Adu, Yaw

e13661 Background: MM survival has improved significantly, resulting in increased survivorship and caregiver burden and is crucial to understand the real-world impact of MM. We analyzed results from a large, prospective MM patient survey using ML models to identify key predictive factors for survivorship and caregiver burden. Methods: A 45-item questionnaire spanning sociodemographics, treatment preferences, symptom burden and caregiver impact was distributed to MM patients at Mayo Clinic and International Myeloma Foundation support groups. Questions about quality of life (QOL) and treatment satisfaction (TS) represented survivorship outcomes while caregiver workday loss (WL) and job loss (JL) were surrogates for caregiver burden. 6 ML models (multinomial, random forest (RF), XGB (XGBoost), k-NN, GBM, Naïve Bayes) with a training: testing cohort of 80:20 were used to predict each of the 4 outcomes independently, considering model accuracy, C-index, precision, recall, and F1 score (Table), and using R studio (V4.4.1) and Bluesky Statistics (V10.3.4). Results: 2,239 participants (54% male, 89% Whites) with median age 68 yrs completed the survey. 71% respondents had a college degree, 44% resided in Midwest states, 62% reported household income >$75,000, and 67% had Medicare/Medicaid. Median age at MM diagnosis was 67 yrs with 58% diagnosed within the past 5 yrs and 73% currently receiving MM treatment. 72% reported their spouse as the primary caregiver. XGB was the best predictive model for QOL with gender, household income, stem cell transplant, CAR-T therapy, support from medical staff, and symptom burden (pain, neuropathy, mental well-being) as significant predictors. The RF model was the best for TS with pain and neuropathy levels as the most impactful predictors. For caregiver burden, XGB was the best model for WL with gender, household income, CAR-T therapy, financial strain, lack of support from medical staff, self-workdays missed, self-job loss, and pain and neuropathy levels as significant predictors. For JL, RF was the best model with significant variables being workdays missed by self, increased healthcare needs, symptom burden (pain, neuropathy, and mental well-being), and restricted physical activity. Conclusions: Our study shows the significant impact of MM survivorship and efficiently identifies predictive factors associated with survivorship and caregiver burden from a large prospective dataset using validated ML models. These findings highlight the complex challenges from MM and provide contemporary ML methods to better understand their interplay such that a framework of real-world interventions can be developed. Outcome Best ML Model Accuracy C-Index Precision Recall F1 score QOL XG 0.996 0.996 0.996 0.997 0.996 TS RF 0.984 0.900 0.937 0.948 0.937 WL XGB 0.984 1.000 0.944 0.947 0.945 JL RF 0.989 0.800 0.829 0.848 0.835

Introduction: Therapeutic advancements for MM have led to improved patient survival, but notable differences in management exist. Novel treatment options are resource-intensive and require adequate patient awareness as well as consideration of patient preferences such that informed decision making is practiced. Despite this, detailed understanding of factors that impact patient decisions regarding healthcare choices, and potentially contribute to variability in healthcare utilization, are under-studied. Additionally, with improved survivorship, the medical, psychosocial, and financial burden of MM management needs to be better understood. Methods: An anonymous, online, 45-question English survey exploring demographics, social determinants of health, selected clinical characteristics, treatment preferences, and survivorship burden was distributed to MM patients within Mayo Clinic and to all International Myeloma Foundation (IMF) support groups. Descriptive statistics were utilized to document participant socio-demographic characteristics, selected treatment history, factors affecting their preferences, and MM survivorship burden. Results: A total of 2239 participants responded to the survey with 54% males, median age 68 years (range 21-95) and median age at MM diagnosis of 67 years. Non-Hispanic Whites (NHW) were the largest (89%) racial-ethnic group. Most participants (71%) had a college degree and 67% had Medicare or Medicaid as primary insurance. MM was diagnosed within 5 years in 58% and 73% were currently on MM treatment at the time of responding to the survey. Majority (76%) had never been on a clinical trial, 59% had received stem cell transplant, 8% had undergone CAR-T therapy and 8% had received Bispecific antibodies as part of their MM management. Majority (64%) preferred oral drugs while 19% preferred injections and 14% infusion therapy.17% had ≥4 healthcare visits per month for MM treatment, 91% used their personal vehicle as the mode of transport for these appointments and the median time to travel to the treatment facility was 30-minutes.Survey participants reported that >10 days of work were missed per year due to MM management among 15% of the patients and 9% of the caregivers, while 15% reported suffering job loss related to MM management. Top factors for treatment decisions were physician recommendations (92%), effectiveness of treatment option (88%), understanding of the treatment(74%), side effects (57%), and family/caregiver input (38%). Psychological challenges and financial strain were reported by 38% and 18% of the respondents, respectively. Increase in healthcare needs since MM diagnosis were reported by 48% and majority reported ongoing symptom burden including fatigue (78%), pain (53%) and neuropathy (60%). Furthermore, of the participants with these symptoms, 67% reported that their fatigue was not relieved by rest, 73% reported their pain to be moderate to severe, and 29% reported their neuropathy to be moderate to severe. Only 42% reported being fully active with the rest reporting varying degrees of functional inabilities. Nearly half (47%) of the participants reported lack of interest or enjoyment in activities they used to like prior to MM diagnosis, however majority (74%) still reported “good” or “excellent” quality of life. A small number of participants reported lack of support from family and friends (4%), lack of support from their healthcare team (3%), difficulty accessing healthcare due to financial hardship (7%) or difficulty accessing healthcare due to job commitments (3%). Conclusions: Decision-making for MM treatment is complex and there are several factors that affect patients behavior. Improved survival in MM is associated with significant survivorship and caregiver burden which can also affect the patient's treatment choices for subsequent therapy. These factors must be addressed systematically to achieve equitable healthcare utilization, shared decision making, and optimal clinical, psychosocial and financial wellbeing of patients with MM.

