The identification of sections in narrative content of Electronic Health Records (EHR) has demonstrated to improve the performance of clinical extraction tasks; however, there is not yet a shared understanding of the concept and its existing methods. The objective is to report the results of a systematic review concerning approaches aimed at identifying sections in narrative content of EHR, using both automatic or semi-automatic methods. This review includes articles from the databases: SCOPUS, Web of Science and PubMed (from January 1994 to September 2018). The selection of studies was done using predefined eligibility criteria and applying the PRISMA recommendations. Search criteria were elaborated by using an iterative and collaborative keyword enrichment. Following the eligibility criteria, 39 studies were selected for analysis. The section identification approaches proposed by these studies vary greatly depending on the kind of narrative, the type of section, and the application. We observed that 57% of them proposed formal methods for identifying sections and 43% adapted a previously created method. Seventy-eight percent were intended for English texts and 41% for discharge summaries. Studies that are able to identify explicit (with headings) and implicit sections correspond to 46%. Regarding the level of granularity, 54% of the studies are able to identify sections, but not subsections. From the technical point of view, the methods can be classified into rule-based methods (59%), machine learning methods (22%) and a combination of both (19%). Hybrid methods showed better results than those relying on pure machine learning approaches, but lower than rule-based methods; however, their scope was more ambitious than the latter ones. Despite all the promising performance results, very few studies reported tests under a formal setup. Almost all the studies relied on custom dictionaries; however, they used them in conjunction with a controlled terminology, most commonly the UMLSⓇ metathesaurus. Identification of sections in EHR narratives is gaining popularity for improving clinical extraction projects. This study enabled the community working on clinical NLP to gain a formal analysis of this task, including the most successful ways to perform it.

Analyses of the accuracy of machine learning algorithms for predicting stock market indices typically employ only one or a small set of stock indices and a small number of time periods. Moreover, these analyses generally ignore the influence of market efficiency on algorithm accuracy, despite theoretical evidence of the potential for such an effect. This paper aims to fill this gap by proposing and applying a method focused on the analysis of the accuracy of stock market prediction models in comparison with market efficiency. This method is applied to a dataset comprising 55 markets and 65 periods to compare the most accurate and frequently used algorithms for stock index prediction: support vector machines, artificial neural networks, gradient-boosted trees, Naive Bayes, random forest, logistic regression, and long-short term memory. These algorithms were trained to predict stock market indices using technical indicators as input. After analyzing the algorithms’ results, we present a detailed comparative analysis of their accuracy supported by a set of nonparametric measures. In addition, dynamic panel data analysis is used to determine whether there is a relationship between stock market’s efficiency and algorithmic precision. We highlight the algorithms that tend to show the best performance in terms of accuracy and obtain interesting results regarding market efficiency.

Background: Globally, mental health (MH) problems increasingly affect young people, contributing significantly to disability and disease. In low- and middle-income countries, such as Colombia, barriers to accessing care exacerbate the treatment gap. In addition, the lack of widespread digital interventions further deepens the digital health divide between the Global North and Global South, limiting equitable access to innovative MH solutions. Objective: This study aims to co-design and develop an MH platform using participatory design methodologies and conduct a 15-month naturalistic observational trial to assess its feasibility among Colombian youth. Methods: This study used a mixed methods approach within a structured research and development cycle. To ensure a user-centered design, we began with a series of co-design workshops, where stakeholders collaboratively identified key user needs. Following this, usability testing was conducted in 2 stages, alpha and beta, using the System Usability Scale (SUS) to assess functionality and user experience. To capture real-world interactions, a naturalistic observational trial ran from July 2022 to October 2023, collecting data on user engagement and system performance. This study integrated quantitative and qualitative analyses. Results: A total of 146 individuals participated in the co-design process, with 110 (75.3%) contributing to the development of platform components and 36 (24.7%) participating in usability testing. The co-designed platform integrated several key features, including social media and advertising, an MH screening tool, registration, targeted psychoeducational resources, automated tailored recommendations, and a “track-as-you-go” feature for continuous MH monitoring. Additional elements included user-friendly follow-up graphs, telecounseling integration, customizable well-being nudges, an emergency button, and gamification components to enhance engagement. During usability testing, the beta prototype received a median SUS score of 85.0 (IQR 80-92.5), indicating high usability. In the subsequent observational trial, which ran from July 2022 to October 2023, a total of 435 users interacted with the platform—314 (72.2%) as registered users and 121 (27.8%) anonymously. Emotional distress was prevalent, with 63.7% (200/314) of the registered users and 61.2% (74/121) of the anonymous users reporting distress, as measured by the 6-item Kessler Psychological Distress Scale. Despite 102 users requesting telecounseling, only 26.5% (27/102) completed a session. While usability scores remained high, engagement challenges emerged, with only 18.8% (59/314) of the users continuing platform use beyond the first day. Conclusions: This study explored the development and user experience of a youth MH platform in Colombia, demonstrating that a cocreation approach is both feasible and effective. By actively involving users throughout the design process, the platform achieved high usability and incorporated features that resonated with its target audience. However, sustaining long-term engagement remains a challenge, as does addressing privacy concerns, particularly for younger users. These findings highlight the importance of continuous user-centered refinement to enhance both accessibility and retention in digital MH interventions.

