A novel machine learning-derived decision tree including uPA/PAI-1 for breast cancer care

Machine learning-based clinical decision support using laboratory data

Artificial intelligence (AI) and machine learning (ML) are becoming vital in laboratory medicine and the broader context of healthcare. In this review article, we summarized the development of ML models and how they contribute to clinical laboratory workflow and improve patient outcomes. The process of ML model development involves data collection, data cleansing, feature engineering, model development, and optimization. These models, once finalized, are subjected to thorough performance assessments and validations. Recently, due to the complexity inherent in model development, automated ML tools were also introduced to streamline the process, enabling non-experts to create models. Clinical Decision Support Systems (CDSS) use ML techniques on large datasets to aid healthcare professionals in test result interpretation. They are revolutionizing laboratory medicine, enabling labs to work more efficiently with less human supervision across pre-analytical, analytical, and post-analytical phases. Despite contributions of the ML tools at all analytical phases, their integration presents challenges like potential model uncertainties, black-box algorithms, and deskilling of professionals. Additionally, acquiring diverse datasets is hard, and models' complexity can limit clinical use. In conclusion, ML-based CDSS in healthcare can greatly enhance clinical decision-making. However, successful adoption demands collaboration among professionals and stakeholders, utilizing hybrid intelligence, external validation, and performance assessments.

MMP-11 expression in early luminal breast cancer: associations with clinical, MRI, pathological characteristics, and disease-free survival

BACKGROUND

Early hormone-positive breast cancers typically have favorable outcomes, yet long-term surveillance is crucial due to the risk of late recurrences. While many studies associate MMP-11 expression with poor prognosis in breast cancer, few focus on early-stage cases. This study explores MMP-11 as an early prognostic marker in hormone-positive breast cancers.

METHODS

In this retrospective study, 228 women with early hormone-positive invasive ductal carcinoma, treated surgically between 2011 and 2016, were included. MMP-11 expression was measured by immunohistochemistry, and its association with clinical and MRI data was analyzed.

RESULTS

Among the patients (aged 31-89, median 60, with average tumor size of 15.7 mm), MMP-11 staining was observed in half of the cases. This positivity correlated with higher uPA levels and tumor grade but not with nodal status or size. Furthermore, MMP-11 positivity showed specific associations with MRI features. Over a follow-up period of 6.5 years, only 12 oncological events occurred. Disease-free survival was linked to Ki67 and MMP-11.

CONCLUSION

MMP-11, primarily present in tumor-surrounding stromal cells, correlates with tumor grade and uPA levels. MMP-11 immunohistochemical score demonstrates a suggestive trend in association with disease-free survival, independent of Ki67 and other traditional prognostic factors. This highlights the potential of MMP-11 as a valuable marker in managing early hormone-positive breast cancer.

From free-text electronic health records to structured cohorts: Onconum, an innovative methodology for real-world data mining in breast cancer

PURPOSE

A considerable amount of valuable information is present in electronic health records (EHRs) however it remains inaccessible because it is embedded into unstructured narrative documents that cannot be easily analyzed. We wanted to develop and evaluate a methodology able to extract and structure information from electronic health records in breast cancer.

METHODS

We developed a software platform called Onconum (ClinicalTrials.gov Identifier: NCT02810093) which uses a hybrid method relying on machine learning approaches and rule-based lexical methods. It is based on natural language processing techniques that allows a targeted analysis of free-text medical data related to breast cancer, independently of any pre-existing dictionary, in a French context (available in N files). We then evaluated it on a validation cohort called Senometry.

FINDINGS

Senometry cohort included 9,599 patients with breast cancer (both invasive and in situ), treated between 2000 and 2017 in the breast cancer unit of Strasbourg University Hospitals. Extraction rates ranged from 45 to 100%, depending on the type of each parameter. Precision of extracted information was 68%-94% compared to a structured cohort, and 89%-98% compared to manually structured databases and it retrieved more rare occurrences compared to another database search engine (+17%).

INTERPRETATION

This innovative method can accurately structure relevant medical information embedded in EHRs in the context of breast cancer. Missing data handling is the main limitation of this method however multiple sources can be incorporated to reduce this limit. Nevertheless, this methodology does not need neither pre-existing dictionaries nor manually annotated corpora. It can therefore be easily implemented in non-English-speaking countries and in other diseases outside breast cancer, and it allows prospective inclusion of new patients.

Biomarkers in Breast Cancer: An Old Story with a New End

Breast cancer is the second most frequent cancer in the world. It is a heterogeneous disease and the leading cause of cancer mortality in women. Advances in molecular technologies allowed for the identification of new and more specifics biomarkers for breast cancer diagnosis, prognosis, and risk prediction, enabling personalized treatments, improving therapy, and preventing overtreatment, undertreatment, and incorrect treatment. Several breast cancer biomarkers have been identified and, along with traditional biomarkers, they can assist physicians throughout treatment plan and increase therapy success. Despite the need of more data to improve specificity and determine the real clinical utility of some biomarkers, others are already established and can be used as a guide to make treatment decisions. In this review, we summarize the available traditional, novel, and potential biomarkers while also including gene expression profiles, breast cancer single-cell and polyploid giant cancer cells. We hope to help physicians understand tumor specific characteristics and support decision-making in patient-personalized clinical management, consequently improving treatment outcome.

[uPA/PAI-1 and EPClin®: Comparison of their impact on the management of intermediate-prognosis breast cancers]

OBJECTIVE

The uPA/PAI-1 assay and the EPClin® test are useful tools that add to clinico-anatomical characteristics to determine the indication of adjuvant chemotherapy in case of intermediate-prognosis invasive breast cancer. The principal purpose of our study was to analyze the concordance of uPA/PAI-1 and EPClin® in classification of patients into two groups: low and high risk of relapse.

METHODS

We prospectively included 63 patients treated for intermediate-prognosis invasive breast cancer. All of these patients received a uPA/PAI-1 assay and an EPClin® test.

RESULTS

The uPA/PAI-1 assay and EPClin® test were consistent for 56.2% and inconsistent for 43.8%. In the event of a discrepancy, the treatment decision was based in 95.2% of patients on the EPClin® test result. In total, 38 patients were selected for adjuvant chemotherapy after achievement of the two tests. The mean time to report results after surgery was 9 days for the uPA/PAI-1 assay and 35 days for the EPClin® test. No cases of recurrence or death were found, with an average follow-up of 32 months.

CONCLUSION

The EPClin® test resulted in more chemotherapy prescriptions than indicated by uPA/PAI-1. However, we can't conclude to the superiority of one of these two tests, survival data and the effectiveness of our study being insufficient. In general, studies comparing different signatures useful to the therapeutic decision of intermediate prognosis breast cancers should be encouraged.