Kline, Timothy L.

Key Points Automated cyst segmentation in autosomal dominant polycystic kidney disease could transform care by enabling precise monitoring of cyst progression with minimal manual effort. This technology can facilitate more consistent assessments of cyst burden across patients. Translating these segmentation models from magnetic resonance imaging to computed tomography is crucial for providing comprehensive, modality-independent evaluations. Background Total kidney and liver volumes are key image-based biomarkers to predict the severity of kidney and liver phenotype in autosomal dominant polycystic kidney disease (ADPKD). However, magnetic resonance (MR) imaging-based advanced biomarkers like total cyst number and cyst parenchyma surface area have been shown to more accurately assess cyst burden and improve the prediction of disease progression. The main aim of this study was to extend the calculation of advanced biomarkers to other imaging modalities; thus, we propose a fully automated model to segment kidney and liver cysts in computed tomography (CT) images. Methods Abdominal CTs of patients with ADPKD were gathered retrospectively between 2001 and 2018. A three-dimensional deep learning method using the nnU-Net architecture was trained to learn cyst edges-cores and the noncystic kidney/liver parenchyma. Separate segmentation models were trained for kidney cysts in contrast-enhanced CTs and liver cysts in noncontrast CTs using an active learning approach. Two experienced research fellows manually generated the reference standard segmentation, which were reviewed by an expert radiologist for accuracy. Results Two-hundred CT scans from 148 patients (mean age, 51.2±14.1 years; 48% male) were used for model training (80%) and testing (20%). In the test set, both models showed good agreement with the reference standard segmentations, similar to the agreement between two independent human readers (model versus reader: TCN kidney/liver r =0.96/0.97 and CPSA kidney r =0.98, inter-reader: TCN kidney/liver r =0.96/0.98 and CPSA kidney r =0.99). Conclusions Our study demonstrates that automated models can segment kidney and liver cysts accurately in CT scans of patients with ADPKD.

Abstract Objectives Large language models (LLMs) offer potential in natural language processing tasks in healthcare. Due to the need for high accuracy, understanding their limitations is essential. The purpose of this study was to evaluate the performance of LLMs in classifying radiology reports for the presence of pulmonary embolism (PE) under various conditions, including different prompt designs and data perturbations. Materials and Methods In this retrospective, institutional review board approved study, we evaluated 3 Google’s LLMs including Gemini-1.5-Pro, Gemini-1.5-Flash-001, and Gemini-1.5-Flash-002, in classifying 11 999 pulmonary CT angiography radiology reports for PE. Ground truth labels were determined by concordance between a computer vision-based PE detection (CVPED) algorithm and multiple LLM runs under various configurations. Discrepancies between algorithms’ classifications were aggregated and manually reviewed. We evaluated the effects of prompt design, data perturbations, and repeated analyses across geographic cloud regions. Performance metrics were calculated. Results Of 11 999 reports, 1296 (10.8%) were PE-positive. Accuracy across LLMs ranged between 0.953 and 0.996. The highest recall rate for a prompt modified after a review of the misclassified cases (up to 0.997). Few-shot prompting improved recall (up to 0.99), while chain-of-thought generally degraded performance. Gemini-1.5-Flash-002 demonstrated the highest robustness against data perturbations. Geographic cloud region variability was minimal for Gemini-1.5+-Pro, while the Flash models showed stable performance. Discussion and Conclusion LLMs demonstrated high performance in classifying radiology reports, though results varied with prompt design and data quality. These findings underscore the need for systematic evaluation and validation of LLMs for clinical applications, particularly in high-stakes scenarios.

