Predicting optimal treatment regimens for patients with HR+/HER2- breast cancer using machine learning based on electronic health records

Cui, Zhanglin Lin; Kadziola, Zbigniew; Lipkovich, Ilya; Faries, Douglas E.; Sheffield, Kristin M.; Carter, Gebra Cuyún

doi:10.2217/cer-2020-0230

Cited by 5 publications

(4 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An observational study by Cui et al in 2021 investigated CDK4/6i treatment usage in nearly 4000 women diagnosed with HR+/HER2− mBC in the USA between 1 January, 2013 and 31 January, 2019 based on data from the Flatiron Health database. In this study, in the 1L and 2L settings, 42.1% and 40.4% of patients received CDK4/6i-based regimens, respectively [ 32 ]. A retrospective study in Germany of data from the real-world registry PRAEGNANT reported a dramatic increase in CDK4/6i usage over time in the 1L setting for mBC, from 14.1% in 2016 when the first CDK4/6i was approved there in November, to 72.2% in 2022 [ 34 ].…”

Section: Resultsmentioning

confidence: 99%

“…Machine-learning approaches leveraging real-world data could be considered for predicting optimal treatment for individual patients based on demographic and clinical characteristics. A study that applied machine learning algorithms to real-world data found that less than 50% of patients in the cohort received optimal treatment with CDK4/6i in 1L and 2L as predicted by the model [ 32 ]. Studies focusing on or reporting subgroup outcomes in specific patient populations (e.g., high Eastern Cooperative Oncology Group performance status) would also be helpful given the heterogeneity within mBC.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Place in Therapy of Cyclin-Dependent Kinase 4/6 Inhibitors in Breast Cancer: A Targeted Literature Review

et al. 2023

View full text Add to dashboard Cite

Cyclin-dependent kinase 4 and 6 inhibitors (CDK4/6i) are the preferred regimen for patients with hormone receptor-positive and human epidermal growth factor receptor 2-negative (HR+/HER2−) advanced or metastatic breast cancer. However, the optimal treatment sequencing for CDK4/6i with other available therapeutic options is unclear. We conducted a targeted literature review to identify the current evidence on CDK4/6i treatment patterns in patients with breast cancer. The search was initially conducted in October 2021 and subsequently updated in October 2022. Biomedical databases and gray literature were searched, and bibliographies of included reviews were screened for relevant studies. The search identified ten reviews published since 2021 and 87 clinical trials or observational studies published since 2015. The included reviews discussed CDK4/6i usage with or without endocrine therapy (ET) in first-line and second-line treatment for patients with HR+/HER2− advanced or metastatic breast cancer, followed by ET, chemotherapy, or targeted therapy with ET. Clinical studies reported similar treatment sequences consisting of ET, chemotherapy, or targeted therapy with ET prior to CDK4/6i with ET, followed by ET monotherapy, chemotherapy, targeted therapy with ET, or continued CDK4/6i with ET. Current evidence suggests CDK4/6i are effective for HR+/HER2− advanced or metastatic breast cancer in earlier lines of therapy. Efficacy of CDK4/6i as measured by progression-free survival and overall survival was similar within a line of therapy regardless of the type of prior therapy. Survival on different post-CDK4/6i treatments was also similar within the same line of therapy. Additional research is needed to investigate the optimal place in therapy of CDK4/6i and the sequencing of treatments following progression on CDK4/6i. Supplementary Information The online version contains supplementary material available at 10.1007/s11523-023-00957-7.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Place in Therapy of Cyclin-Dependent Kinase 4/6 Inhibitors in Breast Cancer: A Targeted Literature Review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…• Limited patient population and insufficient high-quality data. [ 21,22] Disease progression modeling and digital twins…”

