ArticleDiseases of the colon and rectum2026
Risk Prediction for Delayed Bleeding After Endoscopic Submucosal Dissection in Colorectal Precancerous Lesions Using Artificial Intelligence: Retrospective Clinical Trial.
Article in Diseases of the colon and rectum, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Not yet cited in PubMed.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
0 citing papers in PubMed.
No citing paper in PubMed yet.
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
14 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
backgroundDelayed bleeding is a common complication after endoscopic submucosal dissection.
objectiveOur study aimed to assess risk factors for delayed bleeding after endoscopic submucosal dissection in patients with colorectal precancerous lesions and to construct a risk prediction model.
designRetrospective case-control study. SETTINGS: Multicenter study. PATIENTS: A total of 956 patients with colorectal precancerous lesions were included, of whom 72 had delayed bleeding after endoscopic submucosal dissection.
main outcome measuresThe primary clinical outcome assessed in this study was delayed bleeding after endoscopic submucosal dissection, defined as active bleeding necessitating endoscopic hemostasis after a second endoscopic examination within 6 hours to 28 days after endoscopic submucosal dissection.
resultsA total of 72 patients (7.5%) developed delayed bleeding after endoscopic submucosal dissection. Through both univariate and multivariate analyses, we identified 5 independent risk factors from the initial pool of 15 factors considered relevant to delayed bleeding after endoscopic submucosal dissection. These risk factors include male sex, age 65 years or older, lesion size ≥30 mm, procedure time ≥120 minutes, and lesions located in the rectum. Using these identified risk factors, we constructed an XGBoost model to classify patients into low-risk and high-risk categories based on the model's predictive scores. The low-risk group demonstrated a delayed bleeding rate of 4.0% (95% CI, 2.4-5.6) in contrast to a delayed bleeding rate of 13.1% (95% CI, 9.7-16.5) in the high-risk group, as projected by our model. LIMITATIONS: The restricted number of participating centers, the relatively small sample size of patients with delayed bleeding, and potential selection bias.
conclusionsThis model could precisely forecast the risk of delayed bleeding in patients with colorectal precancerous lesions after endoscopic submucosal dissection. See Video Abstract . PREDICCIN DEL RIESGO DE HEMORRAGIA TARDA TRAS LA DISECCIN ENDOSCPICA DE LA SUBMUCOSA EN LESIONES PRECANCEROSAS COLORRECTALES MEDIANTE INTELIGENCIA ARTIFICIAL ENSAYO CLNICO RETROSPECTIVO: ANTECEDENTES:La hemorragia tardía es una complicación frecuente tras la disección endoscópica submucosa.OBJETIVO:El objetivo de nuestro estudio fue evaluar los factores de riesgo de hemorragia tardía tras la disección endoscópica submucosa en pacientes con lesiones precancerosas colorrectales y construir un modelo de predicción del riesgo.DISEÑO:Estudio retrospectivo de casos y controles.ENTORNO:Estudio multicéntrico.PACIENTES:Un total de 956 pacientes con lesiones precancerosas colorrectales, de los cuales 72 presentaron hemorragia tardía tras la disección endoscópica de la submucosa.PRINCIPALES MEDIDAS DE RESULTADO:El resultado clínico principal evaluado en este estudio fue la hemorragia tardía tras la disección endoscópica de la submucosa, definida como hemorragia activa que requiere hemostasia endoscópica tras una segunda exploración endoscópica en las 6 horas a 28 días siguientes a la disección endoscópica de la submucosa.RESULTADOS:Un total de 72 pacientes (7,5 %) desarrollaron hemorragia tardía tras la disección endoscópica de la submucosa. Mediante análisis univariantes y multivariantes, identificamos cinco factores de riesgo independientes a partir del conjunto inicial de 15 factores considerados relevantes para la hemorragia tardía tras la disección endoscópica de la submucosa. Estos factores de riesgo incluyen el sexo masculino, la edad ≥ 65 años, el tamaño de la lesión ≥ 30 mm, la duración del procedimiento ≥ 120 minutos y las lesiones localizadas en el recto. Utilizando estos factores de riesgo identificados, construimos un modelo XGBoost para clasificar a los pacientes en categorías de bajo riesgo y alto riesgo basándonos en las puntuaciones predictivas del modelo. El grupo de bajo riesgo mostró una tasa de hemorragia tardía del 4,0 % (IC del 95 %, 2,4-5,6), en contraste con una tasa de hemorragia tardía del 13,1 % (IC del 95 %, 9,7-16,5) en el grupo de alto riesgo, según las previsiones de nuestro modelo.LIMITACIONES:El número restringido de centros participantes, el tamaño relativamente pequeño de la muestra de pacientes con hemorragia tardía y el posible sesgo de selección.CONCLUSIONES:Este modelo podría predecir con precisión el riesgo de hemorragia tardía en pacientes con lesiones precancerosas colorrectales tras una disección endoscópica de la submucosa. (AI-generated translation ).
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.