{"doi":"10.1001/jamanetworkopen.2023.40232","title":"Use of Voice-Based Conversational Artificial Intelligence for Basal Insulin Prescription Management Among Patients With Type 2 Diabetes","abstract":"<jats:sec><jats:title>Importance</jats:title><jats:p>Optimizing insulin therapy for patients with type 2 diabetes can be challenging given the need for frequent dose adjustments. Most patients receive suboptimal doses and do not achieve glycemic control.</jats:p></jats:sec><jats:sec><jats:title>Objective</jats:title><jats:p>To examine whether a voice-based conversational artificial intelligence (AI) application can help patients with type 2 diabetes titrate basal insulin at home to achieve rapid glycemic control.</jats:p></jats:sec><jats:sec><jats:title>Design, Setting, and Participants</jats:title><jats:p>In this randomized clinical trial conducted at 4 primary care clinics at an academic medical center from March 1, 2021, to December 31, 2022, 32 adults with type 2 diabetes requiring initiation or adjustment of once-daily basal insulin were followed up for 8 weeks. Statistical analysis was performed from January to February 2023.</jats:p></jats:sec><jats:sec><jats:title>Interventions</jats:title><jats:p>Participants were randomized in a 1:1 ratio to receive basal insulin management with a voice-based conversational AI application or standard of care.</jats:p></jats:sec><jats:sec><jats:title>Main Outcomes and Measures</jats:title><jats:p>Primary outcomes were time to optimal insulin dose (number of days needed to achieve glycemic control), insulin adherence, and change in composite survey scores measuring diabetes-related emotional distress and attitudes toward health technology and medication adherence. Secondary outcomes were glycemic control and glycemic improvement. Analysis was performed on an intent-to-treat basis.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>The study population included 32 patients (mean [SD] age, 55.1 [12.7] years; 19 women [59.4%]). Participants in the voice-based conversational AI group more quickly achieved optimal insulin dosing compared with the standard of care group (median, 15 days [IQR, 6-27 days] vs &amp;amp;gt;56 days [IQR, &amp;amp;gt;29.5 to &amp;amp;gt;56 days]; a significant difference in time-to-event curves; <jats:italic>P</jats:italic> = .006) and had better insulin adherence (mean [SD], 82.9% [20.6%] vs 50.2% [43.0%]; difference, 32.7% [95% CI, 8.0%-57.4%]; <jats:italic>P</jats:italic> = .01). Participants in the voice-based conversational AI group were also more likely than those in the standard of care group to achieve glycemic control (13 of 16 [81.3%; 95% CI, 53.7%-95.0%] vs 4 of 16 [25.0%; 95% CI, 8.3%-52.6%]; difference, 56.3% [95% CI, 21.4%-91.1%]; <jats:italic>P</jats:italic> = .005) and glycemic improvement, as measured by change in mean (SD) fasting blood glucose level (−45.9 [45.9] mg/dL [95% CI, −70.4 to −21.5 mg/dL] vs 23.0 [54.7] mg/dL [95% CI, −8.6 to 54.6 mg/dL]; difference, −68.9 mg/dL [95% CI, −107.1 to −30.7 mg/dL]; <jats:italic>P</jats:italic> = .001). There was a significant difference between the voice-based conversational AI group and the standard of care group in change in composite survey scores measuring diabetes-related emotional distress (−1.9 points vs 1.7 points; difference, −3.6 points [95% CI, −6.8 to −0.4 points]; <jats:italic>P</jats:italic> = .03).</jats:p></jats:sec><jats:sec><jats:title>Conclusions and Relevance</jats:title><jats:p>In this randomized clinical trial of a voice-based conversational AI application that provided autonomous basal insulin management for adults with type 2 diabetes, participants in the AI group had significantly improved time to optimal insulin dose, insulin adherence, glycemic control, and diabetes-related emotional distress compared with those in the standard of care group. These findings suggest that voice-based digital health solutions can be useful for medication titration.