Chart Review of Patients With COPD, Using Electronic Medical Records and Artificial Intelligence

The study will be conducted in accordance with legal and regulatory requirements, as well as with scientific purpose, value and rigor and follow generally accepted research practices described in the International Conference Harmonization (ICH) Guideline for Good Clinical Practice, the Helsinki Declaration in its latest edition, Good Pharmacoepidemiology Practices, and applicable local regulations. To maintain patient confidentiality, demographic and personal identifying information (e.g., initials, date of birth, etc.) will not be collected; only age will be collected. In no case Savana staff will handle a correspondence table between the anonymized patient codes and their EMRs. Only the healthcare centre can identify patients. In any case, SEPAR, the study sponsor, or its partners, will not have gto EMRs. It will only access a report, which will contain aggregated information on the data obtained as described in this protocol. The final results will be published. According to the European Data Protection Authority, an anonymous clinical record is released from its status as personal data, so that the General Data Protection Regulation no longer applies. The anonymization is performed at each site by the owner of the information (so that nobody else has access to that information and so that it is not possible to track it). All actions will be taken in accordance with the Code of Good Data Protection Practices for Big Data Projects of the European Data Protection Authority, the European General Data Protection Regulation or another that may replace it. In addition, clinical records will never be stored in a location other than the institution where it is implemented. Savana does not use EMRs from individual patients, but aggregate clinical information, which is also encrypted and secured. The aggregation of the data ensures the impossibility of identifying patients or individual centres. The system is based on the processing of a large amount of information (Big Data), so that the impact of random errors is minimized. The use of this software is possible nowadays since there has been a notable improvement in the implementation of EMRs, which may result in the use of this software in significant investments for the use and better knowledge of the health system. In summary, this new technology allows a complete dissociation between the data obtained for the current study and the personal data of the patient, since this information is obtained in an aggregated and completely anonymous form. This clearly represents an advance in data protection in the context of classical observational epidemiological studies. Therefore, only aggregated and completely anonymous data will be obtained, completely dissociated from the personal data of each patient and centre. The confidentiality of patient records will be maintained at all times. All study reports will contain only aggregated data and will not identify patients, doctors or individual centres. At no time during the study, the sponsor will receive information that may allow the identification of a patient or individual centre.