Section: Ai/ml-enabled Pmx Modelingmentioning

confidence: 99%

“…Members were asked to give a high-level overview of AI/ML activities at their respective companies, including how AI/ML was used for internal decision making or regulatory interactions, how AI/ML can improve upon existing methodologies, and the potential challenges for deploying AI/ML more broadly. The results of this survey were shared with the FDA in October of 2021, and are summarized in Table 1, including a list of key references 5,[16][17][18][19][20][21][22][23][24][25][26][27][28] identified by the working group.…”

mentioning

confidence: 99%

Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

Terranova,

Renard,

Shahin

et al. 2023

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Recent breakthroughs in Artificial Intelligence (AI) and Machine Learning (ML) have ushered in a new era of possibilities across various scientific domains. One area where these advancements hold significant promise is model‐informed drug discovery and development (MID3). To foster a wider adoption and acceptance of these advanced algorithms, the Innovation & Quality (IQ) Consortium initiated the AI/ML working group (WG) in 2021 with the aim of promoting their acceptance among the broader scientific community as well as by regulatory agencies. By drawing insights from workshops organized by the WG and attended by key stakeholders across the biopharma industry, academia, and regulatory agencies, this white paper provides a perspective from the IQ Consortium. The range of applications covered in this white paper encompass the following thematic topics: (1) AI/ML‐enabled Analytics for Pharmacometrics & QSP Workflows; (2) Explainable Artificial Intelligence and its Applications in Disease Progression Modeling; (3) Natural Language Processing (NLP) in Quantitative Pharmacology Modeling; (4) AI/ML Utilization in Drug Discovery. Additionally, the paper offers a set of best practices to ensure an effective and responsible use of AI, including considering the context of use, explainability and generalizability of models, and having human‐in‐the‐loop. We believe that embracing the transformative power of AI in quantitative modeling while adopting a set of good practices can unlock new opportunities for innovation, increase efficiency, and ultimately bring benefits to patients.

show abstract

Incorporation of emergent symptoms and genetic covariates improves prediction of aromatase inhibitor therapy discontinuation

Rattsev,

Stearns,

Blackford

et al. 2024

JAMIA Open

View full text Add to dashboard Cite

Objectives Early discontinuation is common among breast cancer patients taking aromatase inhibitors (AIs). Although several predictors have been identified, it is unclear how to simultaneously consider multiple risk factors for an individual. We sought to develop a tool for prediction of AI discontinuation and to explore how predictive value of risk factors changes with time. Materials and Methods Survival machine learning was used to predict time-to-discontinuation of AIs in 181 women who enrolled in a prospective cohort. Models were evaluated via time-dependent area under the curve (AUC), c-index, and integrated Brier score. Feature importance was analysis was conducted via Shapley Additive Explanations (SHAP) and time-dependence of their predictive value was analyzed by time-dependent AUC. Personalized survival curves were constructed for risk communication. Results The best-performing model incorporated genetic risk factors and changes in patient-reported outcomes, achieving mean time-dependent AUC of 0.66, and AUC of 0.72 and 0.67 at 6- and 12-month cutoffs, respectively. The most significant features included variants in ESR1 and emergent symptoms. Predictive value of genetic risk factors was highest in the first year of treatment. Decrease in physical function was the strongest independent predictor at follow-up. Discussion and Conclusion Incorporation of genomic and 3-month follow-up data improved the ability of the models to identify the individuals at risk of AI discontinuation. Genetic risk factors were particularly important for predicting early discontinuers. This study provides insight into the complex nature of AI discontinuation and highlights the importance of incorporating genetic risk factors and emergent symptoms into prediction models.

show abstract

Predicting optimal treatment regimens for patients with HR+/HER2- breast cancer using machine learning based on electronic health records

Cited by 5 publications

References 48 publications

Place in Therapy of Cyclin-Dependent Kinase 4/6 Inhibitors in Breast Cancer: A Targeted Literature Review

Place in Therapy of Cyclin-Dependent Kinase 4/6 Inhibitors in Breast Cancer: A Targeted Literature Review

Artificial Intelligence for Quantitative Modeling in Drug Discovery and Development: An Innovation and Quality Consortium Perspective on Use Cases and Best Practices

Incorporation of emergent symptoms and genetic covariates improves prediction of aromatase inhibitor therapy discontinuation

Contact Info

Product

Resources

About