The growing popularity of social networking platforms worldwide has substantially increased the presence of offensive language on these platforms. To date, most of the systems developed to mitigate this challenge focus primarily on English content. However, this issue is a global concern, and therefore, other languages, such as Spanish, are involved. This article addresses the task of identifying hate speech, racism, and misogyny in Spanish within the Colombian context on social networks, and introduces a gold standard dataset specifically developed for this purpose. Indeed, the experiment compares the performance of TLM models from Deep Learning methods, such as BERT, Roberta, XLM, and BETO adjusted to the Colombian slang domain, then compares the best TLM model against a GPT, having a significant impact on achieving more accurate predictions in this task. Finally, this study provides a detailed understanding of the different components used in the system, including the architecture of the models and the selection of functions. The best results show that the BERT model achieves an accuracy of 83.6% for hate speech detection, while the GPT model achieves an accuracy of 90.8% for racism speech and 90.4% for misogyny detection.

Objective: Electronic medical records (EMR) typically contain both structured attributes as well as narrative text. The usefulness of EMR for research and administration is hampered by the difficulty in automatically analyzing their narrative portions. Accordingly, this paper proposes SPIRE, a strategy for prioritizing EMR, using natural language processing in combination with analysis of structured data, in order to identify and rank EMR that match specific queries from clinical researchers and health administrators. Materials and Methods: The resulting software tool was evaluated technically and validated with three cases (heart failure, pulmonary hypertension and diabetes mellitus) compared against expert obtained results. Results and Discussion: Our preliminary results show high sensitivity (70%, 82% and 87% respectively) and specificity (85%, 73.7% and 87.5%) in the resulting set of records. The AUC was between 0.84 and 0.9. Conclusions: SPIRE was successfully implemented and used in the context of a university hospital information system, enabling clinical researchers to obtain prioritized EMR to solve their information needs through collaborative search templates with faster and more accurate results than other existing methods.

Objective: Colombia's mental health system is plagued by significant shortages in services and health professionals. Digital health technologies enable access to information and care, overcoming barriers related to systemic limitations, geographic location, cost and stigma. This paper aims to characterise the sample of Colombians who sought telecounselling and support through Mentes Colectivas, a web-based mental health counselling platform. Methods: Participants provided basic demographics and completed the Kessler 6 to track psychological distress. Counsellors collected information about participants’ level of functional impairment, presenting problems, mental health warning signs and session attendance. Descriptive statistics were used to characterise the sample. A range of inferential statistics were used to analyse group differences based on age and session, explore associations within clinical presentations, examine predictors of session attendance and analyse clinical differences between episodes of care. Results: A total of 6442 participants (mean age = 33.6 years; 78.5% female) attended an initial session, with 35.7% returning for at least one follow-up session. Participants on average reported moderate levels of psychological distress, with young people reporting significantly higher distress relative to adults and older adults. Symptoms of anxiety and depression and sleep disturbances were most common. Conclusions: This research confirms the feasibility of Mentes Colectivas to promote help-seeking and support self-management of mental health across the lifespan in Colombia. Digital health technologies have the potential to play a vital role in increasing equity of access to care for the Colombian population, improving mental health and functioning as well as potentially strengthening the health of families and communities.