Key Points This study demonstrates that peritoneal dialysis is a safe and feasible option for patients with autosomal dominant polycystic kidney disease, even with high cystic organ volumes. Larger organ volumes, including height-adjusted cumulative kidney and liver volume, were not associated with increased peritoneal dialysis–related complications. Background Autosomal dominant polycystic kidney disease (ADPKD) is the most prevalent genetic kidney disorder and the fourth leading cause of kidney failure. Peritoneal dialysis (PD), preferred for its home-based convenience and cost-effectiveness, is often underutilized in ADPKD because of concerns over enlarged kidneys and heightened risk of complications. Methods This retrospective cohort study used data from the Mayo Clinic Polycystic Kidney Disease Database to evaluate individuals with ADPKD undergoing PD. We analyzed demographics, clinical parameters, and PD-related parameters. Complications were correlated with kidney and liver volumes derived from pre-kidney failure imaging. Results A total of 155 individuals with ADPKD on PD were included, of whom 45.1% were male. The mean age at PD initiation was 54.3±12.8 years, and the mean body mass index was 28.0±7.0 kg/m 2 . The median duration of PD was 24.3 months (interquartile range [IQR], 10.7–43.1), with 21.9% transitioning to hemodialysis. The most common complications were abdominal hernias (30.3%) and peritonitis (23.9%), with a peritonitis rate of 0.11 episodes per patient-year. Imaging analyses performed on a subset of 50 patients showed a median height-adjusted total kidney liver volume of 2731.9 ml/m (IQR, 2102.5–3131.1) and a median height-adjusted total kidney volume of 1303.5 ml/m (IQR, 733.1–1829.4). Kaplan–Meier analysis demonstrated no differences in complications rates on the basis of height-adjusted total kidney liver volume or height-adjusted total kidney volume (above versus below median values) or body mass index categories. Multivariate Cox regression analysis revealed that higher height-adjusted cumulative organ volume was associated with a lower risk of PD-related complications (hazard ratio=0.56, P = 0.026). Conclusions PD is a safe and feasible treatment option for patients with ADPKD, with no increased risk of PD-related complications associated with larger height-adjusted cumulative organ volumes. Infectious complication rates in this cohort were within International Society of Peritoneal Dialysis guideline thresholds, further supporting the safety of PD in this population.

ABSTRACT Background This medical center migrated from alcohol to sotradecol foam sclerotherapy (SFS) because of perceived improved efficacy in managing symptomatic kidney and liver cysts. We report technical aspects, change in short- and long-term cyst volumes, patient-reported outcomes, safety and applications of the technique. Methods In this retrospective observational study, cases from January 2017 to December 2021 had TKCV/TLCV (per Targeted Kidney or Liver or Cyst analysis) segmented using a deep-learning algorithm and cyst segmentation software (pre-, post-procedure and longitudinally). TKCV/TLCV % change were evaluated using the one-sample Wilcoxon signed rank test. For analyses involving changes in cyst volumes, the median % change in cyst volume per patient was assessed. Longitudinal changes in cyst volumes were assessed using linear mixed models. Changes in quality of life (QOL) [Linear Analog Self-Assessment (LASA), Polycystic Liver Disease Quality of life Questionnaire (PLD-Q) and 12-item short-form (SF12)] were also assessed. Results There were 102 SFS sessions (38 kidney, 58 liver, 6 combined liver/kidney cysts) performed on 77 unique individuals included for analysis. Median [interquartile range (IQR)] % reductions in TKCV were –92.0% (IQR –98.2%, –82.7%, P < .001) and for TLCV were –83.1% (IQR –93.5%, –52.9%, P < .001). Among patients with multiple kidney procedures (n = 7), median % reduction in TKCV was –94.3% (IQR –96.6%, –92.4%, P = .023). For patients with multiple liver procedures (n = 11), median % reduction in TLCV was –63.3% (IQR –85.2%, –28.3%, P = .004). Results were similar among the four patients undergoing multi-stage procedures (n = 1 kidney, n = 3 liver). When measured longitudinally, both liver and kidney cyst volumes declined to levels near 0 mL by 1 year follow-up and remained stable several years later. LASA physical domain and PLD-Q QOL scores improved post-SFS procedure. Conclusion SFS led to substantial long-term reductions in TKCV/TLCV and improved QOL. SFS can augment cyst volume reduction in addition to tolvaptan (kidney cysts) and octreotide (liver cysts). In some individuals with large symptomatic cysts, multiple SFS procedures were safe and effective in reducing TLCV/TKCV and improving symptoms.