Abstract Multiple myeloma (MM) therapeutics have evolved tremendously in recent years, with significant improvement in patient outcomes. As newer treatment options are developed, stem cell transplant (SCT) remains an important modality that provides excellent disease control and delays the progression of disease. Over the years, SCT use has increased overall in the U.S., but two distinct gaps remain, including suboptimal use overall, and racial-ethnic disparities. We evaluated the National Cancer Database (NCDB) to study what sociodemographic factors might play a role within a given racial-ethnic group leading to disparate SCT utilization, such that targeted approaches can be developed to optimize SCT use for all. In nearly 112,000 cases belonging to mutually exclusive categories of non-Hispanic Whites (NHW), non-Hispanic Blacks (NHB), Hispanics, non-Hispanic Asians (NHA), and others, we found certain factors including age, comorbidity index, payor type, facility type (academic vs. community) and facility volume to be uniformly associated with SCT use for all the racial-ethnic groups, while gender was not significant for any of the groups. There were several other factors which had a differential impact on SCT utilization among the various race-ethnicity groups studied, including year of diagnosis (significant for NHW, NHB and Hispanics), income level (significant for NHW and Hispanics), literacy level (significant for NHW and NHB), and geographic location of the treatment facility (significant for NHW and NHA). The suboptimal SCT utilization overall in the U.S., suggests that there may be room for improvement for all, even including the majority NHW, while we continue to work on factors that lead to disparities for the traditionally underserved populations. This study helps identify sociodemographic factors that may play a role specifically in each group and paves the way to devise targeted solutions such that resource utilization and impact can be maximized.

Introduction: Treatment options for multiple myeloma (MM) are evolving rapidly with recent introduction of BCMA-targeting CAR-T (Ide-cel, Cilta-cel) and bispecific antibody (Bi-Ab; Teclistamab) alternatives. These are complex, logistically demanding therapies, and patient awareness/knowledge can affect treatment decisions. There are traditionally underserved patients in MM, and awareness among them must be investigated to uncover disparities which may impact their access to and choice of novel therapies, contributing to disparate outcome. Methods: The study involved an anonymous 25-question online English language survey covering basic demographics, understanding of available T-cell directed MM treatments (CAR-T, Bi-Ab), and preferences for these agents. MM patients within the Mayo Clinic database and members of International Myeloma Foundation's MM support groups were sent a link to the voluntary survey. The survey was active from March 30 until July 12, 2023. Descriptive statistics were calculated with R language (Bluesky Statistics, V7.40), and categorical variables among outcome demographic groups were compared using Pearson Chi-square test (p-value ≤0.05 considered statistically significant). Multiple model logistic regression was used for multivariate analysis amongst statistically significant outcomes. Results: The survey had 2370 respondents with median age 68 years (range: 30-95) and median age at MM diagnosis 62 years (range: 18-88). Time since diagnosis was <5 years in 59.5%. Majority of the respondents (89.4%) were non-Hispanic Whites (NHW). Maximum education categories were high school (10.9%), some college but no degree (18.1%), associate/bachelor (39.7%), and master's/professional (32.3%). Geography and type of residence were reported as: West (24%), Midwest (46.2%), Northeast (3.3%), South (24.8%), outside U.S. (1.7%), and rural (26.7%), urban (21.4%), suburban (51.9%). The goals of MM treatment in order of reported importance were complete remission (66.1%), longer survival (55.3%) and low symptom burden (43.3%). Only 6.5% and 2.6% of respondents had received CAR-T and Bi-Ab, respectively, while 27.9% and 70.5% had never heard of CAR-T and Bi-Ab, respectively. A high proportion of respondents did not understand the risks/benefits of CAR-T (65.5%) or Bi-Ab (90.7%). Given a preference among CAR-T products, 5.4% would prefer Cilta-cel, 1.9% Ide-cel and 92.7% were not sure/no preference. Amongst only those who reported understanding the risks/benefits of CAR-T, the majority (73%) said they would prefer Cilta-cel. The majority (87.5%) were not sure of any differences between the two CAR-T products while some reported different targets (6.3%), response rate (5.9%), response duration (6.2%), side effects (4.9%), and manufacturing time (2.7%). The biggest concern for both CAR-T and Bi-Ab was side effects. Majority (89.4%) were not sure that Teclistamab Bi-Ab targeted BCMA, and nearly 70% felt that CAR-T was superior to Bi-Ab for treating MM. Reported sources of knowledge about MM treatment were healthcare team (82.6%), online resources (43.6%) and other patients/support groups (37.9%). Several demographic characteristics that significantly affected patient's responses to different questions in the survey. Selected questions and respondent categories with statistically significant results in multivariate analysis are shown in Table 1. Generally, higher education, living in northeast U.S., urban or suburban residency, and >5 years since MM diagnosis were associated with better awareness/understanding of CAR-T and Bi-Ab. Respondents with >70-year age were less likely to be aware of these agents or understand their risks/benefits. Race-ethnicity had no statistically significant associations in this cohort of predominantly NHW. Conclusions: This large cross-sectional study identifies lack of adequate awareness regarding CAR-T and Bi-Ab and provides a glimpse of current understanding of these complex therapies. There are disparate groups including rural, less educated, elderly and those with recent diagnosis of MM who have significantly lesser awareness. Some better-informed respondents had preferences among these treatments. Targeted awareness campaigns should be developed so that knowledge gaps can be bridged and patients across all sociodemographic groups are better equipped to take informed decisions about MM treatment.