RADI-22. CHARACTERIZING CLINICAL SURVIVAL PATTERNS USING MACHINE LEARNING: AN ANALYSIS OF BRAIN METASTASIS PATIENTS TREATED WITH STEREOTACTIC RADIOSURGERY

Abstract INTRODUCTION: Increased sophistication in machine-learning algorithms and artificial intelligence have begun to unveil patterns that would be otherwise unappreciated in clinical medicine. Here we applied one such algorithm, Iterative Factorial Analysis of Mixed Data (IFAMD), to better understanding combinations of clinical variables that influence clinical survival of brain metastasis (BM) patients treated with stereotactic radiosurgery (SRS). METHODS: A dataset of 6,326 BM patients was collated from four SRS centers (University of California, San Diego, Katsuta Hospital Mito GammaHouse, Tsukiji Neurological Clinic, and Melanoma Institute of Australia). IFAMD was applied to the analysis of the following clinical variables: age, Karnofsky Performance Status (KPS), cumulative intracranial tumor volume (CITV), total number of metastases, histology (breast, gastrointestinal (GI) cancer, renal cell carcinoma (RCC), melanoma, and lung cancer), systemic disease control, and survival in months. RESULTS: Our machine learning algorithm defined three groups of patients who exhibited differential survival. The group who is most likely to die within 3 months of SRS included patients with lower KPS, poor systemic disease control, higher CITV, higher number of metastasis, and who carried a diagnosis of GI cancer. Patients who are most likely to survive beyond twelve months of SRS fall into two distinct categories. The first consisted of subsets of lung and breast cancer patients with higher KPS, controlled systemic disease, and lower CITV. The second consisted of young breast cancer patients with systemic disease control, independent of KPS, CITV, and the number of metastases. CONCLUSION: Clinical survival after SRS for BM is defined by combinations of known prognostic factors. A prognostic factor critical for survival prognosis in one sub-population of BM patients may bear little relevance in another patient sub-population.

Download Full-text

Optimizing Intracranial Disease Control for Breast Cancer Patients with HER2 Positive Brain Metastasis: Combining SRS and CNS-Penetrating HER2 Blockade Therapy

International Journal of Radiation Oncology*Biology*Physics ◽

10.1016/j.ijrobp.2017.06.433 ◽

2017 ◽

Vol 99 (2) ◽

pp. S171-S172

Author(s):

S. Parsai ◽

J.A. Miller ◽

A. Juloori ◽

S.T. Chao ◽

A.M. Mohammadi ◽

...

Keyword(s):

Breast Cancer ◽

Brain Metastasis ◽

Disease Control ◽

Cancer Patients ◽

Breast Cancer Patients ◽

Her2 Positive ◽

Intracranial Disease

Download Full-text

The incidence and impact of brain metastasis in patients with hereditary BRCA1/2 mutated invasive breast cancer in a prospectively followed cohort.

Journal of Clinical Oncology ◽

10.1200/jco.2020.38.15_suppl.1096 ◽

2020 ◽

Vol 38 (15_suppl) ◽

pp. 1096-1096

Author(s):

Haven Garber ◽

Michael Lehner ◽

Akshara Singareeka Raghavendra ◽

Angelica M. Gutierrez-Barrera ◽

Debu Tripathy ◽

...

Keyword(s):

