical/biochemical severity scores, complications, overall and CS-specific mortality. Results: In 1053 patients [median age at diagnosis 52 years (IQR 37-64), 57% women], metastatic disease was present at diagnosis in 585 (56%). The most common sources of EAS were bronchial neuroendocrine neoplasm (NEN) (304, 29%), pancreatic NEN (114, 11%) and small cell lung carcinoma (114, 11%), with the source of EAS being occult in 192 (18%). Clinical and biochemical severity scores were severe in 475 (45%) and 873 patients (92%) respectively. Hypokalemia was present in 819 patients (78%) in the year prior to diagnosis. Of 342 patients (32%) who had IPSS, 301 (88%) suggested an ectopic source, 7 (2%) a pituitary source, and 23 (7%) were non-diagnostic. Of 595 patients who had both functional and cross-sectional imaging, discordant findings were seen in 122 (21%), concordant lesion was seen on both in 326 (55%), and no lesion in 147 (25%). Of those with discordant results, cross-sectional imaging was accurate in 66 (54%) and functional imaging in 56 (46%).Management included medical therapy alone in 237 (23%), surgical excision of the source of EAS in 158 (15%), bilateral adrenalectomy in 77 (7%) and multimodal therapies in 498 patients (47%). Complications within 5 years after diagnosis included hospitalization related to CS or its therapy in 351 (33%), infection in 337 (32%), thromboembolic event in 102 (10%), cardiovascular event in 83 (8%) and cerebrovascular event in 27 (3%). During a median follow-up of 35 months (IQR 20-122) from CS diagnosis, death occurred in 462 patients (44%), with the cause of death related to CS in 149 (14%). CS-specific mortality was higher in metastatic compared with non-metastatic disease (19% vs. 7%, P<0.001). On multivariable analysis of age, sex, clinical and biochemical severity, older age (HR 1.03, 95% CI: 1.02-1.04) and lower clinical severity score (HR 0.97, 95% CI: 0.94-0.99), were associated with higher CS-specific mortality. Conclusion: Our interim analysis, the largest worldwide, found that most patients with EAS had severe hypercortisolism and hypokalemia. Metastatic disease was present in 56%, and the source of EAS was occult in 18%. CS-related death occurred in 14%, emphasizing the need for urgent management. Presentation: Monday, July 14, 2025

Endogenous Cushing’s syndrome (CS) is a rare neuroendocrine disorder characterized by either secondary cortisol increases due to an adrenocorticotropic hormone (ACTH)-secreting pituitary tumor (Cushing’s disease (CD)), an ACTH-secreting neuroendocrine tumor (NET) of non-pituitary origin (ectopic ACTH syndrome (EAS)), or by the primarily adrenal autonomous overproduction of cortisol [...]

WHAT IS THIS SUMMARY ABOUT?:Hypophosphatasia (HPP for short) is a rare inherited condition that can present at any stage of life, with symptoms typically being more severe in cases that manifest earlier, such as during infancy or childhood. This article summarizes three published studies that looked at the safety and effectiveness of asfotase alfa for people with HPP. The aim of this article is to present the findings of three studies clearly and engagingly to make them accessible to readers without a scientific background. The first study (called study 1) discussed in this article looked at how safe and effective asfotase alfa was for children with life-threatening HPP. The second study (called study 2) looked at how safe and effective asfotase alfa was for children or adolescents who had showed the first signs of HPP at birth or in childhood. They received treatment in clinical practice in Japan, rather than in a clinical research study. The third study (called study 3) looked at how safe and effective asfotase alfa was for adults with HPP who had showed the first signs of the condition in childhood. They received treatment in clinical practice, rather than in a clinical research study. WHAT WERE THE RESULTS?:In study 1, asfotase alfa improved bone health, the ability to breathe, and growth in children with life-threatening HPP. The researchers saw these benefits over 6 years of follow-up by HPP care teams. The treatment was generally well-tolerated. In study 2, asfotase alfa relieved symptoms such as pain, improved growth, and improved the ability to breathe in children and adolescents with HPP in Japan. The treatment was generally well-tolerated, with no serious side effects. Some participants had mild reactions at injection sites. In study 3, asfotase alfa improved physical function and quality of life for adults with HPP. People were able to walk further and faster and had improved grip strength. The researchers saw these benefits as early as 3 months, and they continued over 2 years. The treatment was welltolerated. Some people had mild reactions at injection sites. WHAT DO THE RESULTS OF THE STUDIES MEAN?:The combined results from these studies indicate that asfotase alfa is effective and safe to treat people with HPP of different ages and levels of symptom severity. Asfotase alfa improves bone health, mobility, growth, and breathing ability, and relieves pain. Treatment can improve quality of life for people with HPP. The findings from these studies support the continued use and further development of asfotase alfa as a treatment for people with HPP.