</jats:p></jats:sec><jats:sec><jats:title>Trial Registration</jats:title><jats:p>ClinicalTrials.gov Identifier: <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" ext-link-type=\"uri\" xlink:href=\"https://classic.clinicaltrials.gov/ct2/show/NCT05081011\">NCT05081011</jats:ext-link></jats:p></jats:sec>","journal":"JAMA Network Open","year":2023,"id":621640,"datarank":0.6573039952010823,"base_score":4.382026634673881,"endowment":4.382026634673881,"self_citation_contribution":0.6573039952010823,"citation_network_contribution":0.0,"self_endowment_contribution":0.6573039952010823,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":79,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":2,"is_dataset":false,"is_dataset_confidence":null,"is_data_producer":false,"deposit_databanks":null,"is_oa":false,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":null,"fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1605407,"name":"Sharif Vakili","orcid":null,"position":1,"is_corresponding":false},{"id":1605409,"name":"Kristen Nayak","orcid":null,"position":2,"is_corresponding":false},{"id":1605411,"name":"Margaret Nikolov","orcid":null,"position":3,"is_corresponding":false},{"id":1337038,"name":"Michelle Chiu","orcid":"0000-0002-7585-2764","position":4,"is_corresponding":false},{"id":1605414,"name":"Philip Sosseinheimer","orcid":null,"position":5,"is_corresponding":false},{"id":1034664,"name":"Sarah Talamantes","orcid":"0000-0002-1296-5016","position":6,"is_corresponding":false},{"id":795282,"name":"Stefano Testa","orcid":"0000-0001-5632-5021","position":7,"is_corresponding":false},{"id":654880,"name":"Srikanth Palanisamy","orcid":"0000-0003-1165-9575","position":8,"is_corresponding":false},{"id":1605420,"name":"Vinay Giri","orcid":null,"position":9,"is_corresponding":false},{"id":1605422,"name":"Kevin Schulman","orcid":null,"position":10,"is_corresponding":false},{"id":1199165,"name":"Ashwin Nayak","orcid":"0009-0003-2024-3683","position":0,"is_corresponding":false}],"reference_count":0,"raw_metadata":{"has_enrichment":true,"resolved":true,"title":"Use of Voice-Based Conversational Artificial Intelligence for Basal Insulin Prescription Management Among Patients With Type 2 Diabetes","abstract":"<jats:sec><jats:title>Importance</jats:title><jats:p>Optimizing insulin therapy for patients with type 2 diabetes can be challenging given the need for frequent dose adjustments. Most patients receive suboptimal doses and do not achieve glycemic control.</jats:p></jats:sec><jats:sec><jats:title>Objective</jats:title><jats:p>To examine whether a voice-based conversational artificial intelligence (AI) application can help patients with type 2 diabetes titrate basal insulin at home to achieve rapid glycemic control.</jats:p></jats:sec><jats:sec><jats:title>Design, Setting, and Participants</jats:title><jats:p>In this randomized clinical trial conducted at 4 primary care clinics at an academic medical center from March 1, 2021, to December 31, 2022, 32 adults with type 2 diabetes requiring initiation or adjustment of once-daily basal insulin were followed up for 8 weeks. Statistical analysis was performed from January to February 2023.</jats:p></jats:sec><jats:sec><jats:title>Interventions</jats:title><jats:p>Participants were randomized in a 1:1 ratio to receive basal insulin management with a voice-based conversational AI application or standard of care.</jats:p></jats:sec><jats:sec><jats:title>Main Outcomes and Measures</jats:title><jats:p>Primary outcomes were time to optimal insulin dose (number of days needed to achieve glycemic control), insulin adherence, and change in composite survey scores measuring diabetes-related emotional distress and attitudes toward health technology and medication adherence. Secondary outcomes were glycemic control and glycemic improvement. Analysis was performed on an intent-to-treat basis.</jats:p></jats:sec><jats:sec><jats:title>Results</jats:title><jats:p>The study population included 32 patients (mean [SD] age, 55.1 [12.7] years; 19 women [59.4%]). Participants in the voice-based conversational AI group more quickly achieved optimal insulin dosing compared with the standard of care group (median, 15 days [IQR, 6-27 days] vs &amp;amp;gt;56 days [IQR, &amp;amp;gt;29.5 to &amp;amp;gt;56 days]; a significant difference in time-to-event curves; <jats:italic>P</jats:italic> = .006) and had better insulin adherence (mean [SD], 82.9% [20.6%] vs 50.2% [43.0%]; difference, 32.7% [95% CI, 8.0%-57.4%]; <jats:italic>P</jats:italic> = .01). Participants in the voice-based conversational AI group were also more likely than those in the standard of care group to achieve glycemic control (13 of 16 [81.3%; 95% CI, 53.7%-95.0%] vs 4 of 16 [25.0%; 95% CI, 8.3%-52.6%]; difference, 56.3% [95% CI, 21.4%-91.1%]; <jats:italic>P</jats:italic> = .005) and glycemic improvement, as measured by change in mean (SD) fasting blood glucose level (−45.9 [45.9] mg/dL [95% CI, −70.4 to −21.5 mg/dL] vs 23.0 [54.7] mg/dL [95% CI, −8.6 to 54.6 mg/dL]; difference, −68.9 mg/dL [95% CI, −107.1 to −30.7 mg/dL]; <jats:italic>P</jats:italic> = .001). There was a significant difference between the voice-based conversational AI group and the standard of care group in change in composite survey scores measuring diabetes-related emotional distress (−1.9 points vs 1.7 points; difference, −3.6 points [95% CI, −6.8 to −0.4 points]; <jats:italic>P</jats:italic> = .03).