RESUMO
Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation.
RESUMO
BACKGROUND: Evidence-based timeliness benchmarks have been established to assess quality of breast cancer care, as delays in treatment are associated with poor clinical outcomes. However, few studies have evaluated how current breast cancer care meets these benchmarks and what factors may delay the timely initiation of treatment. PATIENTS AND METHODS: Demographic and disease characteristics of 377 newly diagnosed patients with breast cancer who initiated treatment at Tufts Medical Center (2009-2015) were extracted from electronic medical records. Time from diagnosis to initial surgery and time from diagnosis to initiation of hormone therapy were estimated with Kaplan-Meier curves. Multivariable regression analysis was used to identify factors associated with treatment delays. Thematic analysis was performed to categorize reasons for delay. RESULTS: Of 319 patients who had surgery recommended as the first treatment, 248 (78%) met the 45-day benchmark (median, 28 days; 25th-75th %, 19-43). After adjusting for potential confounders, multivariable regression analysis revealed that negative hormone receptor status (odds ratio, 3.48; 95% confidence interval, 1.44-8.43) and mastectomy (odds ratio, 4.07; 95% confidence interval, 2.10-8.06) were significantly associated with delays in surgery. Delays were mostly owing to clinical complexity or logistical/financial reasons. Of 241 patients eligible for hormone therapy initiation, 232 (96%) met the 1-year benchmark (median, 147 days; 25th-75th %, 79-217). CONCLUSION: Most patients met timeliness guidelines for surgery and initiation of hormone therapy, although risk factors for delay were identified. Knowledge of reasons for breast cancer treatment delay, including clinical complexity and logistical/financial issues, may allow targeting interventions for patients at greatest risk of care delays.