Chronic kidney disease (CKD) is associated with significant disturbances in mineral and vitamin D metabolism, leading to the development of CKD-related mineral and bone disorders (CKD-MBD) and an increased risk of cardiovascular complications, fractures, and mortality. This paper reviews the mechanisms of calcium-phosphorus homeostasis and vitamin D metabolism regulation in CKD, focusing also on the roles of parathyroid hormone (PTH), fibroblast growth factor-23 (FGF-23) and the Klotho protein. Modern approaches to laboratory diagnostics and target mineral parameters in CKD patients are discussed, as well as the potential use of novel biomarkers, such as the 24,25(OH) 2 D/25(OH)D ratio (VMR) and 1,24,25(OH) 3 D/1,25(OH) 2 D ratio (1,25VMR). This review highlights the need for further research to optimize the diagnosis and treatment of mineral disturbances in CKD patients.

Disclosure: R.J. Auchus: Corcept Therapeutics, received grants and personal fees, Crinetics Pharmaceuticals, received grants and personal fees, Diurnal Ltd, received grants and personal fees, Neurocrine Biosciences, received grants and personal fees, Sparrow Pharmaceuticals, received grants and personal fees, Spruce Biosciences, received grants and personal fees, Recordati Rare Diseases, received grants and personal fees, Xeris Pharmaceuticals, received grants and personal fees, Adrenas Therapeutics, received personal fees, Besins Pharmaceuticals, received personal fees, H Lundbeck A/S, received personal fees, Novo Nordisk, received personal fees, Quest Diagnostics, received personal fees. P. Witek: Berlin Chemie, received travel grants and speaker fees, Ipsen, received travel grants and speaker fees, Merck-Serono, received travel grants and speaker fees, Novartis, received travel grants and speaker fees, Novo Nordisk, received travel grants and speaker fees, Recordati Rare Diseases, received travel grants and speaker fees, Strongbridge Biopharma, received travel grants and speaker fees. M.A. Bex: Recordati Rare Diseases, consultancy and received travel grants. Y. Yu: None. Z. Belaya: None. A. Lacroix: Corcept Therapeutics, received grants and personal consulting fees, Novartis, received grants and personal consulting fees, Pfizer, received grants and personal consulting fees, Recordati Rare Diseases, received grants and personal consulting fees. C.M. Scaroni: HRA, received occasional consulting honoraria, Novartis, received occasional consulting honoraria, Pfizer, received occasional consulting honoraria, Recordati Rare Diseases, received occasional consulting honoraria, Sandoz, received occasional consulting honoraria. Y. Hwang: None. P. Kadioglu: None. A. Piacentini: Recordati, employee. A. Mueller: Recordati, employee. R. Pivonello: Corcept Therapeutics, received research funding and served as a consultant, Neurocrine Biosciences, received research funding, Recordati Rare Diseases, received research funding and served as a consultant, Spruce Bioscience, received research funding, Xeris Pharmaceuticals (Strongbridge Biopharma), received research funding, Crinetics Pharmaceuticals, served as a consultant, H Lundbeck A/S, served as a consultant. Introduction: The LINC clinical trial program demonstrated that osilodrostat is effective and well tolerated in patients with Cushing’s disease (CD); however, lifelong treatment is often required. The open-label, multicenter LINC rollover (NCT03606408) study evaluated long-term osilodrostat safety and effectiveness in patients with CD. Methods: The study was planned to be open for ∼5 years (or until December 31, 2023 in the UK). Participants benefiting from osilodrostat treatment after completing either the LINC 2, LINC 3 or LINC 4 trial extension phases were eligible for inclusion. Participants continued in the rollover until osilodrostat no longer provided (investigator-judged) clinical benefit, became commercially available in their country, or one of the protocol-defined discontinuation criteria was met. Participants attended quarterly visits for safety/clinical benefit assessments. The primary objective was to evaluate long-term safety of osilodrostat treatment, assessed by frequency of adverse events (AEs)/serious AEs (SAEs). Cumulative data are reported from parent study baseline (BL) to rollover end, unless otherwise stated. Results: 127 participants entered the rollover (mean [SD] age: 41.3 years [12.4]; female: 74.8%). Median (min–max) osilodrostat exposure and dose was 5.0 (1.7–8.6) years and 4.9 (1.0–46.0) mg/day. All patients experienced ≥1 AE; 86.6% (n=110) were considered treatment related, most commonly (≥25% of patients) nausea (30.7%, n=39), adrenal insufficiency (AI; 28.3%, n=36) and fatigue (28.3%, n=36). SAEs were reported in 44.9% (n=57) of participants; 8.7% (n=11) were considered treatment related, most commonly AI (4.7%, n=6). AEs related to accumulation of adrenal hormone precursors were reported in 65.4% (n=83), hypocortisolism in 55.9% (n=71), pituitary tumor enlargement in 8.7% (n=11), and arrhythmogenic potential and QT prolongation in 5.5% (n=7). During the rollover, 22.0% (n=28) discontinued osilodrostat; 3.9% (n=5) discontinued because of treatment-related AEs, most commonly AI (n=3). At the end of osilodrostat treatment, 78.0% (n=99) continued to receive clinical benefit. From BL to week (W) 12 of the parent studies, mean urinary free cortisol levels decreased from 561.5 nmol/24 h (4.1 x upper limit of normal [ULN]) to 85.0 nmol/24 h (0.6 x ULN), mean glycated hemoglobin levels decreased from 5.8% to 5.6%, and mean systolic blood pressure decreased from 130.7 mmHg to 123.2 mmHg. These parameters then generally remained within normal range during the study. Body weight generally decreased over time. Potassium and sodium levels remained stable and normal throughout the study. Conclusion: The LINC rollover study complements existing evidence demonstrating that osilodrostat is well tolerated and provides sustained effects in patients with CD during long-term treatment (for up to 8.6 years); no new safety signals were identified. Presentation: Sunday, July 13, 2025