ABSTRACT Background Autosomal dominant polycystic kidney disease (ADPKD) is the most commonly inherited progressive kidney disease. Time-restricted eating (TRE) is a fasting regimen that restricts eating to a particular window (typically 8 hours/day), which could slow cyst growth based on preclinical models. Methods A 12-month, randomized, controlled, behavioral dietary intervention compared TRE with a control group given healthy eating advice without TRE (HE), without caloric restriction. Participants underwent baseline and 12-month measurements, including adherence (percentage of participants adhering to the 8-hour window; primary outcome), and MRI to determine height-adjusted total kidney volume (htTKV) and adiposity. Results Twenty-nine participants (23 females, mean standard ± deviation 48 ± 9 years) with a body mass index of 31.1±5 kg/m2 were randomized to TRE (n = 14) or HE (n = 15). Of the total participants, 71% (n = 10) of TRE and 87% (n = 13) of HE participants completed the intervention. The eating window was 9.6 ± 3.6 hours for TRE (60% achieving the 8-hour window) and 12.0 ± 2.0 for HE groups (P = .07). At month 12, both groups lost modest weight (−2.4 ± 6.4% and −3.6 ± 5.4% in the TRE and HE groups, respectively). Annual change in htTKV was 3.0 ± 8.5% and 4.6 ± 8.8% in the TRE and HE groups, respectively. Both change in weight (r = 0.67, P < .01) and change in visceral adiposity (r = 0.54, P < .01) were positively correlated with change in htTKV. Conclusion Both the TRE and HE group lost modest weight at 12 months. The targeted TRE adherence of ≥75% of participants was not achieved. Weight and adiposity loss may be more important drivers of kidney growth than the timing of eating.

Key Points Loss-of-function ALG8 and ALG9 variants were enriched in polycystic kidney/liver groups and International Classification of Diseases–coded cystic individuals in population cohorts. The ALG8 and ALG9 kidney phenotypes were usually mild to moderate, and lower eGFR or kidney failure was rare. ALG8 pathogenic variants sometimes resulted in severe polycystic liver disease. Background Autosomal dominant polycystic kidney disease (ADPKD) is a common, inherited nephropathy often resulting in kidney failure. It is genetically heterogeneous; along with the major genes, PKD1 and PKD2 , at least eight others have been suggested. ALG8 pathogenic variants have been associated with autosomal dominant polycystic liver disease and implicated in ADPKD, while ALG9 has been suggested as an ADPKD gene, but details of the phenotypes and penetrance are unclear. Methods We screened >3900 families with cystic kidneys and/or livers using global approaches to detect ALG8 or ALG9 pathogenic variants. In addition, population cohorts with sequence data (Genomics England 100K Genomics Project, UK Biobank, and Mayo Clinic Biobank [MCBB]) were screened for ALG8 / ALG9 pathogenic variants. Results Multicenter screening of individuals with polycystic kidney and/or liver disease identified 51 (1.3%) ALG8 (7 multiplex) and 23 (0.6%) ALG9 (5 multiplex) families—frequencies that were approximately 10× and approximately 24× greater than nonpolycystic kidney disease controls. Analysis of individuals with polycystic kidney disease phenotypes in 100K Genomics Project, UK Biobank, and MCBB identified nine ALG8 (0.39%) and nine ALG9 (0.39%) families, an enriched frequency over controls. Two individuals had PKD1 and ALG8 pathogenic changes. Eighty-nine percent of individuals with ALG8 mutations with imaging in the entire MCBB had kidney cysts (50%, >10 cysts), with greater median kidney and liver cyst numbers than controls. For ALG9, 78% had kidney cysts (27%, >10 cysts). Individuals with ALG8 mutations typically had mild cystic kidneys with limited enlargement. Liver cysts were common (71%), with enlarged livers (>2L) found in 11 of 62 patients, although surgical intervention was rare. The ALG9 kidney phenotype was also of mild cystic kidneys, but enlarged livers were rare; for both genes, CKD or kidney failure were rare. Conclusions ALG8 and ALG9 are defined as cystic kidney/liver genes but with limited penetrance for lower eGFR.