Ignite Creation Date:
2026-03-26 @ 3:21 PM
Ignite Modification Date:
2026-04-01 @ 10:35 PM
Study NCT ID:
NCT07427927
Status:
ACTIVE_NOT_RECRUITING
Last Update Posted:
2026-02-23
First Post:
2026-02-05
Is NOT Gene Therapy:
True
Has Adverse Events:
False
Brief Title:
Data-driven Clustering in Hemorrhoid Surgery: Retrospective Monocentric Study for the Identification of Clinical Phenotypes
Sponsor:
Organization:
Raw JSON
{'hasResults': False, 'derivedSection': {'miscInfoModule': {'versionHolder': '2026-03-25'}, 'conditionBrowseModule': {'meshes': [{'id': 'D006484', 'term': 'Hemorrhoids'}], 'ancestors': [{'id': 'D012002', 'term': 'Rectal Diseases'}, {'id': 'D007410', 'term': 'Intestinal Diseases'}, {'id': 'D005767', 'term': 'Gastrointestinal Diseases'}, {'id': 'D004066', 'term': 'Digestive System Diseases'}, {'id': 'D014652', 'term': 'Vascular Diseases'}, {'id': 'D002318', 'term': 'Cardiovascular Diseases'}]}}, 'documentSection': {'largeDocumentModule': {'largeDocs': [{'date': '2026-01-20', 'size': 243349, 'label': 'Study Protocol and Statistical Analysis Plan', 'hasIcf': False, 'hasSap': True, 'filename': 'Prot_SAP_000.pdf', 'typeAbbrev': 'Prot_SAP', 'uploadDate': '2026-02-05T06:53', 'hasProtocol': True}]}}, 'protocolSection': {'designModule': {'studyType': 'OBSERVATIONAL', 'designInfo': {'timePerspective': 'RETROSPECTIVE', 'observationalModel': 'COHORT'}, 'enrollmentInfo': {'type': 'ESTIMATED', 'count': 100}, 'patientRegistry': False}, 'statusModule': {'overallStatus': 'ACTIVE_NOT_RECRUITING', 'startDateStruct': {'date': '2024-12-01', 'type': 'ACTUAL'}, 'expandedAccessInfo': {'hasExpandedAccess': False}, 'statusVerifiedDate': '2026-01', 'completionDateStruct': {'date': '2026-04', 'type': 'ESTIMATED'}, 'lastUpdateSubmitDate': '2026-02-16', 'studyFirstSubmitDate': '2026-02-05', 'studyFirstSubmitQcDate': '2026-02-16', 'lastUpdatePostDateStruct': {'date': '2026-02-23', 'type': 'ACTUAL'}, 'studyFirstPostDateStruct': {'date': '2026-02-23', 'type': 'ACTUAL'}, 'primaryCompletionDateStruct': {'date': '2025-12-31', 'type': 'ACTUAL'}}, 'outcomesModule': {'otherOutcomes': [{'measure': 'Cluster separation metrics (beyond silhouette)', 'timeFrame': 'From completion of dataset extraction/cleaning through completion of clustering analysis (retrospective analysis of surgeries performed December 2024 to June 2025)', 'description': '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.'}, {'measure': 'Between-cluster differences in clinical/anatomical/surgical characteristics', 'timeFrame': 'Baseline (preoperative assessment) and intraoperative (day of surgery)', 'description': '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.'}, {'measure': 'Post-hoc feature relevance for cluster formation', 'timeFrame': 'From completion of dataset extraction/cleaning through completion of post-hoc feature relevance analyses (retrospective analysis of surgeries performed December 2024 to June 2025)', 'description': '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.'}], 'primaryOutcomes': [{'measure': 'Internal validity of the unsupervised clustering solution (silhouette coefficient)', 'timeFrame': 'From completion of dataset extraction/cleaning through completion of clustering analysis (retrospective analysis of surgeries performed December 2024 to June 2025)', 'description': '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.'