Your browser doesn't support javascript.
loading
A transparent machine learning algorithm uncovers HbA1c patterns associated with therapeutic inertia in patients with type 2 diabetes and failure of metformin monotherapy.
Musacchio, Nicoletta; Zilich, Rita; Masi, Davide; Baccetti, Fabio; Nreu, Besmir; Bruno Giorda, Carlo; Guaita, Giacomo; Morviducci, Lelio; Muselli, Marco; Ozzello, Alessandro; Pisani, Federico; Ponzani, Paola; Rossi, Antonio; Santin, Pierluigi; Verda, Damiano; Di Cianni, Graziano; Candido, Riccardo.
Afiliación
  • Musacchio N; AMD-AI National Group Coordinator, UOS Integrating Primary and Specialist Care, ASST Nord Milano, Via Filippo Carcano 17, 20149 Milan, Italy.
  • Zilich R; Mix-x Partner, Via Circonvallazione 5, Ivrea (TO), Italy. Electronic address: rita.zilich@mix-x.com.
  • Masi D; Department of Experimental Medicine, Section of Medical Pathophysiology, Food Science and Endocrinology, Sapienza University of Rome, 00161 Rome, Italy. Electronic address: davide.masi@uniroma1.it.
  • Baccetti F; ASL Nordovest Toscana. ASL Nordovest, Massa Carrara (MS), Italy. Electronic address: fabio.baccetti@uslnordovest.toscana.it.
  • Nreu B; Diabetology Unit, Careggi Hospital, Largo G.A. Brambilla, 3, 50134 Florence (FI), Italy. Electronic address: nreub@aou-careggi.toscana.it.
  • Bruno Giorda C; Diabetes and Endocrinology Unit, ASL TO5, Chieri, Turin (TO), Italy.
  • Guaita G; Diabetes and Endocrinology UNIT ASL SULCIS, Carbonia-Iglesias, Italy. Electronic address: giacomo.guaita@aslsulscis.it.
  • Morviducci L; UOC Diabetologia e Dietologia, Ospedale S. Spirito - ASL Roma 1, Borgo Santo Spirito, Roma (RM), Italy. Electronic address: leliomorviducci@aslroma1.it.
  • Muselli M; Rulex Innovation Labs, Rulex Inc, Via Felice Romani 9/2, 16122 Genoa (GE), Italy. Electronic address: marco.muselli@ieiit.cnr.it.
  • Ozzello A; AMD regional past President, Gruppo nazionale AI AMD, Bruino, Torino (TO), Italy.
  • Pisani F; Mix-x Partner, Via Circonvallazione 5, Ivrea (TO), Italy.
  • Ponzani P; Diabetes and Metabolic Disease Unit ASL 4 Liguria, Chiavari (GE), Italy. Electronic address: paola.ponzani@asl4.liguria.it.
  • Rossi A; IRCCS Ospedale Galeazzi-Sant'Ambrogio, 20149 Milan, Italy; Department of Biomedical and Clinical Sciences, Università di Milano, Milan, Italy. Electronic address: antonio.rossi1@unimi.it.
  • Santin P; Data Scientist Deimos, Udine (UD), Italy. Electronic address: p.santin@e-deimos.it.
  • Verda D; Rulex Innovation Labs, Rulex Inc, Via Felice Romani 9/2, 16122 Genoa (GE), Italy. Electronic address: damiano.verda@rulex.ai.
  • Di Cianni G; AMD Past President, Diabetes and Metabolic Diseases Unit, Health Local Unit Nord-West Tuscany, Livorno Hospital, Pad. 4 Viale Alfieri 36, Livorno (LI), Italy. Electronic address: graziano.dicianni@uslnordovest.toscana.it.
  • Candido R; AMD New President, Azienda Sanitaria Universitaria Giuliano Isontina, 34128 Trieste, Italy. Electronic address: riccardo.candido@asugi.sanita.fvg.it.
Int J Med Inform ; 190: 105550, 2024 Oct.
Article en En | MEDLINE | ID: mdl-39059083
ABSTRACT

AIMS:

This study aimed to identify and categorize the determinants influencing the intensification of therapy in Type 2 Diabetes (T2D) patients with suboptimal blood glucose control despite metformin monotherapy.

METHODS:

Employing the Logic Learning Machine (LLM), an advanced artificial intelligence system, we scrutinized electronic health records of 1.5 million patients treated in 271 diabetes clinics affiliated with the Italian Association of Medical Diabetologists from 2005 to 2019. Inclusion criteria comprised patients on metformin monotherapy with two consecutive mean HbA1c levels exceeding 7.0%. The cohort was divided into "inertia-NO" (20,067 patients with prompt intensification) and "inertia-YES" (13,029 patients without timely intensification).

RESULTS:

The LLM model demonstrated robust discriminatory ability among the two groups (ROC-AUC = 0.81, accuracy = 0.71, precision = 0.80, recall = 0.71, F1 score = 0.75). The main novelty of our results is indeed the identification of two main distinct subtypes of therapeutic inertia. The first exhibited a gradual but steady HbA1c increase, while the second featured a moderate, non-uniform rise with substantial fluctuations.

CONCLUSIONS:

Our analysis sheds light on the significant impact of HbA1c levels over time on therapeutic inertia in patients with T2D, emphasizing the importance of early intervention in the presence of specific HbA1c patterns.
Asunto(s)
Palabras clave
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Hemoglobina Glucada / Diabetes Mellitus Tipo 2 / Aprendizaje Automático / Hipoglucemiantes / Metformina Límite: Aged / Female / Humans / Male / Middle aged Idioma: En Revista: Int J Med Inform Asunto de la revista: INFORMATICA MEDICA Año: 2024 Tipo del documento: Article País de afiliación: Italia Pais de publicación: Irlanda
Texto completo
Añadir a Mi BVS
Imprimir
XML
PubMed Links
Buscar en Google

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Hemoglobina Glucada / Diabetes Mellitus Tipo 2 / Aprendizaje Automático / Hipoglucemiantes / Metformina Límite: Aged / Female / Humans / Male / Middle aged Idioma: En Revista: Int J Med Inform Asunto de la revista: INFORMATICA MEDICA Año: 2024 Tipo del documento: Article País de afiliación: Italia Pais de publicación: Irlanda