METHOD: All ADPDK patients hospitalized between January 2007 and March 2019 who underwent an 18 F-FDG PET/CT for suspected CyI were retrospectively identifed using computer-based databases. Medical fles were systematically reviewed. CyI was conventionally defned by: fever (>38°C), abdominal pain, increased plasma CRP levels (≥70 mg/dL), absence of any other cause of infammation and favorable outcomes after ≥21 days of antibiotics. The 18 F-FDG uptake around the suspected CyI was evaluated using the 4-point scale. Stats were performed using SAS version 9.4. RESULTS: Our cohort included 51 18 F-FDG PET/CT in 51 patients, including 11 cases of CyI according to the above-detailed defnition. The agreement between the 4-point scale and the gold-standard criteria of CyI was signifcant, with an odds ratio of 6.03 for CyI in case of a score ≥3(P, 0.014). The corresponding sensitivity and specifcity of PET/CT using the 4-point scale were 63.3% and 77.5%, respectively. CONCLUSION: Our independent validation cohort confrms that the use of a semi- quantitative 4-point scoring system helps in the diagnosis of CyI by 18 F-FDG PET/CT imaging in patients with ADPKD. MO012 DEVELOPMENT OF AN ACCURATE AUTOMATED SEGMENTATION ALGORITHM TO MEASURE TOTAL KIDNEY VOLUME IN ADPKD SUITABLE FOR CLINICAL APPLICATION (THE CYSTVAS STUDY) Jonathan Taylor 1 , Richard Thomas 1 , Peter Metherall 1 , Albert Ong 2,3,4 and Roslyn Simms 3,4 1 Sheffield Teaching Hospitals NHS Foundation Trust, 3DLab, Sheffield, UK, 2 University of Sheffield, Academic Nephrology Unit, IICD, Sheffield, UK, 3 CYSTIc consortium, UK and 4 Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield Kidney Institute, Sheffield, UK BACKGROUND AND AIMS: A major barrier to the routine adoption of total kidney volume (TKV) as a clinical biomarker of disease for autosomal dominant polycystic disease (ADPKD) is the signifcant human operator time required even by experienced analysts (typically, 45–90 min per patient). Several groups have investigated automated and semi-automated kidney segmentation methods to either reduce or eliminate the human interaction required. However, such tools have mostly been developed using data from single centers, which may not translate well to other centers. To date, there has been little attempt to develop or validate algorithms using multi-center and multi-scanner data. Here, we report an automated segmentation tool capable of high performance across diferent patient populations and scanner sequences using 1.5 T MRI data from four centers (the CYSTic consortium). The algorithm was subsequently tested in a separate clinical cohort to assess its likely performance during routine clinical use. METHOD: All 1.5 T studies from the CYSTic trial were downloaded (acquired from Siemens Avanto, GE Optima and Siemens Aera, using diferent sequences). Cases with poor image quality or with sections of kidney missing from the feld of view were excluded. A single, experienced operator selected the most appropriate image series for segmentation and manually segmented each patient’s kidneys using a commercial software program (MIM Encore). There were 454 kidneys segmented from 227 scans. These data were used for algorithm training and validation. In addition, 48 routine clinical scans from the Shefeld 3D Lab were extracted from the archives along with their original segmentations (performed by six diferent analysts), to use as a test set. None of the patients in the clinical test set were included in the training set. An ensemble U-net algorithm was created using the nnUNet approach Isensee et al. (nnU-Net: a self-confguring method for deep learning-based biomedical image segmentation. Nat Meth 2021; 18(2): 203–211), whereby the CYSTic data were used in a 5-fold cross-validation, with stratifcation across the four centers (i.e. each center contributed 80% of the available data to algorithm training in each fold). Algorithm training proceeded according to the standard heuristic nnUnet functions, using a 3D architecture, for 100 epochs. Segmented kidneys were split into left and right sides during post-processing, through analysis of the position of the center of gravity of segmented regions. Once trained, the fve algorithms from cross-validation were applied in an ensemble to the clinical test cohort. RESULTS: In both cross-validation and clinical testing phases, the median DICE score was 0.96 for each kidney (IQR of 0.95–0.97 in cross-validation on both sides, And 0.95–0.97 on the left side for clinical testing and 0.96 for the right). The median total kidney volume error was −0.46% (−2.02 to 1.27) for the left side in cross-validation and −0.82% (−2.55 to 0.86) for the right. In the clinical testing phase, the median volume errors were −1.8% (−3.69 to 1.29), left and −1.79% (−3.95 to 0.65), right. The mean time taken to manually segment kidneys in the CYSTIc dataset was 54 min per scan (SD of 31 min). Use of the algorithm as a frst pass segmentation, with subsequent checking and editing by an operator, would signifcantly reduce human input time to a few minutes per case CONCLUSION: Our new algorithm demonstrates high accuracy compared to the gold standard of manual TKV segmentation and performs well in a wide range of patients with ADPKD imaged