}], 'secondaryOutcomes': [{'measure': 'Cluster stability and reproducibility across model runs', 'timeFrame': 'From completion of dataset extraction/cleaning through completion of clustering robustness analyses (retrospective analysis of surgeries performed December 2024 to June 2025)', 'description': '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.'}, {'measure': 'Operative duration (proxy of operative complexity)', 'timeFrame': 'Intraoperative (day of surgery)', 'description': 'Operative duration (minutes) recorded in the operative report/perioperative database; compared across identified phenotypes.'}, {'measure': 'Postoperative pain intensity', 'timeFrame': 'From surgery to 6 month postoperatively', 'description': '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.'}, {'measure': 'Postoperative complications (Clavien-Dindo classification)', 'timeFrame': 'From surgery to 1 month postoperatively (early complications) and up to 6 months postoperatively (late complications)', 'description': 'Any postoperative complication recorded in routine follow-up, graded according to the Clavien-Dindo system; complication rates and severity compared across clusters.'}, {'measure': 'Time to return to routine activities', 'timeFrame': 'From surgery to 1 month postoperatively', 'description': 'Time to return to routine activities/work when documented in follow-up notes; compared across phenotypes.'}, {'measure': 'Recurrence', 'timeFrame': '1 month and 6 months postoperatively', 'description': '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.'}]}, 'oversightModule': {'oversightHasDmc': False, 'isFdaRegulatedDrug': False, 'isFdaRegulatedDevice': False}, 'conditionsModule': {'keywords': ['Hemorrhoidal Disease', 'Unsupervised Machine Learning'], 'conditions': ['Hemorrhoid', 'Hemorrhoid Prolapse']}, 'referencesModule': {'references': [{'type': 'BACKGROUND', 'citation': 'Bernabé-Díaz JA, Franco M, Vivo JM, Fernández-Breis JT. Optimizing clustering-based analytical methods with trimmed and sparse clustering. Computers in Biology and Medicine. 2025;194:110436. doi:10.1016/j.compbiomed.2025.110436'}, {'type': 'BACKGROUND', 'citation': 'Xiao C, Hong S, Huang W. Optimizing graph layout by t-SNE perplexity estimation. Int J Data Sci Anal. 2023;15(2):159-171. doi:10.1007/s41060-022-00348-7'}, {'type': 'BACKGROUND', 'citation': 'Goldenholz, D.M.; Sun, H.; Ganglberger, W.; Westover, M.B. Sample Size Analysis for Machine Learning Clinical Validation Studies. Biomedicines 2023, 11, 685. https://doi.org/10.3390/ biomedicines11030685'}, {'pmid': '34485376', 'type': 'BACKGROUND', 'citation': 'De Marco S, Tiso D. Lifestyle and Risk Factors in Hemorrhoidal Disease. Front Surg. 2021 Aug 18;8:729166. doi: 10.3389/fsurg.2021.729166. eCollection 2021.'}, {'pmid': '27148566', 'type': 'BACKGROUND', 'citation': 'Robinson PN, Mungall CJ, Haendel M. Capturing phenotypes for precision medicine. Cold Spring Harb Mol Case Stud. 2015 Oct;1(1):a000372. doi: 10.1101/mcs.a000372.'