RESUMEN
Background and purpose: Radiation-induced toxicities are common adverse events in lung cancer (LC) patients undergoing radiotherapy (RT). An accurate prediction of these adverse events might facilitate an informed and shared decision-making process between patient and radiation oncologist with a clearer view of life-balance implications in treatment choices. This work provides a benchmark of machine learning (ML) approaches to predict radiation-induced toxicities in LC patients built upon a real-world health dataset based on a generalizable methodology for their implementation and external validation. Materials and Methods: Ten feature selection (FS) methods were combined with five ML-based classifiers to predict six RT-induced toxicities (acute esophagitis, acute cough, acute dyspnea, acute pneumonitis, chronic dyspnea, and chronic pneumonitis). A real-world health dataset (RWHD) built from 875 consecutive LC patients was used to train and validate the resulting 300 predictive models. Internal and external accuracy was calculated in terms of AUC per clinical endpoint, FS method, and ML-based classifier under analysis. Results: Best performing predictive models obtained per clinical endpoint achieved comparable performances to methods from state-of-the-art at internal validation (AUC ≥ 0.81 in all cases) and at external validation (AUC ≥ 0.73 in 5 out of 6 cases). Conclusion: A benchmark of 300 different ML-based approaches has been tested against a RWHD achieving satisfactory results following a generalizable methodology. The outcomes suggest potential relationships between underrecognized clinical factors and the onset of acute esophagitis or chronic dyspnea, thus demonstrating the potential that ML-based approaches have to generate novel data-driven hypotheses in the field.
RESUMEN
BACKGROUND: COVID-19 pandemic has revealed the weaknesses of most health systems around the world, collapsing them and depleting their available health care resources. Fortunately, the development and enforcement of specific public health policies, such as vaccination, mask wearing, and social distancing, among others, has reduced the prevalence and complications associated with COVID-19 in its acute phase. However, the aftermath of the global pandemic has called for an efficient approach to manage patients with long COVID-19. This is a great opportunity to leverage on innovative digital health solutions to provide exhausted health care systems with the most cost-effective and efficient tools available to support the clinical management of this population. In this context, the SENSING-AI project is focused on the research toward the implementation of an artificial intelligence-driven digital health solution that supports both the adaptive self-management of people living with long COVID-19 and the health care staff in charge of the management and follow-up of this population. OBJECTIVE: The objective of this protocol is the prospective collection of psychometric and biometric data from 10 patients for training algorithms and prediction models to complement the SENSING-AI cohort. METHODS: Publicly available health and lifestyle data registries will be consulted and complemented with a retrospective cohort of anonymized data collected from clinical information of patients diagnosed with long COVID-19. Furthermore, a prospective patient-generated data set will be captured using wearable devices and validated patient-reported outcomes questionnaires to complement the retrospective cohort. Finally, the 'Findability, Accessibility, Interoperability, and Reuse' guiding principles for scientific data management and stewardship will be applied to the resulting data set to encourage the continuous process of discovery, evaluation, and reuse of information for the research community at large. RESULTS: The SENSING-AI cohort is expected to be completed during 2022. It is expected that sufficient data will be obtained to generate artificial intelligence models based on behavior change and mental well-being techniques to improve patients' self-management, while providing useful and timely clinical decision support services to health care professionals based on risk stratification models and early detection of exacerbations. CONCLUSIONS: SENSING-AI focuses on obtaining high-quality data of patients with long COVID-19 during their daily life. Supporting these patients is of paramount importance in the current pandemic situation, including supporting their health care professionals in a cost-effective and efficient management of long COVID-19. TRIAL REGISTRATION: Clinicaltrials.gov NCT05204615; https://clinicaltrials.gov/ct2/show/NCT05204615. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/37704.
RESUMEN
This work addresses a scoping review of Feature Selection (FS) methods applied to a Lung Cancer dataset to elucidate parameters' relevance when predicting radiotherapy (RT) induced toxicity. Subsetting-based and Ranking-based FS methods were implemented along with 4 advanced classifiers to predict the onset of RT-induced acute esophagitis, cough, pneumonitis and dyspnea. Their prediction performance was measured in terms of the AUC for each model to find the best FS.
