The American Society of Clinical Oncology (ASCO) has released the principles for the responsible use of artificial intelligence (AI) in oncology emphasizing fairness, accountability, oversight, equity, and transparency. However, the extent to which these principles are followed is unknown. The goal of this study was to assess the presence of biases and the quality of studies on AI models according to the ASCO principles and examine their potential impact through citation analysis and subsequent research applications. A review of original research articles centered on the evaluation of predictive models for cancer diagnosis published in the ASCO journal dedicated to informatics and data science in clinical oncology was conducted. Seventeen potential bias criteria were used to evaluate the sources of bias in the studies, aligned with the ASCO’s principles for responsible AI use in oncology. The CREMLS checklist was applied to assess the study quality, focusing on the reporting standards, and the performance metrics along with citation counts of the included studies were analyzed. Nine studies were included. The most common biases were environmental and life-course bias, contextual bias, provider expertise bias, and implicit bias. Among the ASCO principles, the least adhered to were transparency, oversight and privacy, and human-centered AI application. Only 22% of the studies provided access to their data. The CREMLS checklist revealed the deficiencies in methodology and evaluation reporting. Most studies reported performance metrics within moderate to high ranges. Additionally, two studies were replicated in the subsequent research. In conclusion, most studies exhibited various types of bias, reporting deficiencies, and failure to adhere to the principles for responsible AI use in oncology, limiting their applicability and reproducibility. Greater transparency, data accessibility, and compliance with international guidelines are recommended to improve the reliability of AI-based research in oncology.

Background: The introduction of natural language processing (NLP) technologies has significantly enhanced the potential of self-administered interventions for treating anxiety and depression by improving human-computer interactions. Although these advances, particularly in complex models such as generative artificial intelligence (AI), are highly promising, robust evidence validating the effectiveness of the interventions remains sparse. Objective: The aim of this study was to determine whether self-administered interventions based on NLP models can reduce depressive and anxiety symptoms. Methods: We conducted a systematic review and meta-analysis. We searched Web of Science, Scopus, MEDLINE, PsycINFO, IEEE Xplore, Embase, and Cochrane Library from inception to November 3, 2023. We included studies with participants of any age diagnosed with depression or anxiety through professional consultation or validated psychometric instruments. Interventions had to be self-administered and based on NLP models, with passive or active comparators. Outcomes measured included depressive and anxiety symptom scores. We included randomized controlled trials and quasi-experimental studies but excluded narrative, systematic, and scoping reviews. Data extraction was performed independently by pairs of authors using a predefined form. Meta-analysis was conducted using standardized mean differences (SMDs) and random effects models to account for heterogeneity. Results: In all, 21 articles were selected for review, of which 76% (16/21) were included in the meta-analysis for each outcome. Most of the studies (16/21, 76%) were recent (2020-2023), with interventions being mostly AI-based NLP models (11/21, 52%); most (19/21, 90%) delivered some form of therapy (primarily cognitive behavioral therapy: 16/19, 84%). The overall meta-analysis showed that self-administered interventions based on NLP models were significantly more effective in reducing both depressive (SMD 0.819, 95% CI 0.389-1.250; P<.001) and anxiety (SMD 0.272, 95% CI 0.116-0.428; P=.001) symptoms compared to various control conditions. Subgroup analysis indicated that AI-based NLP models were effective in reducing depressive symptoms (SMD 0.821, 95% CI 0.207-1.436; P<.001) compared to pooled control conditions. Rule-based NLP models showed effectiveness in reducing both depressive (SMD 0.854, 95% CI 0.172-1.537; P=.01) and anxiety (SMD 0.347, 95% CI 0.116-0.578; P=.003) symptoms. The meta-regression showed no significant association between participants’ mean age and treatment outcomes (all P>.05). Although the findings were positive, the overall certainty of evidence was very low, mainly due to a high risk of bias, heterogeneity, and potential publication bias. Conclusions: Our findings support the effectiveness of self-administered NLP-based interventions in alleviating depressive and anxiety symptoms, highlighting their potential to increase accessibility to, and reduce costs in, mental health care. Although the results were encouraging, the certainty of evidence was low, underscoring the need for further high-quality randomized controlled trials and studies examining implementation and usability. These interventions could become valuable components of public health strategies to address mental health issues. Trial Registration: PROSPERO International Prospective Register of Systematic Reviews CRD42023472120; https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023472120