}, {'pmid': '39228195', 'type': 'BACKGROUND', 'citation': "Brillantino A, Renzi A, Talento P, Brusciano L, Marano L, Grillo M, Maglio MN, Foroni F, Palumbo A, Sotelo MLS, Vicenzo L, Lanza M, Frezza G, Antropoli M, Gambardella C, Monaco L, Ferrante I, Izzo D, Giordano A, Pinto M, Fantini C, Gasparrini M, Schiano Di Visconte M, Milazzo F, Ferreri G, Braini A, Cocozza U, Pezzatini M, Gianfreda V, Di Leo A, Landolfi V, Favetta U, Agradi S, Marino G, Varriale M, Mongardini M, Pagano CEFA, Contul RB, Gallese N, Ucchino G, D'Ambra M, Rizzato R, Sarzo G, Masci B, Da Pozzo F, Ascanelli S, Liguori P, Pezzolla A, Iacobellis F, Boriani E, Cudazzo E, Babic F, Geremia C, Bussotti A, Cicconi M, Sarno AD, Mongardini FM, Brescia A, Lenisa L, Mistrangelo M, Zuin M, Mozzon M, Chiriatti AP, Bottino V, Ferronetti A, Rispoli C, Carbone L, Calabro G, Tirro A, de Vito D, Ioia G, Lamanna GL, Asciore L, Greco E, Bianchi P, D'Oriano G, Stazi A, Antonacci N, Renzo RMD, Poto GE, Ferulano GP, Longo A, Docimo L. The Italian Unitary Society of Colon-Proctology (Societa Italiana Unitaria di Colonproctologia) guidelines for the management of acute and chronic hemorrhoidal disease. Ann Coloproctol. 2024 Aug;40(4):287-320. doi: 10.3393/ac.2023.00871.0124. Epub 2024 Aug 30."}, {'pmid': '37458757', 'type': 'BACKGROUND', 'citation': 'De Gregorio MA, Guirola JA, Serrano-Casorran C, Urbano J, Gutierrez C, Gregorio A, Sierre S, Ciampi-Dopazo JJ, Bernal R, Gil I, De Blas I, Sanchez-Ballestin M, Millera A. Catheter-directed hemorrhoidal embolization for rectal bleeding due to hemorrhoids (Goligher grade I-III): prospective outcomes from a Spanish emborrhoid registry. Eur Radiol. 2023 Dec;33(12):8754-8763. doi: 10.1007/s00330-023-09923-3. Epub 2023 Jul 17.'}, {'pmid': '40493094', 'type': 'BACKGROUND', 'citation': 'van Oostendorp JY, Grossi U, Hoxhaj I, Kimman ML, Kuiper SZ, Breukink SO, Han-Geurts IJM, Gallo G. Limitations of the Goligher classification in randomized trials for hemorrhoidal disease: a qualitative systematic review of selection criteria. Tech Coloproctol. 2025 Jun 10;29(1):133. doi: 10.1007/s10151-025-03170-y.'}, {'pmid': '35141793', 'type': 'BACKGROUND', 'citation': 'Dekker L, Han-Geurts IJM, Grossi U, Gallo G, Veldkamp R. Is the Goligher classification a valid tool in clinical practice and research for hemorrhoidal disease? Tech Coloproctol. 2022 May;26(5):387-392. doi: 10.1007/s10151-022-02591-3. Epub 2022 Feb 9.'}, {'pmid': '34540753', 'type': 'BACKGROUND', 'citation': 'Bozovic B, Radoicic M, Jankovic S, Andelkovic J, Kostic M. Pharmacoeconomic Aspects of Treating Hemorrhoidal Disease-Cost of Illness Study Based on Data from Balkan Country with Recent History of Social and Economic Transition. Iran J Public Health. 2021 Jun;50(6):1288-1290. doi: 10.18502/ijph.v50i6.6433. No abstract available.'}, {'pmid': '36876020', 'type': 'BACKGROUND', 'citation': 'Rorvik HD, Davidsen M, Gierloff MC, Brandstrup B, Olaison G. Quality of life in patients with hemorrhoidal disease. Surg Open Sci. 2023 Feb 24;12:22-28. doi: 10.1016/j.sopen.2023.02.004. eCollection 2023 Mar.'}, {'pmid': '34527700', 'type': 'BACKGROUND', 'citation': "Pata F, Gallo G, Pellino G, Vigorita V, Podda M, Di Saverio S, D'Ambrosio G, Sammarco G. Evolution of Surgical Management of Hemorrhoidal Disease: An Historical Overview. Front Surg. 2021 Aug 30;8:727059. doi: 10.3389/fsurg.2021.727059. eCollection 2021."}, {'pmid': '41196608', 'type': 'BACKGROUND', 'citation': 'Roberts K. What Are Hemorrhoids? JAMA. 2025 Nov 6. doi: 10.1001/jama.2025.17253. Online ahead of print.'}, {'pmid': '37901411', 'type': 'BACKGROUND', 'citation': 'Wang L, Ni J, Hou C, Wu D, Sun L, Jiang Q, Cai Z, Fan W. Time to change? Present and prospects of hemorrhoidal classification. Front Med (Lausanne). 