Asunto(s)
Neoplasias Pulmonares , Traumatismos por Radiación , Radioterapia , Minería de Datos , Trastornos de Deglución/etiología , Disnea/etiología , Esofagitis/etiología , Predicción , Humanos , Neoplasias Pulmonares/radioterapia , Neumonía/etiología , Radioterapia/efectos adversosRESUMEN
An informatics platform has been designed, deployed and validated around the ITCBio initiative to provide support to clinical and translational research in Andalusia. To this end, an infrastructure has been developed which, in a scalable manner, incorporates functionalities aimed to facilitate the consistent definition of information models, the data reusability from electronic health records, as well as the analysis and processing of information. All this with the purpose of providing support to the different clinical and translational research processes associated with clinical trials and research projects. This initiative is based on the creation of a suite of applications that, through using standards, incorporates open-software tools intended to support these research processes. It is currently in widespread and growing use in university hospitals in which the platform is deployed.
Asunto(s)
Registros Electrónicos de Salud , Aplicaciones de la Informática Médica , Investigación Biomédica Traslacional , Interoperabilidad de la Información en Salud , Servicios de Salud , Humanos , Programas Informáticos , España , Investigación Biomédica Traslacional/organización & administraciónRESUMEN
Herein, we describe the characterization of a Digital Consent (DC) System to support current ethical-legal issues associated with challenges posed by informed consent for genomic research. A potential solution to support ongoing interaction with patients and allow control over how their data and samples are being used in genomic research can be Digital Consent based. But there are other challenges that need to be addressed, such as incidental findings when analyzing the results of genomic tests (not expected). This paper addresses security and privacy recommendations for the development of precision medicine, and the interoperability references of Health Information Standardization Organizations such as HL7 and IHE, as well as recent research in the field of ethics in Genomic Medicine. As a result of this work, ten key features that need to be further explored have been identified in order to support the realization of DC in Genomic Research.
RESUMEN
BACKGROUND: New technologies, such as telerehabilitation and gaming devices offer the possibility for patients to train at home. This opens the challenge of safety for the patient as he/she is called to exercise neither with a therapist on the patients' side nor with a therapist linked remotely to supervise the sessions. AIM: To study the safety, usability and patient acceptance of an autonomous telerehabilitation system for balance and gait (the REWIRE platform) in the patients home. DESIGN: Cohort study. SETTING: Community, in the stroke patients' home. POPULATION: Fifteen participants with first-ever stroke, with a mild to moderate residual deficit of the lower extremities. METHODS: Autonomous rehabilitation based on virtual rehabilitation was provided at the participants' home for twelve weeks. The primary outcome was compliance (the ratio between days of actual and scheduled training), analyzed with the two-tailed Wilcoxon Mann-Whitney test. Furthermore safety is defined by adverse events. The secondary endpoint was the acceptance of the system measured with the Technology Acceptance Model (TAM). Additionally, the cumulative duration of weekly training was analyzed. RESULTS: During the study there were no adverse events related to the therapy. Patients performed on average 71% (range 39 to 92%) of the scheduled sessions. The TAM Questionnaire showed excellent values for stroke patients after the training. The average training duration per week was 99±53min. CONCLUSIONS: Autonomous telerehabilitation for balance and gait training with the REWIRE-system is safe, feasible and can help to intensive rehabilitative therapy at home. CLINICAL REHABILITATION IMPACT: Telerehabilitation enables safe training in home environment and supports of the standard rehabilitation therapy.
Asunto(s)
Marcha/fisiología , Satisfacción del Paciente/estadística & datos numéricos , Equilibrio Postural/fisiología , Rehabilitación de Accidente Cerebrovascular/métodos , Telerrehabilitación/métodos , Interfaz Usuario-Computador , Anciano , Enfermedad Crónica , Estudios de Cohortes , Femenino , Servicios de Atención de Salud a Domicilio/organización & administración , Humanos , Masculino , Persona de Mediana Edad , Cooperación del Paciente/estadística & datos numéricos , Proyectos Piloto , Accidente Cerebrovascular/diagnóstico , Resultado del TratamientoRESUMEN
The Andalusian Health Service is the public healthcare provider for 8.302.923 inhabitants in the South Spain. This organization coordinates primary and specialized care with an IT infrastructure composed by multiple Electronic Health Record Systems. According to the large volume of healthcare professionals involved, there is a need for providing a consistent management of information through multiple locations and systems. The HEMIC project aims to address this need developing and validating a methodology based on a software tool for standardizing information contained within EHR systems. The developed tool has been designed for supporting the participation of healthcare professionals the establishment of mechanisms for information governance. This research presents the requirements and designs for of a software tool focused on the adoption of recognized best practice in clinical information modeling. The designed tool has a Service Oriented Architecture that will be able to integrate terminology servers and repositories of clinical information models as part of the modeling process. Moreover, the defined tool organizes clinicians, IT developers and terminology experts involved in the modeling process in three levels to promote their coordination in the definition, specialization and validation of clinical information models. In order to ensure the quality of the developed clinical information models, the defined tool is based on the requirements defined in the ISO13972 Technical Specification.
