Sara Zarraquiños
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sara Zarraquiños has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Astrid Irene Díez-Martín
Grupo de Investigación en Oncología Digestiva-Ourense (GIODO), Fundación Biomédica Galicia Sur, 32003 Ourense, Spain
7 shared publications - David Remedios
Department of Gastroenterology, Hospital Universitario de Ourense, Centro de Investigación Biomédica en Red de Enfermedades Hepáticas y Digestivas (CIBEREHD), 32005 Ourense, Spain
7 shared publications - Joaquín Cubiella
Grupo de Investigación en Oncología Digestiva-Ourense (GIODO), Fundación Biomédica Galicia Sur, 32003 Ourense, Spain
7 shared publications - Luisa De-Castro
Department of Gastroenterology, Complexo Hospitalario Universitario de Vigo, 36312 Vigo, Spain
5 shared publications - Sara Alonso Lorenzo
Department of Gastroenterology, Complexo Hospitalario Universitario de Vigo, 36312 Vigo, Spain
5 shared publications - Alba Nogueira-Rodríguez
Department of Computer Science, ESEI - Escuela Superior de Ingeniería Informática, Universidade de Vigo, Ourense 32004, Spain; Next Generation Computer Systems Research Group (SING), Galicia Sur Health Research Institute (IIS Galicia Sur), SERGAS-UVIGO, Spain
4 shared publications
Latest Publications
- Open Access
- 8 October 2026
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 27 (19) , 8936
Beyond Taxonomy: Fungal Nutraceutical Supplementation Modifies the Functional Potential of the Gut Microbiome in Colorectal Cancer
The gut microbiome is increasingly recognized as an important determinant of host immune regulation, intestinal homeostasis, and recovery after colorectal cancer (CRC) surgery. Although our previous randomized, double-blind, placebo-controlled clinical trial demonstrated that fungal nutraceutical supplementation with Micodigest® was associated with favorable taxonomic and systemic inflammatory changes in patients undergoing CRC surgery with curative intent, the functional consequences of this intervention remain poorly understood. Here, we performed a functional metagenomic analysis of fecal samples collected from patients enrolled in the original clinical trial to investigate whether Micodigest® supplementation was associated with changes in the functional potential of the gut microbiome. A total of 37 patients were analyzed, including 24 receiving Micodigest® and 13 receiving placebo, with paired samples collected before supplementation and after 4–6 weeks of intervention. Shallow shotgun metagenomic sequencing was performed, and microbial functional potential was characterized using KEGG Orthologues (KOs). Differential abundance analysis identified 14 significantly different KOs between groups at baseline and 23 after intervention, with no overlap between the two sets of orthologues. Following supplementation, Micodigest®-treated patients exhibited increased representation of functions related to CRISPR-associated systems, bacteriophage biology, and chitin-derived carbohydrate utilization, together with reduced representation of nutrient acquisition systems, conjugative transfer, sulfur metabolism, and components of the Wood–Ljungdahl pathway. These functional signatures suggest coordinated changes in microbial ecological adaptation, nutrient utilization, genetic exchange, and metabolic activity following fungal nutraceutical supplementation. Integration with previously reported taxonomic and inflammatory findings supports the hypothesis that Micodigest® may promote coordinated remodeling of the gut microbiome and host–microbiota interactions during the perioperative period. Although the present study cannot establish causality or directly infer microbial activity from metagenomic potential, these findings provide novel functional insights into the microbiome response to fungal nutraceutical supplementation in patients with CRC and highlight functional metagenomics as a valuable complement to taxonomic profiling.
- 8 October 2026
- Published by MDPI AG in International Journal of Molecular Sciences
- Vol. 27 (19) , 8936
Open AccessBeyond Taxonomy: Fungal Nutraceutical Supplementation Modifies the Functional Potential of the Gut Microbiome in Colorectal Cancer
The gut microbiome is increasingly recognized as an important determinant of host immune regulation, intestinal homeostasis, and recovery after colorectal cancer (CRC) surgery. Although our previous randomized, double-blind, placebo-controlled clinical trial demonstrated that fungal nutraceutical supplementation with Micodigest® was associated with favorable taxonomic and systemic inflammatory changes in patients undergoing CRC surgery with curative intent, the functional consequences of this intervention remain poorly understood. Here, we performed a functional metagenomic analysis of fecal samples collected from patients enrolled in the original clinical trial to investigate whether Micodigest® supplementation was associated with changes in the functional potential of the gut microbiome. A total of 37 patients were analyzed, including 24 receiving Micodigest® and 13 receiving placebo, with paired samples collected before supplementation and after 4–6 weeks of intervention. Shallow shotgun metagenomic sequencing was performed, and microbial functional potential was characterized using KEGG Orthologues (KOs). Differential abundance analysis identified 14 significantly different KOs between groups at baseline and 23 after intervention, with no overlap between the two sets of orthologues. Following supplementation, Micodigest®-treated patients exhibited increased representation of functions related to CRISPR-associated systems, bacteriophage biology, and chitin-derived carbohydrate utilization, together with reduced representation of nutrient acquisition systems, conjugative transfer, sulfur metabolism, and components of the Wood–Ljungdahl pathway. These functional signatures suggest coordinated changes in microbial ecological adaptation, nutrient utilization, genetic exchange, and metabolic activity following fungal nutraceutical supplementation. Integration with previously reported taxonomic and inflammatory findings supports the hypothesis that Micodigest® may promote coordinated remodeling of the gut microbiome and host–microbiota interactions during the perioperative period. Although the present study cannot establish causality or directly infer microbial activity from metagenomic potential, these findings provide novel functional insights into the microbiome response to fungal nutraceutical supplementation in patients with CRC and highlight functional metagenomics as a valuable complement to taxonomic profiling.
- Open Access
- 30 October 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (21) , 2751
Clinical Evaluation of PolyDeep, A Computer-Aided Detection System: A Multicenter Randomized Tandem Colonoscopy Trial
Background/Objectives: Computer-aided detection (CADe) systems are increasingly used in endoscopy to enhance lesion recognition. PolyDeep is a CADe/x tool previously assessed in an observational study. The aim of our study is to determine if PolyDeep-assisted colonoscopy reduces the adenoma miss rate (AMR) compared with conventional colonoscopy. Methods: We carried out a multicenter randomized controlled trial with a tandem colonoscopy design in participants from a colorectal cancer screening program (positive fecal immunochemical test-FIT or surveillance). Expert endoscopists performed all colonoscopies, and patients were allocated to groups by a computer-generated sequence. The primary endpoint was AMR; secondary endpoints included polyp miss rate (PMR), serrated lesion miss rate (SLMR) and advanced polyp miss rate (APMR). Results: From May to November 2023, we recruited 260 patients and excluded 20, leaving 240 for analysis. Baseline characteristics were balanced between groups (62.1% male; mean age 62.3 ± 6.5 years; 65.8% FIT-positive; mean first withdrawal time 13:38 ± 08:07 min; mean second withdrawal time 07:50 ± 03:38 min; lesion detection rate 76.6%; mean polyps per patient 3.4 ± 3.1). We did not find statistically significant differences between PolyDeep-assisted and conventional colonoscopy groups in AMR (21.3% vs. 18.1%, p = 0.5), PMR (21.8% vs. 20.3%, p = 0.7), SLMR (23.4% vs. 25.6%, p = 0.9) or APMR (7.3% vs. 11.3%, p = 0.5). In the subgroup analysis according to indication, we did not find any statistically significant differences. Conclusions: In the context of a CRC screening program, PolyDeep-assisted colonoscopy did not reduce AMR.
- 30 October 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (21) , 2751
Open AccessClinical Evaluation of PolyDeep, A Computer-Aided Detection System: A Multicenter Randomized Tandem Colonoscopy Trial
Background/Objectives: Computer-aided detection (CADe) systems are increasingly used in endoscopy to enhance lesion recognition. PolyDeep is a CADe/x tool previously assessed in an observational study. The aim of our study is to determine if PolyDeep-assisted colonoscopy reduces the adenoma miss rate (AMR) compared with conventional colonoscopy. Methods: We carried out a multicenter randomized controlled trial with a tandem colonoscopy design in participants from a colorectal cancer screening program (positive fecal immunochemical test-FIT or surveillance). Expert endoscopists performed all colonoscopies, and patients were allocated to groups by a computer-generated sequence. The primary endpoint was AMR; secondary endpoints included polyp miss rate (PMR), serrated lesion miss rate (SLMR) and advanced polyp miss rate (APMR). Results: From May to November 2023, we recruited 260 patients and excluded 20, leaving 240 for analysis. Baseline characteristics were balanced between groups (62.1% male; mean age 62.3 ± 6.5 years; 65.8% FIT-positive; mean first withdrawal time 13:38 ± 08:07 min; mean second withdrawal time 07:50 ± 03:38 min; lesion detection rate 76.6%; mean polyps per patient 3.4 ± 3.1). We did not find statistically significant differences between PolyDeep-assisted and conventional colonoscopy groups in AMR (21.3% vs. 18.1%, p = 0.5), PMR (21.8% vs. 20.3%, p = 0.7), SLMR (23.4% vs. 25.6%, p = 0.9) or APMR (7.3% vs. 11.3%, p = 0.5). In the subgroup analysis according to indication, we did not find any statistically significant differences. Conclusions: In the context of a CRC screening program, PolyDeep-assisted colonoscopy did not reduce AMR.
- Open Access
- 12 September 2025
- Published by MDPI AG in Preprints.org
Clinical Evaluation of PolyDeep, a Computer Aided Detection system: A Multicenter Randomized Tandem Colonoscopy Trial
Background/Objectives: Computer-aided detection (CADe) systems are increasingly used in endoscopy to enhance lesion recognition. PolyDeep is a CADe/x tool previously assessed in an observational study. The aim of our study is to determine if PolyDeep-assisted colonoscopy reduces the adenoma miss rate (AMR) compared with conventional colonoscopy. Methods: We carried out a multicenter randomized controlled trial with a tandem colonoscopy design in participants from a colorectal cancer screening program (positive fecal immunochemical test-FIT or surveillance). Expert endoscopists performed all colonoscopies, and patients were allocated to groups by a computer-generated sequence. The primary endpoint was AMR; secondary endpoints included polyp miss rate (PMR), serrated lesion miss rate (SLMR) and advanced polyp miss rate (APMR). Results: From May to November 2023, we recruited 260 patients and excluded 20, leaving 240 for analysis. Baseline characteristics were balanced between groups (62.1% male; mean age 62.3 ± 6.5 years; 65.8% FIT-positive; mean first withdrawal time 13:38 ± 08:07 minutes; mean second withdrawal time 07:50 ± 03:38 minutes; lesion detection rate 76.6%; mean polyps per patient 3.4 ± 3.1). We did not find statistically significant differences between PolyDeep-assisted and conventional colonoscopy groups in AMR (21.3% vs 18.1%, p = 0.5), PMR (21.8% vs 20.3%, p = 0.7), SLMR (23.4% vs 25.6%, p = 0.9) or APMR (7.3% vs 11.3%, p = 0.5). In the subgroup analysis according to indication, we did not find any statistically significant differences. Conclusions: In the context of a CRC screening program, PolyDeep-assisted colonoscopy did not reduce AMR.
- 12 September 2025
- Published by MDPI AG in Preprints.org
Open AccessClinical Evaluation of PolyDeep, a Computer Aided Detection system: A Multicenter Randomized Tandem Colonoscopy Trial
Background/Objectives: Computer-aided detection (CADe) systems are increasingly used in endoscopy to enhance lesion recognition. PolyDeep is a CADe/x tool previously assessed in an observational study. The aim of our study is to determine if PolyDeep-assisted colonoscopy reduces the adenoma miss rate (AMR) compared with conventional colonoscopy. Methods: We carried out a multicenter randomized controlled trial with a tandem colonoscopy design in participants from a colorectal cancer screening program (positive fecal immunochemical test-FIT or surveillance). Expert endoscopists performed all colonoscopies, and patients were allocated to groups by a computer-generated sequence. The primary endpoint was AMR; secondary endpoints included polyp miss rate (PMR), serrated lesion miss rate (SLMR) and advanced polyp miss rate (APMR). Results: From May to November 2023, we recruited 260 patients and excluded 20, leaving 240 for analysis. Baseline characteristics were balanced between groups (62.1% male; mean age 62.3 ± 6.5 years; 65.8% FIT-positive; mean first withdrawal time 13:38 ± 08:07 minutes; mean second withdrawal time 07:50 ± 03:38 minutes; lesion detection rate 76.6%; mean polyps per patient 3.4 ± 3.1). We did not find statistically significant differences between PolyDeep-assisted and conventional colonoscopy groups in AMR (21.3% vs 18.1%, p = 0.5), PMR (21.8% vs 20.3%, p = 0.7), SLMR (23.4% vs 25.6%, p = 0.9) or APMR (7.3% vs 11.3%, p = 0.5). In the subgroup analysis according to indication, we did not find any statistically significant differences. Conclusions: In the context of a CRC screening program, PolyDeep-assisted colonoscopy did not reduce AMR.
- Open Access
- 13 May 2025
- Published by MDPI AG in Biomedicines
- Vol. 13 (5) , 1185
The Effect of Fungal Nutraceutical Supplementation on Postoperative Complications, Inflammatory Factors and Fecal Microbiota in Patients Undergoing Colorectal Cancer Surgery with Curative Intent: A Randomized, Placebo-Controlled, Double-Blind Clinical Trial
Background/Objectives: The combination of different fungal extracts could be beneficial to cancer patients due to their role in gut microbiota modulation and anti-inflammatory activity. The study aimed to evaluate whether fungal extract supplementation reduces postsurgical complications in patients with colorectal cancer undergoing curative surgery. Methods: Patients were randomized to receive the nutraceutical Micodigest 2.0 or a placebo until surgery. Surgical complications were evaluated using the Clavien-Dindo classification. We also assessed the effect of the nutraceutical on gut microbiota composition, inflammatory response, nutritional status, and quality of life. A subanalysis based on surgery type (robotic vs. non-robotic) was performed. Results: We included 46 patients who met the inclusion criteria, with 27 randomized to the intervention group and 19 to the placebo group, receiving treatment for three (2–4) weeks. Non-robotic surgery was performed in 35 (76.1%) patients. We found non-significant differences in postoperative complications (Micodigest 2.0: 25.9%, placebo: 26.3%; p = 0.9). In non-robotic surgery, we identified a non-significant reduction in postoperative complications (Micodigest 2.0: 25.0%, placebo: 36.4%; p = 0.7), as well as a significant increase in lymphocyte levels and a reduction in the neutrophil-to-lymphocyte ratio (p = 0.02). Micodigest 2.0 supplementation was also associated with significant changes in gut microbiota composition, as indicated by a decreased relative abundance of the phyla Firmicutes (p = 0.004) and Actinobacteria (p = 0.04). Conclusions: Micodigest 2.0 supplementation was associated with non-significant reductions in postoperative complications and significant modifications in gut microbiota composition. Limitations: The trial did not reach the calculated sample size.
- 13 May 2025
- Published by MDPI AG in Biomedicines
- Vol. 13 (5) , 1185
Open AccessThe Effect of Fungal Nutraceutical Supplementation on Postoperative Complications, Inflammatory Factors and Fecal Microbiota in Patients Undergoing Colorectal Cancer Surgery with Curative Intent: A Randomized, Placebo-Controlled, Double-Blind Clinical Trial
Background/Objectives: The combination of different fungal extracts could be beneficial to cancer patients due to their role in gut microbiota modulation and anti-inflammatory activity. The study aimed to evaluate whether fungal extract supplementation reduces postsurgical complications in patients with colorectal cancer undergoing curative surgery. Methods: Patients were randomized to receive the nutraceutical Micodigest 2.0 or a placebo until surgery. Surgical complications were evaluated using the Clavien-Dindo classification. We also assessed the effect of the nutraceutical on gut microbiota composition, inflammatory response, nutritional status, and quality of life. A subanalysis based on surgery type (robotic vs. non-robotic) was performed. Results: We included 46 patients who met the inclusion criteria, with 27 randomized to the intervention group and 19 to the placebo group, receiving treatment for three (2–4) weeks. Non-robotic surgery was performed in 35 (76.1%) patients. We found non-significant differences in postoperative complications (Micodigest 2.0: 25.9%, placebo: 26.3%; p = 0.9). In non-robotic surgery, we identified a non-significant reduction in postoperative complications (Micodigest 2.0: 25.0%, placebo: 36.4%; p = 0.7), as well as a significant increase in lymphocyte levels and a reduction in the neutrophil-to-lymphocyte ratio (p = 0.02). Micodigest 2.0 supplementation was also associated with significant changes in gut microbiota composition, as indicated by a decreased relative abundance of the phyla Firmicutes (p = 0.004) and Actinobacteria (p = 0.04). Conclusions: Micodigest 2.0 supplementation was associated with non-significant reductions in postoperative complications and significant modifications in gut microbiota composition. Limitations: The trial did not reach the calculated sample size.
- Open Access
- 24 February 2025
- Published by MDPI AG in Preprints.org
The Effect of Fungal Nutraceutical Supplementation on Postoperative Complications, Inflammatory Factors and Fecal Microbiota in Patients Undergoing Colorectal Cancer Surgery with Curative Intent: A Randomized, Placebo-Controlled, Double-Blind Clinical Trial
Background/Objectives: The combination of different fungal extracts could be beneficial to cancer patients due to their role in gut microbiota modulation and anti-inflammatory activity. The study aimed to evaluate whether fungal extract supplementation reduces postsurgical complications in patients with colorectal cancer undergoing curative surgery. Methods: Patients were randomized to receive the nutraceutical Micodigest 2.0 or a placebo until surgery. Surgical complications were evaluated using the Clavien-Dindo classification. We also assessed the effect of the nutraceutical on gut microbiota composition, inflammatory response, nutritional status, and quality of life. A subanalysis based on surgery type (robotic vs. non-robotic) was performed. Results: We included 46 patients who met the inclusion criteria, with 27 randomized to the intervention group and 19 to the placebo group, receiving treatment for 3 [2–4] weeks. Non-robotic surgery was performed in 35 (76.1%) patients. We found non-significant differences in postoperative complications (Micodigest 2.0: 25.9%, placebo: 26.3%; p = 0.9). In non-robotic surgery, we identified a non-significant reduction in postoperative complications (Micodigest 2.0: 25.0%, placebo: 36.4%; p = 0.7), as well as a significant increase in lymphocyte levels and a reduction in the neutrophil-to-lymphocyte ratio (p = 0.02). Micodigest 2.0 supplementation was also associated with significant changes in gut microbiota composition, as indicated by a decreased relative abundance of the phyla Firmicutes (p = 0.004) and Actinobacteria (p = 0.04). Conclusions: Micodigest 2.0 supplementation was associated with non-significant reductions in postoperative complications and significant modifications in gut microbiota composition. Limitations: The trial did not reach the calculated sample size.
- 24 February 2025
- Published by MDPI AG in Preprints.org
Open AccessThe Effect of Fungal Nutraceutical Supplementation on Postoperative Complications, Inflammatory Factors and Fecal Microbiota in Patients Undergoing Colorectal Cancer Surgery with Curative Intent: A Randomized, Placebo-Controlled, Double-Blind Clinical Trial
Background/Objectives: The combination of different fungal extracts could be beneficial to cancer patients due to their role in gut microbiota modulation and anti-inflammatory activity. The study aimed to evaluate whether fungal extract supplementation reduces postsurgical complications in patients with colorectal cancer undergoing curative surgery. Methods: Patients were randomized to receive the nutraceutical Micodigest 2.0 or a placebo until surgery. Surgical complications were evaluated using the Clavien-Dindo classification. We also assessed the effect of the nutraceutical on gut microbiota composition, inflammatory response, nutritional status, and quality of life. A subanalysis based on surgery type (robotic vs. non-robotic) was performed. Results: We included 46 patients who met the inclusion criteria, with 27 randomized to the intervention group and 19 to the placebo group, receiving treatment for 3 [2–4] weeks. Non-robotic surgery was performed in 35 (76.1%) patients. We found non-significant differences in postoperative complications (Micodigest 2.0: 25.9%, placebo: 26.3%; p = 0.9). In non-robotic surgery, we identified a non-significant reduction in postoperative complications (Micodigest 2.0: 25.0%, placebo: 36.4%; p = 0.7), as well as a significant increase in lymphocyte levels and a reduction in the neutrophil-to-lymphocyte ratio (p = 0.02). Micodigest 2.0 supplementation was also associated with significant changes in gut microbiota composition, as indicated by a decreased relative abundance of the phyla Firmicutes (p = 0.004) and Actinobacteria (p = 0.04). Conclusions: Micodigest 2.0 supplementation was associated with non-significant reductions in postoperative complications and significant modifications in gut microbiota composition. Limitations: The trial did not reach the calculated sample size.
- Open Access
- 13 February 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (4) , 458
PolyDeep Advance 1: Clinical Validation of a Computer-Aided Detection System for Colorectal Polyp Detection with a Second Observer Design
Background: PolyDeep is a computer-aided detection and characterization system that has demonstrated a high diagnostic yield for in vitro detection of colorectal polyps. Our objective is to compare the diagnostic performance of expert endoscopists and PolyDeep for colorectal polyp detection. Methods: PolyDeep Advance 1 (NCT05514301) is an unicentric diagnostic test study with a second observer design. Endoscopists performed colonoscopy blinded to PolyDeep’s detection results. The main endpoint was the sensitivity for colorectal polyp (adenoma, serrated or hyperplastic lesion) detection. The secondary endpoints were the diagnostic performance for diminutive lesions (≤5 mm), neoplasia (adenoma, serrated lesion) and adenoma detection. Results: We included 205 patients (55.1% male, 63.0 ± 6.2 years of age) referred to colonoscopy (positive faecal immunochemical occult blood test = 60.5%, surveillance colonoscopy = 39.5%). We excluded eight patients due to incomplete colonoscopy. Endoscopists detected 384 lesions, of which 39 were not detected by PolyDeep. In contrast, PolyDeep predicted 410 possible additional lesions, 26 of these predictions confirmed by endoscopists as lesions, resulting in a potential 6.8% detection increase with respect to the 384 lesions detected by the endoscopists. In total, 410 lesions were detected, 20 were not retrieved, five were colorectal adenocarcinoma, 343 were colorectal polyps (231 adenomas, 39 serrated and 73 hyperplastic polyps), 42 were normal mucosa and 289 were ≤5 mm. We did not find statistically significant differences between endoscopists and PolyDeep for colorectal polyp detection (Sensitivity = 94.2%, 91.5%, p = 0.2; Specificity = 9.5%, 14.3%, p = 0.7), diminutive lesions (Sensitivity = 92.3%, 89.5%, p = 0.4; Specificity = 9.8%, 14.6%, p = 0.7), neoplasia (Sensitivity = 95.2%, 92.9%, p = 0.3; Specificity = 9.6%, 13.9%, p = 0.4) and adenoma detection (Sensitivity = 94.4%, 92.6%, p = 0.5; Specificity = 7.2%, 11.8%, p = 0.2). Conclusions: Expert endoscopists and PolyDeep have similar diagnostic performance for colorectal polyp detection.
- 13 February 2025
- Published by MDPI AG in Diagnostics
- Vol. 15 (4) , 458
Open AccessPolyDeep Advance 1: Clinical Validation of a Computer-Aided Detection System for Colorectal Polyp Detection with a Second Observer Design
Background: PolyDeep is a computer-aided detection and characterization system that has demonstrated a high diagnostic yield for in vitro detection of colorectal polyps. Our objective is to compare the diagnostic performance of expert endoscopists and PolyDeep for colorectal polyp detection. Methods: PolyDeep Advance 1 (NCT05514301) is an unicentric diagnostic test study with a second observer design. Endoscopists performed colonoscopy blinded to PolyDeep’s detection results. The main endpoint was the sensitivity for colorectal polyp (adenoma, serrated or hyperplastic lesion) detection. The secondary endpoints were the diagnostic performance for diminutive lesions (≤5 mm), neoplasia (adenoma, serrated lesion) and adenoma detection. Results: We included 205 patients (55.1% male, 63.0 ± 6.2 years of age) referred to colonoscopy (positive faecal immunochemical occult blood test = 60.5%, surveillance colonoscopy = 39.5%). We excluded eight patients due to incomplete colonoscopy. Endoscopists detected 384 lesions, of which 39 were not detected by PolyDeep. In contrast, PolyDeep predicted 410 possible additional lesions, 26 of these predictions confirmed by endoscopists as lesions, resulting in a potential 6.8% detection increase with respect to the 384 lesions detected by the endoscopists. In total, 410 lesions were detected, 20 were not retrieved, five were colorectal adenocarcinoma, 343 were colorectal polyps (231 adenomas, 39 serrated and 73 hyperplastic polyps), 42 were normal mucosa and 289 were ≤5 mm. We did not find statistically significant differences between endoscopists and PolyDeep for colorectal polyp detection (Sensitivity = 94.2%, 91.5%, p = 0.2; Specificity = 9.5%, 14.3%, p = 0.7), diminutive lesions (Sensitivity = 92.3%, 89.5%, p = 0.4; Specificity = 9.8%, 14.6%, p = 0.7), neoplasia (Sensitivity = 95.2%, 92.9%, p = 0.3; Specificity = 9.6%, 13.9%, p = 0.4) and adenoma detection (Sensitivity = 94.4%, 92.6%, p = 0.5; Specificity = 7.2%, 11.8%, p = 0.2). Conclusions: Expert endoscopists and PolyDeep have similar diagnostic performance for colorectal polyp detection.
- Open Access
- 25 December 2024
- Published by MDPI AG in Preprints.org
PolyDeep Advance 1: Clinical Validation of a Computer-Aided Detection System for Colorectal Polyp Detection with a Second Observer Design
Background: PolyDeep is a computer-aided detection and characterization system that has demonstrated a high diagnostic yield for in vitro detection of colorectal polyps. Our objective is to compare the diagnostic performance of expert endoscopists and PolyDeep for colorectal polyp detection. Methods: PolyDeep Advance 1 (NCT05514301) is an unicentric diagnostic test study with a second observer design. Endoscopists performed the colonoscopy blinded to PolyDeep. The main endpoint was the sensitivity for colorectal polyp (adenoma, serrated or hyperplastic lesion) detection. The secondary endpoints were the diagnostic performance for diminutive lesions (≤5 mm), neoplasia (adenoma, serrated lesion) and adenoma detection. Results: We included 205 patients (55.1% male, 63.0 ± 6.2 years of age) referred to colonoscopy (positive faecal immunochemical occult blood test = 60.5%, surveillance colonoscopy = 39.5%). We excluded 8 patients due to incomplete colonoscopy. Endoscopists detected 384 lesions, of which 39 were not detected by PolyDeep. In contrast, PolyDeep predicted 410 possible additional lesions, 26 of these predictions confirmed by endoscopists as lesions, resulting in a potential 6.8% detection increase with respect to the 384 lesions detected by the endoscopists. In total, 410 lesions were detected, 20 were not retrieved, 5 were colorectal adenocarcinoma, 343 were colorectal polyps (231 adenomas, 39 serrated and 73 hyperplastic polyps), 42 were normal mucosa and 289 were ≤5mm. We did not find statistically significant differences between endoscopists and PolyDeep for colorectal polyp detection (Sensitivity = 94.2%, 91.5%, p = 0.2; Specificity = 9.5%, 14.3%, p = 0.7), diminutive lesions (Sensitivity = 92.3%,89.5%, p = 0.4; Specificity = 9.8%, 14.6%, p = 0.7), neoplasia (Sensitivity = 95.2%, 92.9%, p = 0.3; Specificity = 9.6%, 13.9%, p = 0.4) and adenoma detection (Sensitivity = 94.4%, 92.6%, p = 0.5; Specificity = 7.2%, 11.8%, p = 0.2). Conclusion: Expert endoscopists and PolyDeep have similar diagnostic performance for colorectal polyp detection.
- 25 December 2024
- Published by MDPI AG in Preprints.org
Open AccessPolyDeep Advance 1: Clinical Validation of a Computer-Aided Detection System for Colorectal Polyp Detection with a Second Observer Design
Background: PolyDeep is a computer-aided detection and characterization system that has demonstrated a high diagnostic yield for in vitro detection of colorectal polyps. Our objective is to compare the diagnostic performance of expert endoscopists and PolyDeep for colorectal polyp detection. Methods: PolyDeep Advance 1 (NCT05514301) is an unicentric diagnostic test study with a second observer design. Endoscopists performed the colonoscopy blinded to PolyDeep. The main endpoint was the sensitivity for colorectal polyp (adenoma, serrated or hyperplastic lesion) detection. The secondary endpoints were the diagnostic performance for diminutive lesions (≤5 mm), neoplasia (adenoma, serrated lesion) and adenoma detection. Results: We included 205 patients (55.1% male, 63.0 ± 6.2 years of age) referred to colonoscopy (positive faecal immunochemical occult blood test = 60.5%, surveillance colonoscopy = 39.5%). We excluded 8 patients due to incomplete colonoscopy. Endoscopists detected 384 lesions, of which 39 were not detected by PolyDeep. In contrast, PolyDeep predicted 410 possible additional lesions, 26 of these predictions confirmed by endoscopists as lesions, resulting in a potential 6.8% detection increase with respect to the 384 lesions detected by the endoscopists. In total, 410 lesions were detected, 20 were not retrieved, 5 were colorectal adenocarcinoma, 343 were colorectal polyps (231 adenomas, 39 serrated and 73 hyperplastic polyps), 42 were normal mucosa and 289 were ≤5mm. We did not find statistically significant differences between endoscopists and PolyDeep for colorectal polyp detection (Sensitivity = 94.2%, 91.5%, p = 0.2; Specificity = 9.5%, 14.3%, p = 0.7), diminutive lesions (Sensitivity = 92.3%,89.5%, p = 0.4; Specificity = 9.8%, 14.6%, p = 0.7), neoplasia (Sensitivity = 95.2%, 92.9%, p = 0.3; Specificity = 9.6%, 13.9%, p = 0.4) and adenoma detection (Sensitivity = 94.4%, 92.6%, p = 0.5; Specificity = 7.2%, 11.8%, p = 0.2). Conclusion: Expert endoscopists and PolyDeep have similar diagnostic performance for colorectal polyp detection.