Machine Learning to Predict Prostate Artery Embolization Outcomes.

PURPOSE: This study leverages pre-procedural data and machine learning (ML) techniques to predict outcomes at one year following prostate artery embolization (PAE). MATERIALS AND METHODS: This retrospective analysis combines data from the UK-ROPE registry and patients that underwent PAE at our institution between 2012 and 2023. Traditional ML approaches, including linear regression, lasso regression, ridge regression, decision trees and random forests, were used with leave-one-out cross-validation to predict international prostate symptom score (IPSS) at baseline and change at 1 year. Predictors included age, prostate volume, Qmax (maximum urinary flow rate), post-void residual volume, Abrams-Griffiths number (urodynamics score) and baseline IPSS (for change at 1 year). We also independently confirmed our findings using a separate dataset. An interactive digital user interface was developed to facilitate real-time outcome prediction. RESULTS: Complete data were available in 128 patients (66.7 ± 6.9 years). All models predicting IPSS demonstrated reasonable performance, with mean absolute error ranging between 4.9-7.3 for baseline IPSS and 5.2-8.2 for change in IPSS. These numbers represent the differences between the patient-reported and model-predicted IPSS scores. Interestingly, the model error in predicting baseline IPSS (based on objective measures alone) significantly correlated with the change in IPSS at 1-year post-PAE (R2 = 0.2, p < 0.001), forming the basis for our digital user interface. CONCLUSION: This study uses ML methods to predict IPSS improvement at 1 year, integrated into a user-friendly interface for real-time prediction. This tool could be used to counsel patients prior to treatment.

A retrospective cohort study comparing a novel, spherical, resorbable particle against five established embolic agents for uterine fibroid embolisation.

AIM: To evaluate the effectiveness of a novel, resorbable, spherical embolic agent compared with other established agents, by studying percentage fibroid infarction (the best indicator of long-term symptom improvement) in patients undergoing uterine fibroid embolisation (UFE). MATERIALS AND METHODS: This retrospective cohort study examined six different embolic agents used for fibroid embolisation, including a new gelatin-based, fully resorbable, spherical agent. The primary effectiveness outcomes were magnetic resonance imaging (MRI)-determined dominant fibroid infarct percentage (DF%) and all fibroid percentage infarct (AF%) at 3 months post-embolisation. MRI-determined uterine artery patency rate was the secondary outcome. Chi-squared test (χ2), relative risk (RR) calculation (primary outcomes), and analysis of variance (ANOVA) (secondary outcome) were the statistical tests employed. RESULTS: One hundred and twenty patients were treated with six embolic agents (20 consecutive patients per group, overall mean age 44.8±6.4, initial uterine volume 570±472 ml, dominant fibroid volume 249±324 ml). Fibroid infarctrates were similar between the cohorts with no significant difference between the new gelatin-based resorbable particle and other embolics in either DF% (χ2=3.92, p=0.56) or AF% (χ2=2.83, p=0.73). Complete DF% RR=1.07 (0.90-1.27) and AF% RR=1.09 (0.85-1.41) suggest non-inferiority of the resorbable particle (d=0.67, p<0.05). A favourable uterine artery patency rate was demonstrated for the resorbable particle compared with gelatin slurry (82.5% versus 27.5%, p<0.001 after Bonferroni adjustment). CONCLUSIONS: This new gelatin-based, fully resorbable particle is an effective embolic agent for fibroid embolisation and achieves an infarct rate non-inferior to established embolics.

Factors Predicting a Good Symptomatic Outcome After Prostate Artery Embolisation (PAE).

INTRODUCTION: As prostate artery embolisation (PAE) becomes an established treatment for benign prostatic obstruction, factors predicting good symptomatic outcome remain unclear. Pre-embolisation prostate size as a predictor is controversial with a handful of papers coming to conflicting conclusions. We aimed to investigate if an association existed in our patient cohort between prostate size and clinical benefit, in addition to evaluating percentage volume reduction as a predictor of symptomatic outcome following PAE. MATERIALS OR METHODS: Prospective follow-up of 86 PAE patients at a single institution between June 2012 and January 2016 was conducted (mean age 64.9 years, range 54-80 years). Multiple linear regression analysis was performed to assess strength of association between clinical improvement (change in IPSS) and other variables, of any statistical correlation, through Pearson's bivariate analysis. RESULTS: No major procedural complications were identified and clinical success was achieved in 72.1% (n = 62) at 12 months. Initial prostate size and percentage reduction were found to have a significant association with clinical improvement. Multiple linear regression analysis (r2 = 0.48) demonstrated that percentage volume reduction at 3 months (r = 0.68, p < 0.001) had the strongest correlation with good symptomatic improvement at 12 months after adjusting for confounding factors. CONCLUSION: Both the initial prostate size and percentage volume reduction at 3 months predict good symptomatic outcome at 12 months. These findings therefore aid patient selection and counselling to achieve optimal outcomes for men undergoing prostate artery embolisation.

Hepatic fibrosis and cirrhosis in the Fontan circulation: a detailed morphological study.

AIMS: To describe the histological features of the liver in patients with a Fontan circulation. METHODS: Specimens from liver biopsies carried out as part of preoperative assessment prior to extracardiac cavopulmonary conversion of an older style Fontan were examined and scored semi-quantitatively for pertinent histological features. To support the use of the scoring, biopsy specimens were also ranked by eye for severity to allow correlation with assigned scores. RESULTS: Liver biopsy specimens from 18 patients with a Fontan circulation were assessed. All specimens showed sinusoidal fibrosis. In 17 cases there was at least fibrous spur formation, with 14 showing bridging fibrosis and 2 showing frank cirrhosis. In 17 cases at least some of the dense or sinusoidal fibrosis was orcein positive, although a larger proportion of the dense fibrous bands were orcein positive compared with the sinusoidal component. All specimens showed marked sinusoidal dilatation, and 14 showed bile ductular proliferation; 1 showed minimal iron deposition, and 1 showed mild lobular lymphocytic inflammation. There was no cholestasis or evidence of hepatocellular damage. Similar appearances were observed in 2 patients with severe tricuspid regurgitation. DISCUSSION: The histological features of the liver in patients with a Fontan circulation are similar to those described in cardiac sclerosis. Sinusoidal dilatation and sinusoidal fibrosis are marked in the Fontan series. The presence of a significant amount of orcein negative sinusoidal fibrosis suggests there may be a remediable component, although the dense fibrous bands are predominantly orcein positive, suggesting chronicity and permanence. No inflammation or hepatocellular damage is evident, suggesting that fibrosis may be mediated by a non-inflammatory mechanism.

Super-selective angiographic embolisation of a branch of the anterior pudendal artery for the treatment of intractable post-operative bleeding.

We describe a case of post-operative bleeding after a posterior fascial defect repair. This was refractive to exploration and vaginal packing so laparotomy would have been necessary. Superselective cannulation demonstrated bleeding from a branch of the anterior pudendal artery which had crossed the midline making identification difficult during vaginal exploration. The bleeding vessel was embolised using a mixture of PVA300 and Spongistan gel foam and the bleeding ceased. The use of embolisation in the peri-operative phase is discussed.

Distribution of bony metastases in prostatic carcinoma.

Fifty-five prostate cancer and 55 breast cancer patients with positive bone scintigrams were studied. The pattern of spread in the axial skeleton and pelvis showed differences between the 2 groups. This difference was not related primarily to bone volume at the site of metastasis. The difference in distribution of bony metastases between breast and prostate is explained by our knowledge of Batson's vertebral venous plexus.