Machine-Learning-Aided Prediction of Brain Metastases Development in Non-Small-Cell Lung Cancers

Elucidating the Role of EGFRL858R in Brain Metastasis Among Patients With Advanced NSCLC Undergoing TKI Therapy

INTRODUCTION

Brain metastases (BM) are a prevalent and severe complication of non-small cell lung cancer (NSCLC) that significantly affects quality of life. Although several predictive factors for BM have been identified, the influence of EGFR mutation subtypes remains under-explored.

METHODS

We retrospectively examined patients with advanced NSCLC and EGFR mutations treated with first-line EGFR-TKIs. Our primary endpoint was intracranial progression-free survival (icPFS), defined as the time from the initiation of upfront treatment to the development of BM, the progression of existing brain lesions, or death. Additionally, we evaluated intracranial objective response rates (icORR) and disease control rates (icDCR) for patients with baseline BM. Subgroup and multivariate analyses were performed to adjust for relevant factors.

RESULTS

Of the 324 patients analyzed, 40.7% had baseline BM. Overall, the EGFRL858R mutation was linked to a significantly shorter median icPFS of 13.9 months, compared to 23.4 months for those with EGFRΔ19 (HR 1.60, P < .0001) For patients without baseline BM, icPFS was 14.3 months for EGFRL858R versus 26.2 months (HR 1.65, P = .007), while with baseline BM, it was 13.9 versus 18.5 months (HR 1.59, P = .035); icORR was lower for EGFRL858R (31.2% vs. 58.8%). Multivariate analysis showed EGFRL858R was independently linked to worse icPFS in patients with (HR 1.634, P = .031) and without BM (HR 1.606, P = .008), and lower icORR (OR 3.511, P = .007) and icDCR (OR 4.443, P = .006).

CONCLUSIONS

EGFRL858R mutation significantly impacts BM development, intracranial progression, and response, emphasizing its critical role in therapy selection.

Evolving treatments and prognosis in Stage IV non-small cell lung cancer: 20 years of progress of novel therapies

BACKGROUND

Advancements in pharmacotherapy, including molecular targeted therapies and immune checkpoint inhibitors, have revolutionized the treatment for Stage IV non-small cell lung cancer (NSCLC) over the past two decades. However, differences in drug approval timelines across countries raise important questions about their impact on survival rates. This study investigates trends in overall survival (OS), patient characteristics, and the association between OS improvements and the introduction of new drugs.

PATIENTS AND METHODS

This retrospective review included patients with Stage IV NSCLC treated at the National Cancer Center Hospital in Japan from 2001 to 2021. Using data from the Department of Thoracic Oncology registries, 2,555 patients were identified and categorized into four time periods: 2001-2005 (Group A), 2006-2010 (Group B), 2011-2015 (Group C), and 2016-2021 (Group D).

RESULTS

While baseline characteristics remained relatively consistent, Group D had an increased proportion of elderly patients (≥ 75 years) and those with brain metastases. Additionally, the gender ratio became more balanced over time. Notably, Group D patients with EGFR mutations or ALK fusion positivity and older age demonstrated significantly longer OS. Analysis revealed steady and substantial improvements in OS across time periods (median OS: Group A, 10.68 months; Group B, 14.12 months; Group C, 16.49 months; and Group D, 25.46 months, respectively).

CONCLUSIONS

This study demonstrates marked improvements in survival for patients with Stage IV NSCLC, particularly in the last six years, despite the increase in brain metastases and elderly patients. This finding suggests the crucial role of novel therapies in enhancing survival outcomes.

Explainable Machine Learning Models for Brain Diseases: Insights from a Systematic Review

In recent years, Artificial Intelligence (AI) methods, specifically Machine Learning (ML) models, have been providing outstanding results in different areas of knowledge, with the health area being one of its most impactful fields of application. However, to be applied reliably, these models must provide users with clear, simple, and transparent explanations about the medical decision-making process. This systematic review aims to investigate the use and application of explainability in ML models used in brain disease studies. A systematic search was conducted in three major bibliographic databases, Web of Science, Scopus, and PubMed, from January 2014 to December 2023. A total of 133 relevant studies were identified and analyzed out of a total of 682 found in the initial search, in which the explainability of ML models in the medical context was studied, identifying 11 ML models and 12 explainability techniques applied in the study of 20 brain diseases.

Length-scale study in deep learning prediction for non-small cell lung cancer brain metastasis

Deep learning-assisted digital pathology has demonstrated the potential to profoundly impact clinical practice, even surpassing human pathologists in performance. However, as deep neural network (DNN) architectures grow in size and complexity, their explainability decreases, posing challenges in interpreting pathology features for broader clinical insights into physiological diseases. To better assess the interpretability of digital microscopic images and guide future microscopic system design, we developed a novel method to study the predictive feature length-scale that underpins a DNN's predictive power. We applied this method to analyze a DNN's capability in predicting brain metastasis from early-stage non-small-cell lung cancer biopsy slides. This study quantifies DNN's attention for brain metastasis prediction, targeting features at both the cellular scale and tissue scale in H&E-stained histological whole slide images. At the cellular scale, the predictive power of DNNs progressively increases with higher resolution and significantly decreases when the resolvable feature length exceeds 5 microns. Additionally, DNN uses more macro-scale features associated with tissue architecture and is optimized when assessing visual fields greater than 41 microns. Our study computes the length-scale requirements for optimal DNN learning on digital whole-slide microscopic images, holding the promise to guide future optical microscope designs in pathology applications and facilitating downstream deep learning analysis.

AI-guided histopathology predicts brain metastasis in lung cancer patients

Brain metastases can occur in nearly half of patients with early and locally advanced (stage I-III) non-small cell lung cancer (NSCLC). There are no reliable histopathologic or molecular means to identify those who are likely to develop brain metastases. We sought to determine if deep learning (DL) could be applied to routine H&E-stained primary tumor tissue sections from stage I-III NSCLC patients to predict the development of brain metastasis. Diagnostic slides from 158 patients with stage I-III NSCLC followed for at least 5 years for the development of brain metastases (Met+, 65 patients) versus no progression (Met-, 93 patients) were subjected to whole-slide imaging. Three separate iterations were performed by first selecting 118 cases (45 Met+, 73 Met-) to train and validate the DL algorithm, while 40 separate cases (20 Met+, 20 Met-) were used as the test set. The DL algorithm results were compared to a blinded review by four expert pathologists. The DL-based algorithm was able to distinguish the eventual development of brain metastases with an accuracy of 87% (p < 0.0001) compared with an average of 57.3% by the four pathologists and appears to be particularly useful in predicting brain metastases in stage I patients. The DL algorithm appears to focus on a complex set of histologic features. DL-based algorithms using routine H&E-stained slides may identify patients who are likely to develop brain metastases from those who will remain disease free over extended (>5 year) follow-up and may thus be spared systemic therapy. © 2024 The Authors. The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.