Use of Voice-Based Conversational Artificial Intelligence for Basal Insulin Prescription Management Among Patients With Type 2 Diabetes: A Randomized Clinical Trial

Importance

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.

Objective

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.

Design, Setting, and Participants

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.

Interventions

Participants were randomized in a 1:1 ratio to receive basal insulin management with a voice-based conversational AI application or standard of care.

Main Outcomes and Measures

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.

Results

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 >56 days [IQR, >29.5 to >56 days]; a significant difference in time-to-event curves; P = .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%]; P = .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%]; P = .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]; P = .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]; P = .03).

Conclusions and Relevance

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.

Trial Registration

ClinicalTrials.gov Identifier: NCT05081011.

Relationship of circulating immune cells with lifestyle factors and cancer recurrence in early-stage breast cancer

PURPOSE

To evaluate the relationship of circulating immune cells with recurrence and metabolic/lifestyle factors in patients with early-stage breast cancer.

METHODS

Patients with early-stage breast cancer were identified from the electronic record and institutional registry. Lymphocyte and monocyte counts were obtained from blood samples at time of diagnosis prior to any chemotherapy. Correlations between lymphocyte and monocyte and recurrence were assessed in the entire cohort and among obese patients, those reporting alcohol consumption and smoking. Competing risk regression was used to analyze time to recurrence.

RESULTS

A total of 950 patients with ≥ 5 years of follow-up were identified; 433 had complete data and were eligible for analysis. 293 (68%) had hormone receptor-positive breast cancer, 82 (19%) HER2 positive, and 53 (13%) triple negative. Patients in the highest quintile of lymphocytes compared to the lowest quintile had lower risk of recurrence (subhazard ratio (SHR) = 0.17, 95% CI [0.03-0.93], p = 0.041) while patients in the highest quintile of monocytes had lower risk for recurrence (SHR = 0.19, 95% CI [0.04, 0.92], p = 0.039). Higher monocytes were more strongly associated with lower recurrence among those reporting alcohol consumption (HR = 0.10, 95% CI [0.01, 0.91], p = 0.04). In obese patients, higher lymphocytes were associated with lower risk of recurrence (p = 0.046); in non-obese patients, higher monocytes were associated with lower risk of recurrence (p = 0.02). There were no correlations among patients who reported tobacco use.

CONCLUSIONS

High lymphocyte and monocyte counts are associated with lower recurrence rate in early-stage breast cancer, particularly in obese patients and those reporting alcohol consumption.

Circulating immune cell dynamics in patients with triple negative breast cancer treated with neoadjuvant chemotherapy

BACKGROUND

Lymphopenia has been associated with inferior cancer outcomes, but there is limited data in breast cancer. We describe the effects of neoadjuvant chemotherapy on circulating immune cells and its association with pathological complete response (pCR) rates in triple negative breast cancer (TNBC).

METHODS

We constructed a database of patients with early stage TNBC treated with neoadjuvant chemotherapy. Circulating lymphocytes and monocytes were assessed before and after neoadjuvant chemotherapy. These were correlated with pCR rates and disease-free survival (DFS) using Fisher's exact test, logistic regression, and the log-rank test.

RESULTS

From 2000 to 2015, we identified 95 eligible patients. Median age was 50; 29 (31%) were treated with platinum-containing chemotherapy; and 66 (69%) with nonplatinum-containing chemotherapy (anthracycline-taxane, or either alone). About 32 (34%) patients achieved a pCR; and 33 (35%) had recurrence events. Median follow-up time was 47 months. No significant associations were found between changes in lymphocytes and pCR or DFS. There was a correlation between lower monocyte levels after neoadjuvant chemotherapy and pCR (mean monocyte 0.56 in those with no-pCR vs 0.46 in those with pCR, P = .049, multivariate P = .078) and DFS (median DFS in highest monocyte quartile was 30 vs 107 months in lowest quartile, P = .022, multivariate P = .023). In patients who received nonplatinum regimens, DFS was better among those who had larger decreases in monocytes.

CONCLUSIONS

Development of lymphopenia from neoadjuvant chemotherapy was not associated with pCR in patients with TNBC. However, lower absolute circulating monocytes after neoadjuvant chemotherapy was associated with improved outcomes.

Abstract P5-04-16: Association of circulating immune cells with lifestyle factors, and recurrence and mortality in patients with early stage breast cancer

Introduction: Lifestyle factors and metabolic derangements have wide-ranging effects including on immune activity. The association of circulating immune cells and outcomes in patients with early stage breast cancer remain incompletely understood.

Objective: To evaluate the effects of smoking, body mass index (BMI), and alcohol intake on the association between circulating immune cell levels and patient outcomes.

Methods: We retrospectively screened the electronic medical record of 950 patients with early stage breast cancer at the Johns Hopkins Hospital between 2003-2008 with at least 5 years of follow-up data for information on complete blood cell (CBC) counts. Absolute lymphocyte, monocyte, and neutrophil counts were obtained from the CBC differential performed closest to time of diagnosis within a period of ±1 year, and prior to any systemic treatment. Statistical analyses used were t-test for comparison of recurrence vs non-recurrence and Cox proportional hazard models for survival analysis, and linear regression for association between counts and BMI. Covariates adjusted for include grade, stage, smoking status, and alcohol use.

Results: A total of 433 patients with stage 0-III breast cancer had complete data and were included in the analytical population. The populations of analyzed and non-analyzed patients were not significantly different in age or ethnic composition. The median age was 53 years old (range 26-86); 24% (n=103) were African American, and 76% (n=330) were Caucasian. Median BMI at baseline was 27 (range 18-53). Breast cancer subtypes were 68% (n=293) hormone receptor-positive, 19% (n=82) HER2 positive, and 13% (n=53) triple negative. 7.6% (n=33) experienced a recurrence and 6.9% (n=30) died of all causes. Patients with the highest quartile of lymphocytes at diagnosis, compared to the lowest quartile, had a significantly lower risk of recurrence (HR=0.23, 95% CI [0.06, 0.87], p=0.031). Patients with the highest quartile of monocytes were also at a lower risk for recurrence (HR= 0.17, 95% CI [0.11, 0.72] p=0.02). This effect was magnified in subgroup analysis among patients with hormone negative (n=125, p=0.017) and grade 3 (n=155, p=0.02) breast cancer. Patients in the highest quartile of both lymphocytes and monocytes had similarly lower recurrence rates (HR=0.24, 95% CI [0.08, 0.88] p=0.034). In subgroup analysis with regard to lifestyle factors, association of higher monocytes with lower recurrence was most significant among those consuming alcohol (n=237, p=0.005). Subgroup analysis of alcohol use was unremarkable for lymphocytes, as was subgroup analysis of smoking history (n=144) for lymphocytes and monocytes. In patients with BMI>30, lower lymphocytes were more strongly associated with recurrence (n=144, p=0.04); conversely, in patients with BMI<30, lower monocytes were more strongly associated with recurrence (n=289, p=0.02). There was no association between BMI and either monocytes or lymphocytes.

Conclusion: Higher recurrence rates are observed in patients with early stage breast cancer who have low-normal lymphocyte and monocyte counts at time of diagnosis. This association is stronger in subgroups of patient with high BMI and who consume alcohol, known risk factors for breast cancer.

Citation Format: Eric G Xie, Maya M Lapinski, Sarah Talamantes, Kala Visvanathan, Antonio Wolff, Cesar Santa-Maria. Association of circulating immune cells with lifestyle factors, and recurrence and mortality in patients with early stage breast cancer [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P5-04-16.