Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia

Michael Cabanillas-Carbonell

doi:10.1007/978-3-032-24724-7_40

Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia

Michael Cabanillas-Carbonell

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

This study aimed to develop an intelligent virtual assistant for anemia management using Retrieval-Augmented Generation (RAG) integrated with large language models (LLMs). Through a comparative experimental methodology, four models — GPT-4 Turbo, LLaMA-3-70B, Mistral 7B, and Gemini 1.5 Pro — were evaluated before and after RAG implementation. The results showed notable improvements, with LLaMA-3-70B reaching 89% diagnostic accuracy (a 17% increase) and an F1-score of 0.85 in anemia subtype classification. The system achieved 95% accuracy in nutritional anemia and 93% accuracy in emergency cases, while maintaining 82% accuracy in complex cases. User testing indicated high satisfaction (4.6/5) and strong clinical utility. In conclusion, integrating RAG-based retrieval, medical domain expertise, and mobile accessibility enhanced diagnostic precision and knowledge access, demonstrating the potential of specialized AI to improve anemia management in resource-limited healthcare environments.

Original language	English
Title of host publication	Advances in Digital Health and Medical Bioengineering 2 - Volume 1
Subtitle of host publication	Medical Devices, Measurements, and Artificial Intelligence Applications
Editors	Hariton-Nicolae Costin, Ratko Magjarevic, Gabriela-Gladiola Petroiu
Pages	399-413
Number of pages	15
DOIs	https://doi.org/10.1007/978-3-032-24724-7_40
State	Published - 2026
Event	13th International Conference on E-Health and Bioengineering, EHB 2025 - Iasi, Romania Duration: 13 Nov 2025 → 14 Nov 2025

Publication series

Name	IFMBE Proceedings
Volume	142 IFMBE
ISSN (Print)	1680-0737
ISSN (Electronic)	1433-9277

Conference

Conference	13th International Conference on E-Health and Bioengineering, EHB 2025
Country/Territory	Romania
City	Iasi
Period	13/11/25 → 14/11/25

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

anemia
LLM
public health
RAG
Virtual assistant

Access to Document

10.1007/978-3-032-24724-7_40

Cite this

Cabanillas-Carbonell, M. (2026). Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia. In H.-N. Costin, R. Magjarevic, & G.-G. Petroiu (Eds.), Advances in Digital Health and Medical Bioengineering 2 - Volume 1: Medical Devices, Measurements, and Artificial Intelligence Applications (pp. 399-413). (IFMBE Proceedings; Vol. 142 IFMBE). https://doi.org/10.1007/978-3-032-24724-7_40

Cabanillas-Carbonell, Michael. / Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia. Advances in Digital Health and Medical Bioengineering 2 - Volume 1: Medical Devices, Measurements, and Artificial Intelligence Applications. editor / Hariton-Nicolae Costin ; Ratko Magjarevic ; Gabriela-Gladiola Petroiu. 2026. pp. 399-413 (IFMBE Proceedings).

@inproceedings{8e0293dd7a404cdcb171185001476597,

title = "Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia",

abstract = "This study aimed to develop an intelligent virtual assistant for anemia management using Retrieval-Augmented Generation (RAG) integrated with large language models (LLMs). Through a comparative experimental methodology, four models — GPT-4 Turbo, LLaMA-3-70B, Mistral 7B, and Gemini 1.5 Pro — were evaluated before and after RAG implementation. The results showed notable improvements, with LLaMA-3-70B reaching 89\% diagnostic accuracy (a 17\% increase) and an F1-score of 0.85 in anemia subtype classification. The system achieved 95\% accuracy in nutritional anemia and 93\% accuracy in emergency cases, while maintaining 82\% accuracy in complex cases. User testing indicated high satisfaction (4.6/5) and strong clinical utility. In conclusion, integrating RAG-based retrieval, medical domain expertise, and mobile accessibility enhanced diagnostic precision and knowledge access, demonstrating the potential of specialized AI to improve anemia management in resource-limited healthcare environments.",

keywords = "anemia, LLM, public health, RAG, Virtual assistant",

author = "Michael Cabanillas-Carbonell",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.; 13th International Conference on E-Health and Bioengineering, EHB 2025 ; Conference date: 13-11-2025 Through 14-11-2025",

year = "2026",

doi = "10.1007/978-3-032-24724-7\_40",

language = "English",

isbn = "9783032247230",

series = "IFMBE Proceedings",

pages = "399--413",

editor = "Hariton-Nicolae Costin and Ratko Magjarevic and Gabriela-Gladiola Petroiu",

booktitle = "Advances in Digital Health and Medical Bioengineering 2 - Volume 1",