Breast Cancer ◽

Brain Metastasis ◽

Cancer Patients ◽

Recurrent Disease ◽

Systemic Disease ◽

Metastatic Breast ◽

Disease Recurrence ◽

Stage I ◽

Breast Cancer Patients ◽

Brca1 Mutations

1096 Background: Previous reports suggest the incidence of brain metastasis is higher in patients with hereditary BRCA1 mutations compared to BRCA1 noncarriers among breast cancer patients who develop recurrent disease. PARP inhibitors are now standard therapies for metastatic breast cancer patients with germline BRCA1 or BRCA2 mutations ( gBRCA1/2) based on their efficacy in treating systemic disease. However, as management of systemic disease improves, a concern is that patients with hereditary BRCA mutations may experience higher rates of disease progression in the CNS. We aimed to estimate the incidence of brain metastasis in breast cancer patients with gBRCA1/2 using a prospectively maintained gBRCA database and to assess the impact of brain metastasis on survival. Methods: To determine incidence, we queried a prospectively maintained electronic database that included patients referred to the MDACC genetics department and who underwent gBRCA1/2 testing. We identified patients with stage I-III invasive breast cancer who were treated between 2000-2017 and assessed for disease recurrence and brain metastasis. To expand our cohort for descriptive characteristics (separate from the incidence analysis), we queried the Breast Medical Oncology database for patients with brain metastasis who had undergone BRCA1/2 testing outside the genetics department or at outside institutions. Results: Of 474 patients with Stage I-III breast cancer and gBRCA1, 77 (16.2%) developed distant metastasis (median f/u: 9.1 years). Of these patients, 34/77 (44.2%) developed brain metastasis. In comparison, 42 of 318 (13.2%) of gBRCA2 patients with Stage I-III breast cancer developed distant recurrence (median f/u: 8.4 years), and 7/42 (16.7%) experienced brain metastasis. In gBRCA1 patients with brain metastasis, 45/48 (83.8%) had triple negative disease, and the median time from diagnosis to brain metastasis was 2.45 years. The brain was among the initial sites of disease recurrence in 24/48 (50%) of gBRCA1 patients. For gBRCA1 patients with distantly recurrent disease, median OS from diagnosis was 3.19 years for patients with brain metastasis vs. 5.37 years for patients without brain mets (HR 0.54; 95% CI 0.34 to 0.85; P = 0.0082). Conclusions: Brain metastasis is frequent among breast cancer patients with recurrent disease and hereditary BRCA1 mutations. Development and testing of agents with intracranial activity is critical for improving long-term outcomes in gBRCA1 patients with metastatic breast cancer.

Download Full-text

Applying a Machine Learning Approach to Predict Acute Toxicities During Radiation for Breast Cancer Patients

International Journal of Radiation Oncology*Biology*Physics ◽

10.1016/j.ijrobp.2018.06.167 ◽

2018 ◽

Vol 102 (3) ◽

pp. S59

Author(s):

J. Reddy ◽

W.D. Lindsay ◽

C.G. Berlind ◽

C.A. Ahern ◽

B.D. Smith

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Cancer Patients ◽

Learning Approach ◽

Breast Cancer Patients ◽

Machine Learning Approach

Download Full-text

A machine learning approach to predict healthcare cost of breast cancer patients

Scientific Reports ◽

10.1038/s41598-021-91580-x ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Pratyusha Rakshit ◽

Onintze Zaballa ◽

Aritz Pérez ◽

Elisa Gómez-Inhiesto ◽

Maria T. Acaiturri-Ayesta ◽

...

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Cancer Patients ◽

Healthcare Cost ◽

Percentage Error ◽

Learning Approach ◽

Early Prediction ◽

Breast Cancer Patients ◽

Machine Learning Approach ◽

Clinical Records

AbstractThis paper presents a novel machine learning approach to perform an early prediction of the healthcare cost of breast cancer patients. The learning phase of our prediction method considers the following two steps: (1) in the first step, the patients are clustered taking into account the sequences of actions undergoing similar clinical activities and ensuring similar healthcare costs, and (2) a Markov chain is then learned for each group to describe the action-sequences of the patients in the cluster. A two step procedure is undertaken in the prediction phase: (1) first, the healthcare cost of a new patient’s treatment is estimated based on the average healthcare cost of its k-nearest neighbors in each group, and (2) finally, an aggregate measure of the healthcare cost estimated by each group is used as the final predicted cost. Experiments undertaken reveal a mean absolute percentage error as small as 6%, even when half of the clinical records of a patient is available, substantiating the early prediction capability of the proposed method. Comparative analysis substantiates the superiority of the proposed algorithm over the state-of-the-art techniques.

Download Full-text