Automatic support system for tumor coding in pathology reports in Spanish.

Pathology reports provide valuable information for cancer registries to understand, plan and implement strategies to mitigate the impact of cancer. However, coding key information from unstructured reports is done by experts in a time-consuming manual process. Here we report an automatic deep learning-based system that recognizes tumor morphology and topography mentions from free-text and suggests codes from the International Classification of Diseases for Oncology (ICD-O) in Spanish.

• Colaboración:Centro Modelamiento Matemático - U. de Chile

Predicting Pathologic Complete Response to Neoadjuvant Treatment in HER2 using Interpretable Classification.

The objective of this work is to obtain a model to predict the pCR of patients to neoadjuvant treatment combining cytotoxic chemotherapy with double HER2 blockade, before they undergo treatment, using interpretable machine learning (IML) techniques. This will allow us to determine which variables could affect the response of a patient to this treatment.

Validación de calculadora para estimar riesgo quirúrgico.

Automatic detection of distant metastasis mentions in Spanish-language radiology reports.

Metastasis-related information is crucial for planning treatment, evaluating patient prognoses, and conducting cancer research. Findings of distant metastasis are written in radiology reports, which are often unstructured, making it difficult to extract relevant information automatically. In this study, we developed a named entity recognition model to capture mentions of distant metastasis in radiology and nuclear medicine reports in Spanish of prostate, colorectal, and breast cancer patients

Experiencia del desarrollo e implementación de la metodología de un Registro Hospitalario de Tumores en un Centro Oncológico de Chile. Evaluación a 5 años del funcionamiento.

La elaboración de un registro hospitalario de tumores que genere datos de cáncer confiables para evaluar la correcta utilización de recursos sanitarios, en base a las necesidades de los pacientes y la evolución de la enfermedad, es un elemento necesario para el control del cáncer en un país. Para dar respuesta a este desafío FALP implementó un registro de tumores siguiendo las directrices establecidas en el Plan Nacional de Cáncer y su respectivo plan de acción 2018-2028

Validación de calculadora para estimar riesgo quirúrgico.

Las complicaciones y eventos adversos post-operatorios de corto plazo constituyen importantes desenlaces en cirugía oncológica y su medición puede utilizarse para mejorar la calidad de atención clínica. El presente estudio busca validar retrospectivamente el score predictivo de riesgo propuesto por Lohmann y colaboradores, a través del cálculo del riesgo post-operatorio de presentar eventos adversos específicos en los pacientes operados de tumores cerebrales o espinales en FALP, y su posterior correlación (o consistencia) con las complicaciones y eventos adversos reales presentados por estos en el período postoperatorio.

Implementación y evaluación de sistema de gestión de casos oncológicos no GES entre prestadores de salud públicos y privados en Chile

Se propone el diseño e implementación de un software que permita la trazabilidad de los casos entre prestadores públicos y privados, favoreciendo el intercambio de datos clínicos y administrativos para la toma de decisiones oportuna y eficiente. A diciembre de 2022, se han derivado un total de 893 pacientes, de los cuales 388 han sido o están siendo tratados. Se han realizado 504 cirugías, 1819 sesiones de radioterapia y 517 sesiones de quimioterapia. Se envió la escala de usabilidad a 108 gestores de casos de instituciones públicas a cargo de la derivación de casos a FALP, de las cuales respondieron 22 usuarios. Se obtuvo un puntaje SUS promedio de 82.95 (95% IC: 78.6 - 87.3), correspondiente al percentil 90-95% del ranking SUS.

Simultaneous and Spatially-Resolved Analysis of T-Lymphocytes, Macrophages and PD-L1 Immune Checkpoint in Rare Cancers

This work describes the experience of a Chilean cancer center using multiplexed immunofluorescence to study a case series of four penile cancers, two anal cancers and one vulvar cancer and simultaneous detection of CD8, CD68, PD-L1, Cytokeratin and Ki-67 in FFPE samples. Fluorescent image analyses were performed using open sources for automated tissue segmentation and cell phenotyping. Our results showed an objective and reliable counting of objects with a single or combined labeling or within a specific tissue compartment.

• Colaboración:Laboratorio de Medicina Traslacional - FALP

Implementation of Health-Related Quality of Life measures in breast cancer: learning from the real-world setting experience in Chile

This work describes the experience of a Chilean cancer center using multiplexed immunofluorescence to study a case series of four penile cancers, two anal cancers and one vulvar cancer and simultaneous detection of CD8, CD68, PD-L1, Cytokeratin and Ki-67 in FFPE samples. Fluorescent image analyses were performed using open sources for automated tissue segmentation and cell phenotyping. Our results showed an objective and reliable counting of objects with a single or combined labeling or within a specific tissue compartment.

• Colaboración:ETESA - FALP | Equipo Oncología Mama - FALP

Frecuencia de factores protectores y de riesgo oncológicos en una población chilena

• Colaboración:Unidad de Investigación Epidemiológica y Clínica (UIEC) - FALP

Simultaneous and Spatially-Resolved Analysis of T-Lymphocytes, Macrophages and PD-L1 Immune Checkpoint in Rare Cancers

This work describes the experience of a Chilean cancer center using multiplexed immunofluorescence to study a case series of four penile cancers, two anal cancers and one vulvar cancer and simultaneous detection of CD8, CD68, PD-L1, Cytokeratin and Ki-67 in FFPE samples. Fluorescent image analyses were performed using open sources for automated tissue segmentation and cell phenotyping. Our results showed an objective and reliable counting of objects with a single or combined labeling or within a specific tissue compartment.

• Colaboración:Laboratorio de Medicina Traslacional - FALP

Implementation of Health-Related Quality of Life measures in breast cancer: learning from the real-world setting experience in Chile

This work describes the experience of a Chilean cancer center using multiplexed immunofluorescence to study a case series of four penile cancers, two anal cancers and one vulvar cancer and simultaneous detection of CD8, CD68, PD-L1, Cytokeratin and Ki-67 in FFPE samples. Fluorescent image analyses were performed using open sources for automated tissue segmentation and cell phenotyping. Our results showed an objective and reliable counting of objects with a single or combined labeling or within a specific tissue compartment.

• Colaboración:ETESA - FALP | Equipo Oncología Mama - FALP

Frecuencia de factores protectores y de riesgo oncológicos en una población chilena

• Colaboración:Unidad de Investigación Epidemiológica y Clínica (UIEC) - FALP