</jats:p></jats:sec><jats:sec><jats:title>Conclusions and Relevance</jats:title><jats:p>In this randomized clinical trial of a voice-based conversational AI application that provided autonomous basal insulin management for adults with type 2 diabetes, participants in the AI group had significantly improved time to optimal insulin dose, insulin adherence, glycemic control, and diabetes-related emotional distress compared with those in the standard of care group. These findings suggest that voice-based digital health solutions can be useful for medication titration.</jats:p></jats:sec><jats:sec><jats:title>Trial Registration</jats:title><jats:p>ClinicalTrials.gov Identifier: <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" ext-link-type=\"uri\" xlink:href=\"https://classic.clinicaltrials.gov/ct2/show/NCT05081011\">NCT05081011</jats:ext-link></jats:p></jats:sec>","is_dataset_classified":null,"base_score":4.382026634673881,"endowment":4.382026634673881,"datacite_reuse_total":2,"file_count":0,"downloads":0,"views":0,"has_version_chain":false,"is_dataset":false,"is_oa":false,"pmid":"38039007","pmcid":"PMC10692866","openalex_id":"https://openalex.org/W4389244587","authors":[],"funders":[],"total_grants":0,"fwci":11.8513,"citation_percentile":0.99077385,"influential_citations":0,"citation_trend":[{"year":2024,"count":18},{"year":2025,"count":46},{"year":2026,"count":15}],"oa_status":"gold","license":"cc-by","oa_locations":[{"url":"https://jamanetwork.com/journals/jamanetworkopen/articlepdf/2812420/nayak_2023_oi_231171_1700596739.94383.pdf","host_type":"journal"},{"url":"https://jamanetwork.com/journals/jamanetworkopen/articlepdf/2812420/nayak_2023_oi_231171_1700596739.94383.pdf","host_type":"publisher"},{"url":"https://doi.org/10.1001/jamanetworkopen.2023.40232","host_type":"journal"},{"url":"https://pubmed.ncbi.nlm.nih.gov/38039007","host_type":"repository"},{"url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10692866","host_type":"repository"},{"url":"https://europepmc.org/articles/PMC10692866","host_type":"Europe_PMC"}],"fields_of_study":["Diabetes Management and Education","Mobile Health and mHealth Applications","Diabetes Management and Research","Adult","Female","Humans","Middle Aged","Artificial Intelligence","Blood Glucose","Diabetes Mellitus, Type 2","Glycated Hemoglobin","Hypoglycemic Agents","Insulin","Insulin, Regular, Human","Male","Aged"],"mesh_terms":["Adult","Aged","Artificial Intelligence","Blood Glucose","Diabetes Mellitus, Type 2","Female","Glycated Hemoglobin","Humans","Hypoglycemic Agents","Insulin","Male","Middle Aged","Insulin, Regular, Human"],"keywords":["Medical prescription","Basal (medicine)","Basal insulin","Type 2 diabetes","Insulin","Computer science","Diabetes mellitus","Psychology","Medicine","Speech recognition","Communication","Internal medicine","Endocrinology","Nursing"],"sdg_mappings":[{"sdg_number":0,"sdg_label":"Quality Education"}],"linked_datasets":[{"doi":"10.6084/m9.figshare.25459492.v1","title":"Additional file 1 of Interactive virtual assistance for mental health promotion and self-care management in elderly with type 2 diabetes (IVAM-ED): study protocol and statistical analysis plan for a randomized controlled trial","publisher":"figshare","resource_type":"JournalArticle"},{"doi":"10.6084/m9.figshare.25459492","title":"Additional file 1 of Interactive virtual assistance for mental health promotion and self-care management in elderly with type 2 diabetes (IVAM-ED): study protocol and statistical analysis plan for a randomized controlled trial","publisher":"figshare","resource_type":"JournalArticle"}],"clinical_trials":[],"software_tools":[],"database_accessions":[{"name":"nct"}],"source":"live","citation_network_status":"fetched"},"created_at":"2026-08-03T15:23:34.434528Z","pmid":null,"pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}