Dataset Information

Machine learning survival models trained on clinical data to identify high risk patients with hormone responsive HER2 negative breast cancer.

ABSTRACT: For endocrine-positive Her2 negative breast cancer patients at an early stage, the benefit of adding chemotherapy to adjuvant endocrine therapy is not still confirmed. Several genomic tests are available on the market but are very expensive. Therefore, there is the urgent need to explore novel reliable and less expensive prognostic tools in this setting. In this paper, we shown a machine learning survival model to estimate Invasive Disease-Free Events trained on clinical and histological data commonly collected in clinical practice. We collected clinical and cytohistological outcomes of 145 patients referred to Istituto Tumori "Giovanni Paolo II". Three machine learning survival models are compared with the Cox proportional hazards regression according to time-dependent performance metrics evaluated in cross-validation. The c-index at 10 years obtained by random survival forest, gradient boosting, and component-wise gradient boosting is stabled with or without feature selection at approximately 0.68 in average respect to 0.57 obtained to Cox model. Moreover, machine learning survival models have accurately discriminated low- and high-risk patients, and so a large group which can be spared additional chemotherapy to hormone therapy. The preliminary results obtained by including only clinical determinants are encouraging. The integrated use of data already collected in clinical practice for routine diagnostic investigations, if properly analyzed, can reduce time and costs of the genomic tests.

SUBMITTER: Fanizzi A

PROVIDER: S-EPMC10220052 | biostudies-literature | 2023 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Machine learning survival models trained on clinical data to identify high risk patients with hormone responsive HER2 negative breast cancer.

Fanizzi Annarita A Pomarico Domenico D Rizzo Alessandro A Bove Samantha S Comes Maria Colomba MC Didonna Vittorio V Giotta Francesco F La Forgia Daniele D Latorre Agnese A Pastena Maria Irene MI Petruzzellis Nicole N Rinaldi Lucia L Tamborra Pasquale P Zito Alfredo A Lorusso Vito V Massafra Raffaella R

Scientific reports 20230526 1

For endocrine-positive Her2 negative breast cancer patients at an early stage, the benefit of adding chemotherapy to adjuvant endocrine therapy is not still confirmed. Several genomic tests are available on the market but are very expensive. Therefore, there is the urgent need to explore novel reliable and less expensive prognostic tools in this setting. In this paper, we shown a machine learning survival model to estimate Invasive Disease-Free Events trained on clinical and histological data co ...[more]

PMID: 37237020

Similar Datasets

Project description:Objectives.People with refractory epilepsy are overwhelmed by the uncertainty of their next seizures. Accurate prediction of future seizures could greatly improve the quality of life for these patients. New evidence suggests that seizure occurrences can have cyclical patterns for some patients. Even though these cyclicalities are not intuitive, they can be identified by machine learning (ML), to identify patients with predictable vs unpredictable seizure patterns.Approach.Self-reported seizure logs of 153 patients from the Human Epilepsy Project with more than three reported seizures (totaling 8337 seizures) were used to obtain inter-seizure interval time-series for training and evaluation of the forecasting models. Two classes of prediction methods were studied: (1) statistical approaches using Bayesian fusion of population-wise and individual-wise seizure patterns; and (2) ML-based algorithms including least squares, least absolute shrinkage and selection operator, support vector machine (SVM) regression, and long short-term memory regression. Leave-one-person-out cross-validation was used for training and evaluation, by training on seizure diaries of all except one subject and testing on the left-out subject.Main results.The leading forecasting models were the SVM regression and a statistical model that combined the median of population-wise seizure time-intervals with a test subject's prior seizure intervals. SVM was able to forecast 50%, 70%, 81%, 84%, and 87% of seizures of unseen subjects within 0, 1, 2, 3 to 4 d of mean absolute forecasting error, respectively. The subject-wise performances show that patients with more frequent seizures were generally better predicted.Significance.ML models can leverage non-random patterns within self-reported seizure diaries to forecast future seizures. While diary-based seizure forecasting alone is only one of many aspects of clinical care of patients with epilepsy, studying the level of predictability across seizures and patients paves the path towards a better understanding of predictable vs unpredictable seizures on individualized and population-wise bases.

Project description:We reviewed randomized phase II/III trials comparing first- or second-line endocrine therapy as monotherapy or in combination with targeted therapies for treatment of postmenopausal patients with hormone receptor-positive advanced breast cancer. First-line was defined as treatment for endocrine therapy-naïve advanced breast cancer or advanced disease treated with endocrine therapy in the adjuvant/neoadjuvant setting. Second-line was defined as endocrine therapy for advanced breast cancer following disease progression on endocrine therapy for advanced disease. Publications reporting progression-free survival (PFS)/time to progression (TTP) or overall survival (OS) for FDA-approved agents anastrozole, exemestane, fulvestrant 250 mg, fulvestrant 500 mg, letrozole (0.5 and 2.5 mg), megestrol acetate, and tamoxifen as monotherapy, or in combination with everolimus, palbociclib or ribociclib, were assessed. First-line monotherapy with anastrozole, fulvestrant 500 mg or letrozole 2.5 mg significantly improved PFS/TTP versus comparator endocrine therapy; however, only fulvestrant 500 mg improved OS. For endocrine therapy in combination with targeted therapies, palbociclib plus letrozole 2.5 mg, and ribociclib plus letrozole 2.5 mg significantly improved PFS versus letrozole 2.5 mg alone first-line. For second-line monotherapies, exemestane, fulvestrant 500 mg and letrozole 2.5 mg significantly improved PFS/TTP versus comparator endocrine therapy; only fulvestrant 500 mg and letrozole 2.5 mg improved OS. For second-line combination therapies, everolimus plus exemestane, and palbociclib plus fulvestrant 500 mg, improved PFS versus endocrine therapy alone. In both first- and second-line settings, aromatase inhibitors demonstrated PFS benefits versus comparator endocrine therapy; however, fulvestrant 500 mg was the only endocrine therapy included in our review to show both PFS and OS advantages compared with other endocrine therapies. Targeted agents in combination with endocrine therapy have demonstrated PFS improvements both first- and second-line; OS data are awaited.

Dataset Information

Machine learning survival models trained on clinical data to identify high risk patients with hormone responsive HER2 negative breast cancer.

Publications

Machine learning survival models trained on clinical data to identify high risk patients with hormone responsive HER2 negative breast cancer.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets