Vicky Sarapura
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Vicky Sarapura has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Ide Unchupaico Payano
Universidad Nacional del Centro del Peru
3 shared publications - Jordan Ninahuanca Carhuas
Faculty of Health Sciences, Universidad Peruana Los Andes (12000), Huancayo, Junín, Perú
3 shared publications - Carlos Quispe Eulogio
Los Andes Peruvian University
2 shared publications - Carolina Miranda-Torpoco
Facultad de Ingeniería, Universidad Peruana Los Andes, Huancayo, Peru
2 shared publications - Edgar Garcia-Olarte
Facultad de Zootecnia, Universidad Nacional del Centro del Perú, Huancayo, Junín, Perú
2 shared publications - Edith Ancco Gomez
Los Andes Peruvian University
2 shared publications
Latest Publications
- Open Access
- 8 August 2025
- Published by Universidad Nacional de Trujillo in Scientia Agropecuaria
- Vol. 16 (4) , 487-498
Balancing accuracy, interpretability, and stability in machine-learning models: Live-weight prediction of Andean sheep from morphometric traits
The objective of this research was to predict the live weight of Corriedale lambs using morphological measurements and machine learning algorithms. A total of 291 five-month-old lambs from the Corpacancha Production Unit of SAIS PACHACÚTEC SAC were used. These animals represented a homogeneous group in terms of age, sex, and genetics, as they belonged to the Corriedale breed and were offspring of "Category A" ewes. Morphological measurements recorded included Body Length (BL), Withers Height (WH), Thoracic Girth (TG), Rump Width (RW), Abdominal Girth (AG), Cannon Bone Length (CBL), Chest Depth (CD), and Live Weight (LW). The models evaluated were Multiple Linear Regression, Ridge Regression, Decision Trees, Random Forest, and XGBoost. The comparative analysis of the machine learning models identified ModG and Ridge as the most accurate and stable options, standing out for their low Mean Squared Error (MSE = 0.083) and Root Mean Squared Error (RMSE ≈ 0.287 – 0.288). Additionally, they exhibited the highest coefficients of determination (R2 = 0.89, RAdj2 = 0.88), indicating excellent predictive capability and data fit. Their low coefficient of variation (CV%) confirms their stability, establishing them as the best choices for applications where precision is paramount, such as predicting critical values in production processes and high-demand scientific studies. While XGBoost proved to be a robust alternative with an MSE of 0.119, an RMSE of 0.345, and a relative error of 2.22%. These findings confirm that prioritizing models that balance accuracy, interpretability, and stability enable faster, data-driven decision-making in Corriedale sheep production. Such an approach optimizes feed allocation, classifies lambs by market weight, and promptly detects growth deviations, thereby improving overall flock profitability.
- 8 August 2025
- Published by Universidad Nacional de Trujillo in Scientia Agropecuaria
- Vol. 16 (4) , 487-498
Open AccessBalancing accuracy, interpretability, and stability in machine-learning models: Live-weight prediction of Andean sheep from morphometric traits
The objective of this research was to predict the live weight of Corriedale lambs using morphological measurements and machine learning algorithms. A total of 291 five-month-old lambs from the Corpacancha Production Unit of SAIS PACHACÚTEC SAC were used. These animals represented a homogeneous group in terms of age, sex, and genetics, as they belonged to the Corriedale breed and were offspring of "Category A" ewes. Morphological measurements recorded included Body Length (BL), Withers Height (WH), Thoracic Girth (TG), Rump Width (RW), Abdominal Girth (AG), Cannon Bone Length (CBL), Chest Depth (CD), and Live Weight (LW). The models evaluated were Multiple Linear Regression, Ridge Regression, Decision Trees, Random Forest, and XGBoost. The comparative analysis of the machine learning models identified ModG and Ridge as the most accurate and stable options, standing out for their low Mean Squared Error (MSE = 0.083) and Root Mean Squared Error (RMSE ≈ 0.287 – 0.288). Additionally, they exhibited the highest coefficients of determination (R2 = 0.89, RAdj2 = 0.88), indicating excellent predictive capability and data fit. Their low coefficient of variation (CV%) confirms their stability, establishing them as the best choices for applications where precision is paramount, such as predicting critical values in production processes and high-demand scientific studies. While XGBoost proved to be a robust alternative with an MSE of 0.119, an RMSE of 0.345, and a relative error of 2.22%. These findings confirm that prioritizing models that balance accuracy, interpretability, and stability enable faster, data-driven decision-making in Corriedale sheep production. Such an approach optimizes feed allocation, classifies lambs by market weight, and promptly detects growth deviations, thereby improving overall flock profitability.
- 30 March 2025
- Published by Scienceline Publication in World's Veterinary Journal
- Vol. 15 (1) , 176-181
Surgical Correction of Anal Atresia in a 4-Day-Old Brown Swiss Calf
A 4-day-old Brown Swiss calf was presented to a veterinary clinic in Huancayo, Peru, with congenital anal atresia. The condition was characterized by an absence of defecation, progressive abdominal distension, and a blind rectal pouch confirmed radiographically. Clinical examination revealed no anal opening, moderate tympany, and normal neurological function. Surgical correction was conducted under pre-anesthetic sedation using xylazine (0.2 mg/kg IM) and sacrococcygeal epidural anesthesia with lidocaine (0.5 mL/kg). A 12-cm vertical incision in the intertubercular ischiatic region exposed the distended rectal pouch, allowing for an end-to-cutaneous anastomosis with polyglactin 910 (Vicryl® 2-0). Subsequently, a 2-3 cm distal rectal incision was created to form a neoanus. The mucosal edges were sutured to the skin margins with interrupted simple stitches (Vicryl® 3-0), a technique aimed at preventing stenosis and maintaining a neoanal diameter of approximately 1.5-2 cm. Postoperative management included prophylactic penicillin. Within three hours of surgery, the calf passed impacted meconium, indicating the functional patency of the neoanus. Although the prognosis was favorable, the patient was closely monitored for five days to detect any signs of stricture or infection. This case illustrated the effectiveness of early surgical intervention in reestablishing gastrointestinal continuity in congenital anal atresia.