using diferent scanners at several European centers. Its high performance in a real-world clinical dataset demonstrates that such tools can provide a reliable means of measuring TKV in routine practice and reduces the previous barrier of analyst time and experience. MO013 RELATIONSHIP BETWEEN DISEASE AWARENESS AND SEVERITY OF KIDNEY DISEASE IN AUTOSOMAL DOMINANT POLYCYSTIC KIDNEY DISEASE PATIENTS Ege Dogan 1 , Necmi Eren 2 ,¸ Seyda Gül Özcan 3 , Orcun Altunoren 4 , Ozkan Gungor 4 , Hamad Dheir 5 , Mehmet Tanrisev 6 , Hafsa Kocyigit 7 , Abdülmecit Yıldız 8 , Ismail Kocyigit 9 , Nurhan Seyahi 10 and Erhan Tatar 11 1 Department of Internal Medicine, University of Health Science, Bozyaka Education and Research Hospital, Izmir Faculty of Medicine, Izmir, Turkey, 2 Division of Nephrology, Faculty of Medicine, Kocaeli University, Kocaeli, Turkey, 3 Istanbul University-Cerrahpasa, Department of Internal Medicine, Cerrahpasa Medical Faculty, Istanbul, Turkey 4 Department of Nephrology, Kahramanmara¸ s Sütçü ˙ Imam University, Turkey, 5 Department of Nephrology, Sakarya University, Turkey, 6 Department of Nephrology, University of Health Science, Izmir Faculty of Medicine, Tepecik Education and Research Hospital, Turkey, 7 Department of Internal Medicine, Erciyes University, Turkey, 8 Department of Nephrology, Uludag University, Turkey, 9 Department of Nephrology, Erciyes University, Turkey, 10 Department of Nephrology, Istanbul University-Cerrahpasa, Turkey and 11 Department of Nephrology, University of Health Science, Bozyaka Education and Research Hospital, Izmir Faculty of Medicine, Turkey BACKGROUND AND AIMS: Autosomal dominant polycystic kidney disease (ADPKD) is the most common hereditary kidney disease with difuse cysts in both kidneys and is responsible for 5–10% of end-stage renal disease Levy and Feingold (Estimating prevalence in single-gene kidney diseases progressing to renal failure. Kidney Int. 2000;58(3):925). Recently, tolvaptan, which can improve kidney survival, was approved for the management of the disease (Drug Approval Package: Jynarque (tolvaptan) Otsuka Pharmaceutical Development & Commercialization, Inc. application Number: 204 441, Approval Date: 04/23/2018). We examined the relationship between renal and extrarenal fndings, disease severity and the level of consciousness of patients with ADPKD patients. METHOD: About 516 patients who applied to nephrology clinics of seven diferent centers in Turkey were asked to answer the questionnaire about ADPKD that consisted of 38 questions. Disease severity was determined according to e-GFR, and disease awareness was assessed on a four-point scale by adapting the Disease Perception Scale to ADPKD. Awareness of patients was evaluated comparatively with chronic kidney disease stage, age, region and symptoms. RESULTS: One out of fve patients does not know that this disease is inherited. Mean awareness scores of the patients decreased signifcantly with increasing age. The average awareness score of the Central Anatolia region was signifcantly higher compared to other regions. Awareness scores were signifcantly higher in patients with fank pain and urinary tract stones. CONCLUSION: To the best of our knowledge, this is the frst study about ADPKD awareness. Although ADPKD is the most common hereditary kidney disease, the rate of patients’ knowledge on this subject is low. Awareness levels may vary according to age, regional diferences or symptoms. Increased awareness might lead to better treatment and improved survival in those patients. MO014 DEVELOPMENT AND VALIDATION OF THE THIRST DISTRESS SCALE FOR PATIENTS WITH AUTOSOMAL DOMINANT POLYCYSTIC KIDNEY DISEASE ¸ Seyda Gül Özcan 1 , Sibel Bek 2 , Necmi Eren 3 , Zeynep Atli 4 , Abdülmecit Yıldız 5 , Ismail Kocyigit 6 , Caner Cavdar 7 , Nurhan Seyahi 8 , Tevfik Ecder 9 and Nana Waldreus 10 1 Cerrahpasa Medical Faculty, Internal Medicine, Istanbul, Turkey, 2 Kocaeli Medical Faculty, Nephrology, Turkey, 3 Kocaeli Medical Faculty, Nephrology, Turkey, 4 Account and Tax Application, Sinop University, Istanbul, Turkey, 5 Faculty of Medicine, Uludag University, Nephrology, Bursa, Turkey, 6 Erciyes Medical Faculty, Nephrology, Kayseri, Turkey, 7 Dokuz Eylul Medical Faculty, Nephrology, Istanbul, Turkey, 8 ˙ Istanbul Üniversitesi-Cerrahpa ¸ sa Cerrahpa ¸ sa Tıp Fakültesi, Nephrology, Istanbul, Turkey, 9 Demiroglu Bilim Medical Faculty, Nephrology, Istanbul, Turkey and 10 Karolinska Institutet, Neurobiology, Care Sciences and Society, Sweden BACKGROUND AND AIMS: Abundant water intake is advised for patients with autosomal dominant polycystic kidney disease (ADPKD) Meijer and Casteleijn (Riding the waves: evidence for a benefcial efect of increased water intake in autosomal dominant polycystic kidney disease patients? Nephrol Dialysis Transpl. 2014;29(9):1615–1617). Thirst, which can be defned as a sensation of dryness in the mouth and throat associated with a desire for liquids, is the main driver for fuid consumption Fitzsimons (Thirst. Physiol Rev 1972;52(2):468–561). However, daily routines may limit water intake. There is no established tool to quantify the drivers of i6 Abstract Downloaded from https://academic.oup.com/ndt/article/37/Supplement_3/gfac061.009/6578350 by guest on 21 March 2023