Background: In Peru, there is an increase in the creation of mobile health (mHealth) apps; however, this situation could present problems related to the quality of information these apps share, data security and privacy, usability, and effectiveness, as there is no specific local regulation about their creation and use. Objective: The objective of this study was to review mHealth apps created, uploaded, or used in Peru, and perform an analysis of the national regulatory framework that could be applied to evaluate whether there is a need to develop and implement a specific regulation to these apps. Methods: A total of 3 reviews were performed. First, we reviewed information about Peruvian mHealth apps created up to May 2019 from scientific publications, news, government communications, and virtual stores, and evaluated their purpose, creator, and the available evidence of their usability and effectiveness. The second review was carried out by taking a sample of the 10 most commonly used mHealth apps in Peru (regardless of the country of creation), to evaluate the information they collect and classify them according to the possible risks that they could present in terms of security and privacy. In addition, we evaluated whether they refer to or endorse the information they provided. Finally, in the third review, we searched for Peruvian standards related to electronic health (eHealth) that involve information technology that can be applied to regulate these apps. Results: A total of 66 apps meeting our inclusion criteria were identified; of these, 47% (n=31) belonged to government agencies and 47% (n=31) were designed for administrative purposes (private and government agencies). There was no evidence about the usability or effectiveness of any of these apps. Concerning the 10 most commonly used mHealth apps in Peru, about the half of them gathered user information that could be leaked, changed, or lost, thus posing a great harm to their users or to their related patients. In addition, 6/10 (60%) of these apps did not mention the source of the information they provided. Among the Peruvian norms, the Law on the Protection of Personal Data, Law on Medical Devices, and administrative directives on standards and criteria for health information systems have some regulations that could be applied to these apps; however, these do not fully cover all aspects concerning the evaluation of security and privacy of data, quality of provided information, and evidence of an app’s usability and effectiveness. Conclusions: Because many Peruvian mHealth apps have issues related to security and privacy of data, quality of information provided, and lack of available evidence of their usability and effectiveness, there is an urgent need to develop a regulatory framework based on existing medical device and health information system norms in order to promote the evaluation and regulation of all the aforesaid aspects, including the creation of a national repository for these apps that describes all these characteristics.

Background: Complicated grief (CG) resulting from poor adaptation to the death of a close person may have been related with the presence of other mental health problems in older adults in Peru during the COVID-19 pandemic. Our study aimed to assess the association between CG and anxiety, depression, and suicidal ideation in older adults in Peru in the context of the COVID-19 pandemic. Methods: We conducted a cross-sectional analysis using data from the “Socioemotional evaluation form” applied in 2020 to mental health problems in older adults attending the Peruvian Social Security (EsSalud). For our study, we included older adults who reported the death of a close person during the last six months when this assessment was performed. CG, depression, anxiety, and suicidal ideation were initially evaluated using validated questionnaires. The association between CG and the presence of mental health problems was calculated through multivariate analysis, where prevalence ratios (PR) were estimated with 95% confidence intervals (CI). Results: Of the 249 older adults included, 175 (70.3%) were female with a median age of 71 years (interquartile range: 9), and 35 (14.1%) reported the presence of CG. It was found that CG in this population was associated with the presence of anxiety (PR: 1.35, 95% CI: 0.98 to 1.85), depression (PR: 1.44, 95% CI: 1.06 to 1.95), and suicidal ideation (PR: 2.84, 95% CI: 1.06 to 7.59). Conclusions: CG is related to the presence of mental health problems in older adults in Peru. It is essential to implement measures that facilitate the prevention and proper management of this condition in this population, especially in the context of high population mortality such as the COVID-19 pandemic.

There is a paucity of information about the association between acculturation and alcohol consumption in rural-to-urban migrants who move to urban environments usually characterized by a higher prevalence of alcohol consumption than their rural places of origin. To evaluate the cross-sectional association between surrogates of acculturation and alcohol consumption in Peruvian rural-to-urban migrants; to explore the effects of sex and age at migration on these associations; and to explore this association longitudinally. Data from the PERU MIGRANT Study, which evaluated a cohort of Peruvian rural-to-urban migrants from 2007 to 2012, were analyzed. Four acculturation surrogates were evaluated: language preference on the radio, language spoken at home, Spanish proficiency, and length of residence in urban area. Alcohol consumption was defined as having consumed alcohol in the last year at the time of the baseline survey, while onset of alcohol consumption was defined as having consumed alcohol in the last year at the follow-up survey. Poisson regressions with robust variance were performed to estimate crude and adjusted prevalence ratios (PR) and relative risks (RR) with a 95% confidence interval (95% CI) to cross-sectional and longitudinal analyses respectively. Data from 567 rural-to-urban migrants, mean age 47.6 years (SD ±11.5), 52% females, was included in the study. Crude cross-sectional analyses showed an association between acculturation surrogates and alcohol consumption, but these were not observed in adjusted regressions. In the sex-stratified analyses, only women showed an association between Spanish proficiency and alcohol consumption, where those with higher language proficiency had a 22% higher prevalence of alcohol consumption (PR: 1.22, 95% CI: 1.04–1.43). Analyses stratified by age at migration showed no association between acculturation surrogates and alcohol consumption. On the longitudinal analyses, acculturation surrogates were not associated with the onset of alcohol consumption. No association between acculturation surrogates and alcohol consumption in cross-sectional and longitudinal analyses were found. The only exception was observed in female migrants according to their Spanish proficiency and alcohol consumption .