Connecting patient care to global health trends by health app analytics
Notice bibliographique
Résumé
The spectrum of mobile health applications, or ‘apps’, follows the supply chain of health services from storage of and access to knowledge, training and reference tools, diagnostic and treatment supply chain management, clinical care and direct patient services. Their potential for improving health services for the world's poor now seems obvious, as mobile phones rest in the hands of the majority of people in the developing world. In this issue of Public Health Action, Wright et al. report on the international use of a recent mobile health (mHealth) app developed by Medicins Sans Frontieres (MSF) to support their own and other care providers with clinical care guidelines in remote and resource-limited settings.1 The MSF Guidance app improved field accessibility of their guidelines over paper versions, which often suffered from limited supply and lack of accessibility in the field. The MSF guidelines are now freely available to anyone with an Android or iOS phone and (even intermittent) data connections. The app has the additional benefit of tracking the health subject matter accessed, and therefore has the potential to be used to track geographical outbreaks of certain conditions. Usage analytics of the app, in this case offered freely by Google Analytics, have empowered the back end of the application to consolidate valuable information on geographical health interests of the app users, stamped in time. This is key. By using some basic selection criteria, such as time spent on each app page as an indication of what information is likely being consumed by the user (an algorithm that could eventually be further refined for big data analysis), geographic interest in disease conditions can be identified. This was illustrated by the Ebola page access peak in 2014, when guidelines were released to support the West Africa outbreak, and a spike in respiratory infection views in South Sudan in November. As the authors mention, many spikes may reflect users' general educational needs, or interest in current global health issues; however, they may also indicate increased presentation of clinical syndromes that may precede definitive causal detection of outbreaks or other health trends. If evaluated in real-time, the approach could be an electronic flag to emerging health issues. The authors note that one limitation is not being able to identify which users were MSF clinical staff; however, this may be interpreted as a strength. MSF currently operates in over 70 countries worldwide, yet the app was downloaded in 150 countries, indicating spillover in use and the potential to contribute to surveillance on an even larger scale. By publishing these findings, they are starting to build a publicly available database of clinician health information seeking. The MSF Guidance app, while used widely across the globe, is relatively new, and represents only a portion of the world's frontline clinical app users.2 Others should be encouraged to publish their analytics. At a minimum, information sharing can provide static cross-sections of clinicians' needs and interests, akin to meta-analyses. Beyond that, globally interconnected real-time monitoring of front-line clinicians who are using health apps, regardless of their affiliation, could be a powerful way to monitor global trends from the front lines. Typical for MSF, the top three countries using their particular app were in areas of significant poverty and insecurity, ensuring the information technology revolution is reaching out to those who may need it most.
Récupéré en direct depuis OpenAlex et désinversé. Les résumés ne sont pas conservés dans cette base de données : les index inversés représentent 8,6 Go des 9,3 Go de texte de la base, et le serveur dispose de 13 Go libres.
Comment cette classification a été obtenuedéplier
Prédiction distillée sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Apprise à partir de 10 348 étiquettes directes de Codex et de 10 348 étiquettes directes de Gemma. Le mode candidate est l'union des têtes enseignantes seuillées; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont ni des étiquettes humaines ni des étiquettes directes de modèles de pointe.
Scores Codex et Gemma par catégorie
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,005 | 0,001 |
| Méta-épidémiologie (sens strict) | 0,000 | 0,001 |
| Méta-épidémiologie (sens large) | 0,001 | 0,000 |
| Bibliométrie | 0,001 | 0,003 |
| Études des sciences et des technologies | 0,004 | 0,000 |
| Communication savante | 0,000 | 0,000 |
| Science ouverte | 0,000 | 0,000 |
| Intégrité de la recherche | 0,000 | 0,001 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,000 | 0,001 |
Scores machine (provisoires)
Les deux têtes enseignantes du modèle étudiant, lues sur ce travail. Un score ordonne la base pour la relecture; il n'affirme jamais une catégorie, et le statut de validation accompagne chaque rangée tel quel.
Scores de référence d'un modèle non mature (critères de maturité non atteints, 7 itérations). Un score ordonne; il n'affirme jamais une catégorie.
score_only:v0-immature-baseline · tel quel depuis la passe de notation : score_only signifie que le nombre peut ordonner les travaux, et qu'aucune étiquette de catégorie n'en découleClassification
machine, non validéePrédiction automatique; un appel candidat d’une seule tête enseignante, pas un consensus.
Le détail, modèle par modèle et score par score, se trouve en fin de page sous « Comment cette classification a été obtenue ».