Searchable abstracts of presentations at key conferences in endocrinology ISSN 1470-3947 (print) | ISSN 1479-6848 (online)

Abstract Disclosure: D. Trukhina: None. K. Voronov: None. E. Mamedova: None. A. Solodovnikov: None. Z. Belaya: None. Background. MEN-1 is a rare autosomal dominant disorder caused by mutations in the MEN1 gene encoding the menin protein (gMEN1). This syndrome is characterised by the occurrence of parathyroid tumours, gastroenteropancreatic neuroendocrine tumours, pituitary adenomas, and other endocrine and non-endocrine neoplasms. If a patient with the MEN-1 phenotype does not have any mutation in the MEN1 gene, the condition is considered a phenocopy of the syndrome (phMEN1).The goal of this study was to develop a machine learning algorithm to estimate the probability of gMEN-1 vs phMEN-1 based on easily available clinical features at first line differential diagnostics. Materials and methods. A single-center, one-stage, cohort, retrospective study was carried out. Patients were randomly stratified into 2 cohorts: training (80%) and test (20%). Eight machine learning algorithms were used to develop predictive models: Logistic Regression, k-nearest neighbors (kNN), Naive Bayes, binary decision tree (CART), C5.0 decision tree algorithms, Bagged CART, Random Forest, Gradient Boosting (Stochastic Gradient Boosting, GBM). Results. The study included 95 patients with genetically confirmed gMEN-1 syndrome and 60 patients with its phenocopies. As a result of preliminary data processing and selection for the most informative features, the final variables for the classification and prediction of gMEN-1 syndrome were identified: the number of affected parathyroid glands, age at diagnostics, pancreatic tumour existence, heredity, type of pituitary adenoma secretion, and gender. The kNN algorithm demonstrated the best diagnostic performance in a training sample (ROC-AUC - 0.96, sensitivity - 84%, specificity - 100%), which was confirmed in a test sample (ROC-AUC - 1.0; sensitivity - 94.4%, specificity - 100%) to determine genetically confirmed MEN-1 syndrome. Conclusion. The k-nearest neighbours (kNN) algorithm may be used as a first-line differential diagnostics method to select patients to be refered for genetic testing for gMEN-1. Presentation: 6/1/2024

Searchable abstracts of presentations at key conferences in endocrinology ISSN 1470-3947 (print) | ISSN 1479-6848 (online)