Asunto(s)
Registros Electrónicos de Salud , Sistemas de Registros Médicos Computarizados , Programas Informáticos , Sistemas de Computación , Humanos , EspañaRESUMEN
Interoperability assets is the term applied to refer to any resource that can support the design, implementation and successful adoption of eHealth services that can exchange data meaningfully. Some examples may include functional requirements, specifications, standards, clinical models and term lists, guidance on how standards may be used concurrently, implementation guides, educational resources, and other resources. Unfortunately, these are largely accessible in ad hoc ways and result in scattered fragments of a solution space that urgently need to be brought together. At present, it is well known that new initiatives and projects will reinvent assets of which they were unaware, while those assets which were potentially of great value are forgotten, not maintained and eventually fall into disuse. This research has defined a quality in use model and assessed the suitability of this quality framework based on the feedback and opinion of a representative sample of potential end users. This quality framework covers the following domains of asset development and adoption: (i) Development process, (ii) Maturity level, (iii) Trustworthiness, (iv) Support & skills, (v) Sustainability, (vi) Semantic interoperability, (vii) Cost & effort of adoption (viii) Maintenance. When participants were requested to evaluate how the overall quality in use framework, 70% would recommend using the register to their colleagues, 70% felt that it could provide relevant benefits for discovering new assets, and 50% responded that it would support their decision making about the recommended asset to adopt or implement in their organisation. Several European projects have expressed interest in using the register, which will now be sustained and promoted by the the European Institute for Innovation through Health Data.
Asunto(s)
Integración de Sistemas , Telemedicina , Registros Electrónicos de Salud , Europa (Continente) , Registro Médico CoordinadoRESUMEN
OBJECTIVE: Clinical information models are formal specifications for representing the structure and semantics of the clinical content within electronic health record systems. This research aims to define, test, and validate evaluation metrics for software tools designed to support the processes associated with the definition, management, and implementation of these models. METHODOLOGY: The proposed framework builds on previous research that focused on obtaining agreement on the essential requirements in this area. A set of 50 conformance criteria were defined based on the 20 functional requirements agreed by that consensus and applied to evaluate the currently available tools. RESULTS: Of the 11 initiative developing tools for clinical information modeling identified, 9 were evaluated according to their performance on the evaluation metrics. Results show that functionalities related to management of data types, specifications, metadata, and terminology or ontology bindings have a good level of adoption. Improvements can be made in other areas focused on information modeling and associated processes. Other criteria related to displaying semantic relationships between concepts and communication with terminology servers had low levels of adoption. CONCLUSIONS: The proposed evaluation metrics were successfully tested and validated against a representative sample of existing tools. The results identify the need to improve tool support for information modeling and software development processes, especially in those areas related to governance, clinician involvement, and optimizing the technical validation of testing processes. This research confirmed the potential of these evaluation metrics to support decision makers in identifying the most appropriate tool for their organization. OBJECTIVO: Los Modelos de Información Clínica son especificaciones para representar la estructura y características semánticas del contenido clínico en los sistemas de Historia Clínica Electrónica. Esta investigación define, prueba y valida un marco para la evaluación de herramientas informáticas diseñadas para dar soporte en la en los procesos de definición, gestión e implementación de estos modelos. METODOLOGIA: El marco de evaluación propuesto se basa en una investigación previa para obtener consenso en la definición de requisitos esenciales en esta área. A partir de los 20 requisitos funcionales acordados, un conjunto de 50 criterios de conformidad fueron definidos y aplicados en la evaluación de las herramientas existentes. RESULTADOS: Un total de 9 de las 11 iniciativas identificadas desarrollando herramientas para el modelado de información clínica fueron evaluadas. Los resultados muestran que las funcionalidades relacionadas con la gestión de tipos de datos, especificaciones, metadatos y mapeo con terminologías u ontologías tienen un buen nivel de adopción. Se identifican posibles mejoras en áreas relacionadas con los procesos de modelado de información. Otros criterios relacionados con presentar las relaciones semánticas entre conceptos y la comunicación con servidores de terminología tienen un bajo nivel de adopción. CONCLUSIONES: El marco de evaluación propuesto fue probado y validado satisfactoriamente contra un conjunto representativo de las herramientas existentes. Los resultados identifican la necesidad de mejorar el soporte de herramientas a los procesos de modelado de información y desarrollo de software, especialmente en las áreas relacionadas con gobernanza, participación de profesionales clínicos y la optimización de la validación técnica en los procesos de pruebas técnicas. Esta investigación ha confirmado el potencial de este marco de evaluación para dar soporte a los usuarios en la toma de decisiones sobre que herramienta es más apropiadas para su organización.