}

Cabanillas-Carbonell, M 2026, Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia. in H-N Costin, R Magjarevic & G-G Petroiu (eds), Advances in Digital Health and Medical Bioengineering 2 - Volume 1: Medical Devices, Measurements, and Artificial Intelligence Applications. IFMBE Proceedings, vol. 142 IFMBE, pp. 399-413, 13th International Conference on E-Health and Bioengineering, EHB 2025, Iasi, Romania, 13/11/25. https://doi.org/10.1007/978-3-032-24724-7_40

Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia. / Cabanillas-Carbonell, Michael.
Advances in Digital Health and Medical Bioengineering 2 - Volume 1: Medical Devices, Measurements, and Artificial Intelligence Applications. ed. / Hariton-Nicolae Costin; Ratko Magjarevic; Gabriela-Gladiola Petroiu. 2026. p. 399-413 (IFMBE Proceedings; Vol. 142 IFMBE).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia

AU - Cabanillas-Carbonell, Michael

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

PY - 2026

Y1 - 2026

N2 - This study aimed to develop an intelligent virtual assistant for anemia management using Retrieval-Augmented Generation (RAG) integrated with large language models (LLMs). Through a comparative experimental methodology, four models — GPT-4 Turbo, LLaMA-3-70B, Mistral 7B, and Gemini 1.5 Pro — were evaluated before and after RAG implementation. The results showed notable improvements, with LLaMA-3-70B reaching 89% diagnostic accuracy (a 17% increase) and an F1-score of 0.85 in anemia subtype classification. The system achieved 95% accuracy in nutritional anemia and 93% accuracy in emergency cases, while maintaining 82% accuracy in complex cases. User testing indicated high satisfaction (4.6/5) and strong clinical utility. In conclusion, integrating RAG-based retrieval, medical domain expertise, and mobile accessibility enhanced diagnostic precision and knowledge access, demonstrating the potential of specialized AI to improve anemia management in resource-limited healthcare environments.

AB - This study aimed to develop an intelligent virtual assistant for anemia management using Retrieval-Augmented Generation (RAG) integrated with large language models (LLMs). Through a comparative experimental methodology, four models — GPT-4 Turbo, LLaMA-3-70B, Mistral 7B, and Gemini 1.5 Pro — were evaluated before and after RAG implementation. The results showed notable improvements, with LLaMA-3-70B reaching 89% diagnostic accuracy (a 17% increase) and an F1-score of 0.85 in anemia subtype classification. The system achieved 95% accuracy in nutritional anemia and 93% accuracy in emergency cases, while maintaining 82% accuracy in complex cases. User testing indicated high satisfaction (4.6/5) and strong clinical utility. In conclusion, integrating RAG-based retrieval, medical domain expertise, and mobile accessibility enhanced diagnostic precision and knowledge access, demonstrating the potential of specialized AI to improve anemia management in resource-limited healthcare environments.

KW - anemia

KW - LLM

KW - public health

KW - RAG

KW - Virtual assistant

UR - https://www.scopus.com/pages/publications/105041665676

U2 - 10.1007/978-3-032-24724-7_40

DO - 10.1007/978-3-032-24724-7_40

M3 - Conference contribution

AN - SCOPUS:105041665676

SN - 9783032247230

T3 - IFMBE Proceedings

SP - 399

EP - 413

BT - Advances in Digital Health and Medical Bioengineering 2 - Volume 1

A2 - Costin, Hariton-Nicolae

A2 - Magjarevic, Ratko

A2 - Petroiu, Gabriela-Gladiola

T2 - 13th International Conference on E-Health and Bioengineering, EHB 2025

Y2 - 13 November 2025 through 14 November 2025

ER -

Cabanillas-Carbonell M. Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia. In Costin HN, Magjarevic R, Petroiu GG, editors, Advances in Digital Health and Medical Bioengineering 2 - Volume 1: Medical Devices, Measurements, and Artificial Intelligence Applications. 2026. p. 399-413. (IFMBE Proceedings). doi: 10.1007/978-3-032-24724-7_40

Development of an Application with Virtual Assistant Based on LLM for the Knowledge Domain on Anemia

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Other files and links

Fingerprint

Cite this