BACKGROUND: Osteoporosis is often diagnosed at the stage with complications, i.e., low-energy fractures. Vertebral compression fractures, which are complications of osteoporosis and predictors of subsequent fractures, are often asymptomatic. Compression fractures can be found by computed tomography performed for other indications with vertebral morphometry. Approaches to using artificial intelligence algorithms designed for diagnosing vertebral compression fractures were analyzed. AIM: Testing artificial intelligence algorithms to conduct morphometric analysis of vertebrae on chest computed tomography scans and assess the possibility of their implementation in medical organizations of the Moscow Healthcare Department. MATERIALS AND METHODS: To set a clinical task for artificial intelligence algorithms, basic diagnostic requirements in the area of “vertebral compression fractures (osteoporosis)” were formulated. The testing of the artificial intelligence algorithms included the following stages: self-testing, functional and calibration testing, practical evaluation, and operation testing. The first three stages of testing were performed using previously generated datasets. At practical evaluation and operation testing, artificial intelligence algorithms analyzed the data from computed tomography performed in medical organizations. The expert group of radiologists assessed the diagnostic accuracy and functional capacity of the AI algorithms at all stages. The resulting quantitative metrics of the accuracy of artificial intelligence algorithms were compared with the required target values. RESULTS: From June 2021 to June 2022, two artificial intelligence algorithms (Nos. 1 and 2) with different methods of detecting compression fractures were tested. Both artificial intelligence algorithms successfully passed the self-testing (6 tests), functional (5 tests), and calibration (100 tests) stages. The area under the ROC curve for artificial intelligence algorithm No. 1 was 0.99 (95% CI, 0.98–1), and for artificial intelligence algorithm No. 2, it was 0.91 (95% CI, 0.85–0.96). Artificial intelligence algorithm No. 1 passed the practical evaluation stage without any significant remarks, whereas algorithm No. 2 was sent for fine-tuning. After the operation testing stage, the following accuracy metrics were obtained: the areas under the ROC curve for artificial intelligence algorithm Nos. 1 and 2 were 0.93 (95% CI, 0.89–0.96) and 0.92 (95% CI, 0.90–0.94), respectively. At all stages, both artificial intelligence algorithms demonstrated sufficient metrics for clinical validation. CONCLUSION: Artificial intelligence algorithms for the automatic diagnosis of vertebral compression fractures have been tested, demonstrating the high quality of their operation. artificial intelligence algorithms can be applied as a supplementary tool in the medical decision support system.

Abstract Introduction Ectopic ACTH syndrome (EAS) is a rare cause of endogenous hypercortisolism. We present a case of a patient diagnosed with severe EAS, achieving eucortisolism and a favorable outcome of ACTH-producing metastatic pancreatic neuroendocrine tumor (NET) after 177Lu-DOTATATE and osilodrostat treatment. Clinical Case A female patient was admitted to our clinic at the age of 55 complaining of severe fatigue, facial and leg edema. Laboratory tests revealed a significant degree of ACTH-dependent hypercortisolemia (late-night serum cortisol 1856 nmol/L (64–327), late-night salivary cortisol (LNSC) 387.7 nmol/L (0.5–9.65), 24hUFC 8561 nmol/L (100–379), ACTH 332.8 pg/mL (7.2–63.3)), hypokalemia (1.88 mmol/L), increased liver enzymes (alanine aminotransferase (ALT) 303.2 U/L (0–55), aspartate aminotransferase (AST) 94.3 U/L (5–34)). MRI of the brain was negative for pituitary abnormalities. CT and somatostatin receptor scintigraphy with 99mTc-Tektrotyd revealed NET of the pancreas and multiple liver metastases. Subsequent biopsy confirmed NET grade 2, Ki67 – 7%. Treatment with lanreotide 120 mg every four weeks was initiated. In order to control hypercortisolism the patient received osilodrostat at a dose of 10 mg daily, which improved the patient's general condition in the first days of therapy. After 1 month of treatment, her hypercortisolism symptoms improved, LNSC dropped to 0.54 nmol/L and morning cortisol dropped from 1451 nmol/L (101–535) to 60.7 nmol/L, which could suggest adrenal insufficiency. She also had normalization of potassium and liver enzymes (ALT 18.4 U/L, AST 23 U/L). The dose of osilodrostat was firstly reduced and then discontinued. 177Lu-DOTATATE treatment was offered with four doses (7.4 GBq (200 mCi) every 8 weeks). The first dose was administered in January 2023. The SPECT-CT performed after the second dose demonstrated disease stabilization. At the time of writing, the patient remains in eucortisolism (LNSC 5,36 nmol/L, morning cortisol 140 nmol/L, ACTH 36.4 pg/ml) with tumor stabilisation after 4 doses of 177Lu-DOTATATE. However, the most recent routine blood test revealed thrombocytopenia (platelets 44×109/μl (150–400)), decreased white blood cell count (3.24×109/μl (4.5–11)), lymphocytes (0.71×109/μl (1.18–1.34)) and hemoglobin 98 g/L (117–160). Nevertheless, her general condition remains stable and significantly improved versus the initial investigation. Conclusion This observation highlights the feasibility and efficacy of a combined approach using osilodrostat and 177Lu-DOTATATE in the management of patients with metastatic ACTH-producing NET. This approach resulted in a substantially improved patient quality of life. Funding Russian Scientific Foundation 19-15-00398