Asunto(s)
Interoperabilidad de la Información en Salud , Informática Médica , Modelos Teóricos , Técnica Delphi , Registros Electrónicos de Salud , Estudios de Evaluación como Asunto , Humanos , Investigación Cualitativa , Semántica , Encuestas y CuestionariosRESUMEN
Clinical Decision Support Systems (CDSS) are software applications that support clinicians in making healthcare decisions providing relevant information for individual patients about their specific conditions. The lack of integration between CDSS and Electronic Health Record (EHR) has been identified as a significant barrier to CDSS development and adoption. Andalusia Healthcare Public System (AHPS) provides an interoperable health information infrastructure based on a Service Oriented Architecture (SOA) that eases CDSS implementation. This paper details the deployment of a CDSS jointly with the deployment of a Terminology Server (TS) within the AHPS infrastructure. It also explains a case study about the application of decision support to thromboembolism patients and its potential impact on improving patient safety. We will apply the inSPECt tool proposal to evaluate the appropriateness of alerts in this scenario.
Asunto(s)
Sistemas de Apoyo a Decisiones Clínicas/normas , Registros Electrónicos de Salud/normas , Errores Médicos/prevención & control , Seguridad del Paciente/normas , Indicadores de Calidad de la Atención de Salud/normas , Terminología como Asunto , Humanos , Almacenamiento y Recuperación de la Información/métodos , Registro Médico Coordinado/normas , Procesamiento de Lenguaje Natural , EspañaRESUMEN
Given that acceptance of systems within the healthcare domain multiple papers highlighted the importance of integrating tools with the clinical workflow. This paper analyse how clinical context management could be deployed in order to promote the adoption of cloud advanced services and within the clinical workflow. This deployment will be able to be integrated with the eHealth European Interoperability Framework promoted specifications. Throughout this paper, it is proposed a cloud-based service-oriented architecture. This architecture will implement a context management system aligned with the HL7 standard known as CCOW.
Asunto(s)
Nube Computacional/normas , Registros Electrónicos de Salud/normas , Sistemas de Información en Salud/normas , Modelos Organizacionales , Guías de Práctica Clínica como Asunto , Flujo de Trabajo , Registros Electrónicos de Salud/estadística & datos numéricos , Europa (Continente) , Sistemas de Información en Salud/estadística & datos numéricos , Estándar HL7/normas , Integración de Sistemas , Interfaz Usuario-Computador , Revisión de Utilización de RecursosRESUMEN
OBJECTIVE: This study proposes consensus requirements for clinical information modelling tools that can support modelling tasks in medium/large scale institutions. Rather than identify which functionalities are currently available in existing tools, the study has focused on functionalities that should be covered in order to provide guidance about how to evolve the existing tools. METHODOLOGY: After identifying a set of 56 requirements for clinical information modelling tools based on a literature review and interviews with experts, a classical Delphi study methodology was applied to conduct a two round survey in order to classify them as essential or recommended. Essential requirements are those that must be met by any tool that claims to be suitable for clinical information modelling, and if we one day have a certified tools list, any tool that does not meet essential criteria would be excluded. Recommended requirements are those more advanced requirements that may be met by tools offering a superior product or only needed in certain modelling situations. RESULTS: According to the answers provided by 57 experts from 14 different countries, we found a high level of agreement to enable the study to identify 20 essential and 21 recommended requirements for these tools. CONCLUSIONS: It is expected that this list of identified requirements will guide developers on the inclusion of new basic and advanced functionalities that have strong support by end users. This list could also guide regulators in order to identify requirements that could be demanded of tools adopted within their institutions.
