In Chile, 18% of the population is over 60 years old and is projected to reach 31% in three decades. An aging population demands the development of strategies to improve quality of life (QoL). In this randomized trial, we present the implementation and evaluation of the Quida platform, which consists of a network of unintrusive sensors installed in the houses of elderly participants to monitor their activities and provide assistance. Sixty-nine elderly participants were included. A significant increase in overall QoL was observed amongst participants allocated to the interventional arm (p < 0.02). While some studies point out difficulties monitoring users at home, Quida demonstrates that it is possible to detect presence and movement to identify patterns of behavior in the sample studied, allowing us to visualize the behavior of older adults at different time intervals to support their medical evaluation.

Background: The World Health Organization recommends incorporating patient-reported experience measures and patient-reported outcome measures to ensure care processes. New technologies, such as mobile apps, could help report and monitor patients’ adverse effects and doubts during treatment. However, engaging patients in the daily use of mobile apps is a challenge that must be addressed in accordance with the needs of people. Objective: We present a qualitative case study documenting the process of identifying the information needs of breast cancer patients and health care professionals during the treatment process in a Chilean cancer institution. The study aims to identify patients’ information requirements for integration into a mobile app that accompanies patients throughout their treatment while also providing features for reporting adverse symptoms. Methods: We conducted focus groups with breast cancer patients who were undergoing chemotherapy (n=3) or who completed chemotherapy between 3 months and 1 year (n=1). We also surveyed health care professionals (n=9) who were involved in patient care and who belonged to the oncology committee of the cancer center where the study took place. Content analysis was applied to the responses to categorize the information needs and the means to satisfy them. A user interface was designed according to the findings of the focus groups and was assessed by 3 trained information system and user interaction design experts from 2 countries, using heuristic evaluation guidelines for mobile apps. Results: Patients’ information needs were classified into 4 areas: an overview of the disease, information on treatment and day-to-day affairs, assistance on the normality and abnormality of symptoms during treatment, and symptoms relevant to report. Health care professionals required patients to be provided with information on the administrative and financial process. We noted that the active involvement of the following 4 main actors is required to satisfy the information needs: patients, caregivers, social network moderators, and health professionals. Seven usability guidelines were extracted from the heuristic evaluation recommendations. Conclusions: A mobile app that seeks to accompany breast cancer patients to report symptoms requires the involvement of multiple participants to handle the reports and day-to-day information needs. User interfaces must be designed with consideration of the patient’s social conventions and the emotional load of the disease information.

In March 2020, the first version of EPIVIGILA was deployed in a productive environment a few days after the first local case of COVID- 19. This system is a technological integration plat-form for national epidemiological surveillance of notifiable diseases. Previously, Chile used a manual process that would probably have failed with a peak volume of more than 38 000 daily notifications; in a country with 18 million inhabitants, long and narrow geography, and centralized governance. This work highlights the importance of the national electronic surveillance system – EPIVIGILA – in managing the pandemic. The system’s main strength is its ability to adapt to the needs of reliable, precise, timely, and real- time information. EPIVIGILA was able to include, under the circumstances, different flows, actors, data, and functionalities with high expectations of accuracy. This valuable information allowed the authorities to assess the impact of the measures to manage and control the pandemic. Its versatility positions this platform among the few globally that operates national data with a high level of granularity in a single system through a pandemic. In Chile, EPIVIGILA is the primary source of information for daily reports, epidemiological reports, and data published on government websites about COVID- 19. Thus, electronic systems prove fundamental for public health because the recording and processing of data generate clear, reliable, and timely information, helping authorities make decisions to reduce the spread of infectious diseases, prevent deaths, and improve the population’s quality of life.

Reliably detecting COVID-19 is critical for diagnosis and disease control. However, imbalanced data in medical datasets pose significant challenges for machine learning models, leading to bias and poor generalization. The dataset obtained from the EPIVIGILA system and the Chilean Epidemiological Surveillance Process contains information on over 6,000,000 patients, but, like many current datasets, it suffers from class imbalance. To address this issue, we applied various machine learning algorithms, both with and without sampling methods, and compared them using different classification and diagnostic metrics such as precision, sensitivity, specificity, likelihood ratio positive, and diagnostic odds ratio. Our results showed that applying sampling methods to this dataset improved the metric values and contributed to models with better generalization. Effectively managing imbalanced data is crucial for reliable COVID-19 diagnosis. This study enhances the understanding of how machine learning techniques can improve diagnostic reliability and contribute to better patient outcomes.

The 2019 Coronavirus disease (COVID-19) pandemic is a current challenge for the world’s health systems aiming to control this disease. From an epidemiological point of view, the control of the incidence of this disease requires an understanding of the influence of the variables describing a population. This research aims to predict the COVID-19 incidence in three risk categories using two types of machine learning models, together with an analysis of the relative importance of the available features in predicting the COVID-19 incidence in the Chilean urban commune of Concepción. The classification results indicate that the ConvLSTM (Convolutional Long Short-Term Memory) classifier performed better than the SVM (Support Vector Machine), with results between 93% and 96% in terms of accuracy (ACC) and F-measure (F1) metrics. In addition, when considering each one of the regional and national features as well as the communal features (DEATHS and MOBILITY), it was observed that at the regional level the CRITICAL BED OCCUPANCY and PATIENTS IN ICU features positively contributed to the performance of the classifiers, while at the national level the features that most impacted the performance of the SVM and ConvLSTM were those related to the type of hospitalization of patients and the use of mechanical ventilators.

Cancer causes millions of deaths worldwide, making its registration essential. There are clinical, hospital, and population -based registries in place. The latter is the gold standard for information on cancer incidence and survival in a defined region. Chile has five population -based registries located in specific areas of the country. The Chilean National Cancer Registry emerged with the challenge of creating a tool encompassing all three types of registries to identify the number of cancer cases by type. Its design involved a series of actions to achieve consensus among various actors regarding information, validation, and events to be registered. Four stages were identified in the care and registration process: suspected diagnosis, morphological confirmation (biopsy), clinical resolution (oncology committee, including treatment recommendations), treatment, and oncological follow-up. The platform's development (from 2018 to 2021) involved gathering information and agreements on the requirements for co -designing the registry, including a successful pilot program with over 20 public and private healthcare facilities that recorded nearly 7500 cancer cases. The deployment and use of the National Cancer Registry at a national level depends on the healthcare authority. It is an information system that continuously and systematically collects, stores, processes, and analyzes data on all cancer cases and types occurring in the country. This work presents the design and development of the tool, the challenges addressed, as well as its strengths and weaknesses.