COVID-19 Vaccine Equity and Access: Case Study for Health Care Chatbots
Notice bibliographique
Résumé
BACKGROUND: Disparities in COVID-19 information and vaccine access have emerged during the pandemic. Individuals from historically excluded communities (eg, Black and Latin American) experience disproportionately negative health outcomes related to COVID-19. Community gaps in COVID-19 education, social, and health care services (including vaccines) should be prioritized as a critical effort to end the pandemic. Misinformation created by the politicization of COVID-19 and related public health measures has magnified the pandemic's challenges, including access to health care, vaccination and testing efforts, as well as personal protective equipment. Information and Communication Technology (ICT) has been demonstrated to reduce the gaps of marginalization in education and access among communities. Chatbots are an increasingly present example of ICTs, particularly in health care and in relation to the COVID-19 pandemic. OBJECTIVE: This project aimed to (1) follow an inclusive and theoretically driven design process to develop and test a COVID-19 information ICT bilingual (English and Spanish) chatbot tool named "Ana" and (2) characterize and evaluate user experiences of these innovative technologies. METHODS: Ana was developed following a multitheoretical framework, and the project team was comprised of public health experts, behavioral scientists, community members, and medical team. A total of 7 iterations of ß chatbots were tested, and a total of 22 ß testers participated in this process. Content was curated primarily to provide users with factual answers to common questions about COVID-19. To ensure relevance of the content, topics were driven by community concerns and questions, as ascertained through research. Ana's repository of educational content was based on national and international organizations as well as interdisciplinary experts. In the context of this development and pilot project, we identified an evaluation framework to explore reach, engagement, and satisfaction. RESULTS: A total of 626 community members used Ana from August 2021 to March 2022. Among those participants, 346 used the English version, with an average of 43 users per month; and 280 participants used the Spanish version, with an average of 40 users monthly. Across all users, 63.87% (n=221) of English users and 22.14% (n=62) of Spanish users returned to use Ana at least once; 18.49% (n=64) among the English version users and 18.57% (n=52) among the Spanish version users reported their ranking. Positive ranking comprised the "smiley" and "loved" emojis, and negative ranking comprised the "neutral," "sad," and "mad" emojis. When comparing negative and positive experiences, the latter was higher across Ana's platforms (English: n=41, 64.06%; Spanish: n=41, 77.35%) versus the former (English: n=23, 35.93%; Spanish: n=12, 22.64%). CONCLUSIONS: This pilot project demonstrated the feasibility and capacity of an innovative ICT to share COVID-19 information within diverse communities. Creating a chatbot like Ana with bilingual content contributed to an equitable approach to address the lack of accessible COVID-19-related information.
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 machine sur la base complète
Imitation des enseignantsNi prévalence calibrée, ni vérité terrain. Validation humaine à venir. Le volet Gemma est une étiquette directe du modèle pour chaque travail de la base, lue sur la notice réduite au titre. Le volet Codex est un classifieur appris des 10 348 étiquettes directes de Codex et calibré sur les taux pondérés de l'échantillon; les champs sans appui suffisant ne portent aucun appel Codex. Le mode candidate est l'union des deux volets; le consensus est leur intersection. Ces sorties portent le statut machine_predicted_unvalidated et ne sont pas des étiquettes humaines.
Scores du classifieur distillé par catégorie (deux têtes)
| Catégorie | Codex | Gemma |
|---|---|---|
| Métarecherche | 0,008 | 0,023 |
| Méta-épidémiologie (sens strict) | 0,001 | 0,001 |
| Méta-épidémiologie (sens large) | 0,001 | 0,001 |
| Bibliométrie | 0,002 | 0,002 |
| Études des sciences et des technologies | 0,015 | 0,004 |
| Communication savante | 0,004 | 0,003 |
| Science ouverte | 0,003 | 0,007 |
| Intégrité de la recherche | 0,004 | 0,004 |
| Charge utile insuffisante (le modèle a refusé de juger) | 0,006 | 0,000 |
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 source (Gemma direct ou Codex distillé), 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 ».