Asunto(s)
Sistemas de Información en Hospital/normas , Gestión de la Información , Sistemas de Registros Médicos Computarizados , Modelos Teóricos , HumanosRESUMEN
OBJECTIVE: This systematic review aims to identify and compare the existing processes and methodologies that have been published in the literature for defining clinical information models (CIMs) that support the semantic interoperability of electronic health record (EHR) systems. MATERIAL AND METHODS: Following the preferred reporting items for systematic reviews and meta-analyses systematic review methodology, the authors reviewed published papers between 2000 and 2013 that covered that semantic interoperability of EHRs, found by searching the PubMed, IEEE Xplore, and ScienceDirect databases. Additionally, after selection of a final group of articles, an inductive content analysis was done to summarize the steps and methodologies followed in order to build CIMs described in those articles. RESULTS: Three hundred and seventy-eight articles were screened and thirty six were selected for full review. The articles selected for full review were analyzed to extract relevant information for the analysis and characterized according to the steps the authors had followed for clinical information modeling. DISCUSSION: Most of the reviewed papers lack a detailed description of the modeling methodologies used to create CIMs. A representative example is the lack of description related to the definition of terminology bindings and the publication of the generated models. However, this systematic review confirms that most clinical information modeling activities follow very similar steps for the definition of CIMs. Having a robust and shared methodology could improve their correctness, reliability, and quality. CONCLUSION: Independently of implementation technologies and standards, it is possible to find common patterns in methods for developing CIMs, suggesting the viability of defining a unified good practice methodology to be used by any clinical information modeler.
Asunto(s)
Registros Electrónicos de Salud/organización & administración , Informática Médica , Vocabulario Controlado , Sistemas de Información/organización & administración , Modelos Teóricos , Semántica , Integración de SistemasRESUMEN
This paper introduces the evaluation report after fostering a Standard-based Interoperability Framework (SIF) between the Virgen del Rocío University Hospital (VRUH) Haemodialysis (HD) Unit and 5 outsourced HD centres in order to improve integrated care by automatically sharing patients' Electronic Health Record (EHR) and lab test reports. A pre-post study was conducted during fourteen months. The number of lab test reports of both emergency and routine nature regarding to 379 outpatients was computed before and after the integration of the SIF. Before fostering SIF, 19.38 lab tests per patient were shared between VRUH and HD centres, 5.52 of them were of emergency nature while 13.85 were routine. After integrating SIF, 17.98 lab tests per patient were shared, 3.82 of them were of emergency nature while 14.16 were routine. The inclusion of a SIF in the HD Integrated Care Process has led to an average reduction of 1.39 (p=0.775) lab test requests per patient, including a reduction of 1.70 (p=0.084) in those of emergency nature, whereas an increase of 0.31 (p=0.062) was observed in routine lab tests. Fostering this strategy has led to the reduction in emergency lab test requests, which implies a potential improvement of the integrated care.