2023 Oct 11;10:1252468. doi: 10.3389/fmed.2023.1252468. eCollection 2023.'}, {'pmid': '38318578', 'type': 'BACKGROUND', 'citation': 'Al-Masoudi RO, Shosho R, Alquhra D, Alzahrani M, Hemdi M, Alshareef L. Prevalence of Hemorrhoids and the Associated Risk Factors Among the General Adult Population in Makkah, Saudi Arabia. Cureus. 2024 Jan 3;16(1):e51612. doi: 10.7759/cureus.51612. eCollection 2024 Jan.'}, {'pmid': '40952854', 'type': 'BACKGROUND', 'citation': 'Error in Figure 4 and References. JAMA. 2025 Oct 7;334(13):1203. doi: 10.1001/jama.2025.17752. No abstract available.'}]}, 'descriptionModule': {'briefSummary': '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.', 'detailedDescription': '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.\n\nThis 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.\n\nThe 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.\n\nAfter 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.\n\nAll 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.'}, 'eligibilityModule': {'sex': 'ALL', 'stdAges': ['ADULT', 'OLDER_ADULT'], 'minimumAge': '18 Years', 'samplingMethod': 'NON_PROBABILITY_SAMPLE', 'studyPopulation': 'Patients undergoing surgery for symptomatic hemorrhoidal disease', 'healthyVolunteers': False, 'eligibilityCriteria': 'Inclusion criteria\n\n* Age ≥ 18 years\n* Clinical and/or intraoperative diagnosis of symptomatic hemorrhoidal disease\n* Availability of complete perioperative data: demographic, clinical, surgical, and postoperative variables Exclusion criteria\n* Incomplete or missing clinical data\n* Presence of anorectal neoplastic conditions (e.g., anal or rectal carcinoma)\n* Anorectal surgery within the previous 6 months (to avoid confounding effects on symptoms and anatomy)'}, 'identificationModule': {'nctId': 'NCT07427927', 'acronym': 'PROCTO-CLUSTER', 'briefTitle': 'Data-driven Clustering in Hemorrhoid Surgery: Retrospective Monocentric Study for the Identification of Clinical Phenotypes', 'organization': {'class': 'OTHER', 'fullName': 'IRCCS Policlinico S. Donato'}, 'officialTitle': 'Data-driven Clustering in Hemorrhoid Surgery: Retrospective Monocentric Study for the Identification of Clinical Phenotypes', 'orgStudyIdInfo': {'id': 'CET 18-2026'}}, 'armsInterventionsModule': {'armGroups': [{'label': 'patients who underwent surgery for symptomatic hemorrhoidal disease', 'description': '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.\n\nInclusion 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)', 'interventionNames': ['Procedure: Any surgical procedure for hemorrhoidal disease']}], 'interventions': [{'name': 'Any surgical procedure for hemorrhoidal disease', 'type': 'PROCEDURE', 'description': 'standard hemorrhoidectomy, advanced hemorrhoidectomy, prolapsectomy, Doppler-guided procedures, or combined techniques', 'armGroupLabels': ['patients who underwent surgery for symptomatic hemorrhoidal disease']}]}, 'contactsLocationsModule': {'locations': [{'zip': '20097', 'city': 'San Donato Milanese', 'state': 'Milan', 'country': 'Italy', 'facility': 'IRCCS Policlinico San Donato', 'geoPoint': {'lat': 45.41047, 'lon': 9.26838}}]}, 'ipdSharingStatementModule': {'ipdSharing': 'NO'}, 'sponsorCollaboratorsModule': {'leadSponsor': {'name': 'IRCCS Policlinico S. Donato', 'class': 'OTHER'}, 'responsibleParty': {'type': 'SPONSOR'}}}}