- 30 March 2025
- Published by Scienceline Publication in World's Veterinary Journal
- Vol. 15 (1) , 176-181
Surgical Correction of Anal Atresia in a 4-Day-Old Brown Swiss Calf
A 4-day-old Brown Swiss calf was presented to a veterinary clinic in Huancayo, Peru, with congenital anal atresia. The condition was characterized by an absence of defecation, progressive abdominal distension, and a blind rectal pouch confirmed radiographically. Clinical examination revealed no anal opening, moderate tympany, and normal neurological function. Surgical correction was conducted under pre-anesthetic sedation using xylazine (0.2 mg/kg IM) and sacrococcygeal epidural anesthesia with lidocaine (0.5 mL/kg). A 12-cm vertical incision in the intertubercular ischiatic region exposed the distended rectal pouch, allowing for an end-to-cutaneous anastomosis with polyglactin 910 (Vicryl® 2-0). Subsequently, a 2-3 cm distal rectal incision was created to form a neoanus. The mucosal edges were sutured to the skin margins with interrupted simple stitches (Vicryl® 3-0), a technique aimed at preventing stenosis and maintaining a neoanal diameter of approximately 1.5-2 cm. Postoperative management included prophylactic penicillin. Within three hours of surgery, the calf passed impacted meconium, indicating the functional patency of the neoanus. Although the prognosis was favorable, the patient was closely monitored for five days to detect any signs of stricture or infection. This case illustrated the effectiveness of early surgical intervention in reestablishing gastrointestinal continuity in congenital anal atresia.
- Open Access
- 2 January 2025
- Published by Universidad Nacional del Nordeste in Revista Veterinaria
- Vol. 36 (1) , 1-6
Somatotropina vs. hormona foliculoestimulante: recuento folicular antral en vacas lactantes y no lactantes
El objetivo fue evaluar el efecto de la hormona foliculoestimulante (FSH) y la somatotropina bovina (bST) sobre la dinámica folicular en vacas lecheras lactantes y no lactantes. Se realizó un ANOVA factorial 2x2, considerando el estado de lactancia y la hormona utilizada como factores. Se utilizaron 20 vacas, 10 lactantes (5 con FSH y 5 con bST) y 10 no lactantes (5 con FSH y 5 con bST). En vacas lactantes, el tratamiento con bST mostró un recuento total de folículos significativamente mayor (16,4 ± 2,3) frente a FSH (11,8 ± 1,92), mientras que en no lactantes no hubo diferencias significativas (p>0,05). En número de folículos de tamaño 2-4 mm, se evidenció diferencias estadísticas (p0,05). En caso de viabilidad la bST mostró mejores resultados encontrando diferencias estadísticas (p<0,05) frente al grupo de FSH, tanto para vacas lactantes como no lactantes. Estos resultados subrayan la necesidad de ajustar los protocolos hormonales basados en el estado fisiológico de las vacas para maximizar la producción de ovocitos viables, lo cual es crucial para la reproducción asistida y para mejorar la eficiencia reproductiva en la industria ganadera.
- 2 January 2025
- Published by Universidad Nacional del Nordeste in Revista Veterinaria
- Vol. 36 (1) , 1-6
Open AccessSomatotropina vs. hormona foliculoestimulante: recuento folicular antral en vacas lactantes y no lactantes
El objetivo fue evaluar el efecto de la hormona foliculoestimulante (FSH) y la somatotropina bovina (bST) sobre la dinámica folicular en vacas lecheras lactantes y no lactantes. Se realizó un ANOVA factorial 2x2, considerando el estado de lactancia y la hormona utilizada como factores. Se utilizaron 20 vacas, 10 lactantes (5 con FSH y 5 con bST) y 10 no lactantes (5 con FSH y 5 con bST). En vacas lactantes, el tratamiento con bST mostró un recuento total de folículos significativamente mayor (16,4 ± 2,3) frente a FSH (11,8 ± 1,92), mientras que en no lactantes no hubo diferencias significativas (p>0,05). En número de folículos de tamaño 2-4 mm, se evidenció diferencias estadísticas (p0,05). En caso de viabilidad la bST mostró mejores resultados encontrando diferencias estadísticas (p<0,05) frente al grupo de FSH, tanto para vacas lactantes como no lactantes. Estos resultados subrayan la necesidad de ajustar los protocolos hormonales basados en el estado fisiológico de las vacas para maximizar la producción de ovocitos viables, lo cual es crucial para la reproducción asistida y para mejorar la eficiencia reproductiva en la industria ganadera.
- Open Access
- 1 January 2021
- Published by Elsevier in Toxicology Reports
- Vol. 8, 1461-1470
Heavy metals in soils and edible tissues of Lepidium meyenii (maca) and health risk assessment in areas influenced by mining activity in the Central region of Peru
- 1 January 2021
- Published by Elsevier in Toxicology Reports
- Vol. 8, 1461-1470
Open AccessHeavy metals in soils and edible tissues of Lepidium meyenii (maca) and health risk assessment in areas influenced by mining activity in the Central region of Peru