An observational study in Hemorrhoid and Hemorrhoid Prolapse, sponsored by IRCCS Policlinico S. Donato. Enrolling by invitation at 1 site in Italy. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-08-27.
Sponsored by IRCCS Policlinico S. Donato · Observational
This retrospective, single-center observational study will use routinely collected perioperative data from adults undergoing surgery for symptomatic hemorrhoidal disease to identify data-driven clinical phenotypes. Unsupervised machine learning will be applied to characterize clusters of patients based on demographic, clinical, anatomical, and surgical variables. The study will explore whether the resulting phenotypes differ in operative complexity and postoperative course, and will generate hypotheses to inform future predictive models and personalized surgical planning.
Hemorrhoidal disease presents with heterogeneous symptom patterns, anatomical findings, and operative strategies that are not fully captured by traditional degree-based classifications. This study aims to identify latent, clinically interpretable phenotypes among surgical patients using a fully unsupervised machine learning pipeline applied to routinely collected perioperative data from a high-volume tertiary referral center.
This is a retrospective, observational analysis of de-identified institutional records. The analytic dataset will include routinely documented variables spanning baseline demographics/anthropometrics, symptom profile and relevant clinical history, operative technique and intraoperative descriptors, and routinely captured postoperative follow-up information. Data will be extracted using a predefined data dictionary and standardized preprocessing rules to support reproducibility and reduce variability in variable definitions.
The primary analytic approach will be unsupervised clustering. Variables will be cleaned and standardized prior to modeling. Dimensionality reduction will be performed using t-distributed stochastic neighbor embedding (t-SNE), initialized with principal component analysis to improve stability. Cluster discovery will then be conducted using k-means clustering on the reduced feature space. A range of cluster solutions will be explored, and the final solution will be selected using internal validity metrics (e.g., silhouette-based measures) together with assessment of clinical interpretability. Model robustness will be evaluated through repeated runs across multiple random seeds and key parameter settings to assess stability of cluster assignments.
After cluster assignment, clusters will be characterized using descriptive and comparative statistics to identify variables that most differentiate phenotypes. Post-hoc feature relevance/importance approaches will be used to explore which demographic, clinical, and surgical factors most strongly contribute to cluster formation, with emphasis on effect sizes and clinically meaningful patterns rather than hypothesis-testing alone. Findings will be used to generate hypotheses regarding phenotypes that may be associated with greater operative complexity and different postoperative trajectories, supporting future work on predictive modeling and individualized surgical decision support.
All analyses will be conducted within a controlled institutional environment using validated statistical and data-mining software, with documented parameter settings and version tracking to enable reproducibility. Only de-identified data will be used for analysis, and results will be reported in aggregate to protect patient privacy.
238 studies on the registry are indexed under Hemorrhoids; 73 are open to participants now.
This study's planned enrollment of 100 is below the median of 151 across 49 observational studies indexed under Hemorrhoids.
Browse Hemorrhoids studies →IRCCS Policlinico S. Donato is the lead sponsor of 103 studies on the registry; 51 are open to participants now.
Counted across the registry records on this site, refreshed daily.
Patients undergoing surgery for symptomatic hemorrhoidal disease
Inclusion criteria
Consecutive patients who underwent surgery for symptomatic hemorrhoidal disease at IRCCS Policlinico San Donato between December 2024 and June 2025. Consecutive enrollment was chosen to minimize selection bias and to represent the full spectrum of disease severity in the surgical setting. Inclusion criteria Age ≥ 18 years Clinical and/or intraoperative diagnosis of symptomatic hemorrhoidal disease Availability of complete perioperative data: demographic, clinical, surgical, and postoperative variables Exclusion criteria Incomplete or missing clinical data Presence of anorectal neoplastic conditions (e.g., anal or rectal carcinoma) Anorectal surgery within the previous 6 months (to avoid confounding effects on symptoms and anatomy)
Procedure: Any surgical procedure for hemorrhoidal disease
standard hemorrhoidectomy, advanced hemorrhoidectomy, prolapsectomy, Doppler-guided procedures, or combined techniques
Internal validity of the unsupervised clustering solution (silhouette coefficient)
Silhouette coefficient of the final k-means clustering solution derived from t-SNE-reduced perioperative data. The silhouette coefficient will be used as the primary internal validity metric to quantify cluster cohesion and separation for the selected number of clusters.
Time frame: From completion of dataset extraction/cleaning through completion of clustering analysis (retrospective analysis of surgeries performed December 2024 to June 2025)
Cluster stability and reproducibility across model runs
Stability of cluster assignments across multiple random seeds and t-SNE parameter settings (including perplexity), summarized by reproducibility/consistency of membership and stability of internal validity metrics across runs.
Time frame: From completion of dataset extraction/cleaning through completion of clustering robustness analyses (retrospective analysis of surgeries performed December 2024 to June 2025)
Operative duration (proxy of operative complexity)
Operative duration (minutes) recorded in the operative report/perioperative database; compared across identified phenotypes.
Time frame: Intraoperative (day of surgery)
Postoperative pain intensity
Pain intensity as documented in routine postoperative records/follow-up notes (e.g., numeric rating scale when available or clinician-documented pain status), analyzed as pain trajectory/pattern across early and intermediate follow-up and compared across clusters.
Time frame: From surgery to 6 month postoperatively
Postoperative complications (Clavien-Dindo classification)
Any postoperative complication recorded in routine follow-up, graded according to the Clavien-Dindo system; complication rates and severity compared across clusters.
Time frame: From surgery to 1 month postoperatively (early complications) and up to 6 months postoperatively (late complications)
Time to return to routine activities
Time to return to routine activities/work when documented in follow-up notes; compared across phenotypes.
Time frame: From surgery to 1 month postoperatively
Recurrence
Recurrence patterns or persistence/return of hemorrhoid-related symptoms (e.g., bleeding/prolapse/other symptoms) as documented in routine follow-up and need for re-evaluation or additional intervention; compared across clusters.
Time frame: 1 month and 6 months postoperatively
Cluster separation metrics (beyond silhouette)
Additional internal cluster separation metrics (e.g., measures of between-cluster separation/within-cluster dispersion as implemented in the analytic workflow) reported to support interpretability of the phenotype solution.
Time frame: From completion of dataset extraction/cleaning through completion of clustering analysis (retrospective analysis of surgeries performed December 2024 to June 2025)
Between-cluster differences in clinical/anatomical/surgical characteristics
Differences across clusters in routinely collected demographic and clinical history variables (e.g., age, sex, BMI, comorbidity burden, medications, symptom profile, bowel habit characteristics), anatomical descriptors (when documented), and procedure type/technique selection.
Time frame: Baseline (preoperative assessment) and intraoperative (day of surgery)
Post-hoc feature relevance for cluster formation
Relative contribution/importance of demographic, clinical, and surgical variables to cluster formation assessed using post-hoc feature relevance approaches; used to interpret drivers of phenotype structure.
Time frame: From completion of dataset extraction/cleaning through completion of post-hoc feature relevance analyses (retrospective analysis of surgeries performed December 2024 to June 2025)
PDFs hosted by the registry, ClinicalTrials.gov.
Plan to share: No
Ran from Dec 2024 to primary completion in Dec 2025, 12 months.
How these figures are worked out, and which studies are left out of them.
Eligibility is decided by the study team. Share this record with your doctor or contact the team directly.
No contact was published for this record. The registry link below has the sponsor’s details.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.