Asunto(s)
Sistemas de Información en Laboratorio Clínico/normas , Prestación Integrada de Atención de Salud/normas , Registros Electrónicos de Salud/normas , Fallo Renal Crónico/terapia , Registro Médico Coordinado/normas , Mejoramiento de la Calidad/normas , Diálisis Renal/normas , Guías como Asunto , Humanos , EspañaRESUMEN
INTRODUCTION: Social networks applied through Web 2.0 tools have gained importance in health domain, because they produce improvements on the communication and coordination capabilities among health professionals. This is highly relevant for multimorbidity patients care because there is a large number of health professionals in charge of patient care, and this requires to obtain clinical consensus in their decisions. Our objective is to develop a tool for collaborative work among health professionals for multimorbidity patient care. We describe the architecture to incorporate decision support functionalities in a social network tool to enable the adoption of shared decisions among health professionals from different care levels. As part of the first stage of the project, this paper describes the results obtained in a pilot study about acceptance and use of the social network component in our healthcare setting. METHODS: At Virgen del Rocío University Hospital we have designed and developed the Shared Care Platform (SCP) to provide support in the continuity of care for multimorbidity patients. The SCP has two consecutively developed components: social network component, called Clinical Wall, and Clinical Decision Support (CDS) system. The Clinical Wall contains a record where health professionals are able to debate and define shared decisions. We conducted a pilot study to assess the use and acceptance of the SCP by healthcare professionals through questionnaire based on the theory of the Technology Acceptance Model. RESULTS: In March 2012 we released and deployed the SCP, but only with the social network component. The pilot project lasted 6 months in the hospital and 2 primary care centers. From March to September 2012 we created 16 records in the Clinical Wall, all with a high priority. A total of 10 professionals took part in the exchange of messages: 3 internists and 7 general practitioners generated 33 messages. 12 of the 16 record (75%) were answered by the destination health professionals. The professionals valued positively all the items in the questionnaire. As part of the SCP, opensource tools for CDS will be incorporated to provide recommendations for medication and problem interactions, as well as to calculate indexes or scales from validated questionnaires. They will receive the patient summary information provided by the regional Electronic Health Record system through a web service with the information defined according to the virtual Medical Record specification. CONCLUSIONS: Clinical Wall has been developed to allow communication and coordination between the healthcare professionals involved in multimorbidity patient care. Agreed decisions were about coordination for appointment changing, patient conditions, diagnosis tests, and prescription changes and renewal. The application of interoperability standards and open source software can bridge the gap between knowledge and clinical practice, while enabling interoperability and scalability. Open source with the social network encourages adoption and facilitates collaboration. Although the results obtained for use indicators are still not as high as it was expected, based on the promising results obtained in the acceptance questionnaire of SMP, we expect that the new CDS tools will increase the use by the health professionals.
Asunto(s)
Manejo de Caso , Toma de Decisiones , Pautas de la Práctica en Medicina , Apoyo Social , Adulto , Femenino , Humanos , Masculino , Persona de Mediana EdadRESUMEN
Objetivo. El estadio del cáncer de mama constituye uno de los factores pronósticos más relevantes. Sin embargo, la compleja clasificación TNM, la existencia de diferentes versiones y la variabilidad de la fuente de la información hacen que la recogida de datos sobre texto libre sea compleja. El objetivo de este trabajo es desarrollar una herramienta que permita ayudar a la estadificación de manera automática. Pacientes y métodos. El trabajo incluyó el estudio de los informes de 100 pacientes con cáncer de mama no metastásico tratadas con cirugía y radioterapia en 2012. La recogida del tamaño tumoral posquirúrgico (séptima edición TNM) se realizó con la herramienta desarrollada y manualmente por un médico en formación especializada de tercer año de oncología radioterápica. Resultados. La aplicación fue capaz de detectar el 62% de los casos tras examinar los informes de anatomía patológica, y el 77% al añadir el examen de los informes de oncología radioterápica. Los casos no detectados se debieron a que la información estaba almacenada en otra sección de la estación clínica. Comparando los resultados entre la aplicación y la recogida manual, hubo una diferencia del 13% (10/77). Se observó que en el 50% de los casos (5/10) la aplicación era correcta, mientras que en el otro 50% lo fue la recogida manual. Conclusiones. Esta herramienta innovadora permite recoger automáticamente el tamaño tumoral en el cáncer de mama, ahorrando tiempo en la recogida de datos y evitando errores en la clasificación tumoral, por lo que puede contribuir de modo notable en la decisión terapéutica(AU)
Objective. Staging of breast cancer is one of the most important prognostic factors. However, collecting data for staging manually from unstructured free text is variable and imprecise because of the complexity of the TNM classification, the existence of different versions over time, and variability in the source used to obtain data. The aim of this study was to develop an artificial intelligence tool to allow data on tumoral staging to be mined automatically. Patients and methods. The study included the reports of the first 100 patients with nonmetastatic breast cancer treated with surgery and radiotherapy in 2012. Data on postoperative tumor size (TNM seventh edition) were collected with a specially designed software tool and manually by a third-year resident physician in radiation oncology. Results. The software application detected 62% of cases when pathology reports were included, and 77% when radiation oncology reports were added. Non-detection was due to the information being stored in another section of the clinical station. When we compared the results of the software application and manual collection, we found a difference of 13% (10/77). In these 10 cases, the application was correct in 50%, while manual collection was correct in the remaining 50%. Conclusions. This innovative system allows automatic staging of tumoral size in breast cancer. The use of this tool would save time in data collection and prevent errors in tumoral classification and could also improve therapeutic decisions(AU)