Lung cancer survival prediction and biomarker identification with an ensemble machine learning analysis of tumor core biopsy metabolomic data

A Thorough Review of the Clinical Applications of Artificial Intelligence in Lung Cancer

According to data from the World Health Organization (WHO), lung cancer is becoming a global epidemic. It is particularly high in the list of the leading causes of death not only in developed countries, but also worldwide; furthermore, it holds the leading place in terms of cancer-related mortality. Nevertheless, many breakthroughs have been made the last two decades regarding its management, with one of the most prominent being the implementation of artificial intelligence (AI) in various aspects of disease management. We included 473 papers in this thorough review, most of which have been published during the last 5-10 years, in order to describe these breakthroughs. In screening programs, AI is capable of not only detecting suspicious lung nodules in different imaging modalities-such as chest X-rays, computed tomography (CT), and positron emission tomography (PET) scans-but also discriminating between benign and malignant nodules as well, with success rates comparable to or even better than those of experienced radiologists. Furthermore, AI seems to be able to recognize biomarkers that appear in patients who may develop lung cancer, even years before this event. Moreover, it can also assist pathologists and cytologists in recognizing the type of lung tumor, as well as specific histologic or genetic markers that play a key role in treating the disease. Finally, in the treatment field, AI can guide in the development of personalized options for lung cancer patients, possibly improving their prognosis.

Biomedical data analytics for better patient outcomes

Medical professionals today have access to immense amounts of data, which enables them to make decisions that enhance patient care and treatment efficacy. This innovative strategy can improve global health care by bridging the divide between clinical practice and medical research. This paper reviews biomedical developments aimed at improving patient outcomes by addressing three main questions regarding techniques, data sources and challenges. The review includes peer-reviewed articles from 2018 to 2023, found via systematic searches in PubMed, Scopus and Google Scholar. The results show diverse disease-specific applications. Challenges such as data quality and ethics are discussed, underscoring data analytics' potential for patient-focused health care. The review concludes that successful implementation requires addressing gaps, collaboration and innovation in biomedical science and data analytics.

Enhanced Lung Cancer Survival Prediction Using Semi-Supervised Pseudo-Labeling and Learning from Diverse PET/CT Datasets

OBJECTIVE

This study explores a semi-supervised learning (SSL), pseudo-labeled strategy using diverse datasets such as head and neck cancer (HNCa) to enhance lung cancer (LCa) survival outcome predictions, analyzing handcrafted and deep radiomic features (HRF/DRF) from PET/CT scans with hybrid machine learning systems (HMLSs).

METHODS

We collected 199 LCa patients with both PET and CT images, obtained from TCIA and our local database, alongside 408 HNCa PET/CT images from TCIA. We extracted 215 HRFs and 1024 DRFs by PySERA and a 3D autoencoder, respectively, within the ViSERA 1.0.0 software, from segmented primary tumors. The supervised strategy (SL) employed an HMLS-PCA connected with six classifiers on both HRFs and DRFs. The SSL strategy expanded the datasets by adding 408 pseudo-labeled HNCa cases (labeled by the Random Forest algorithm) to 199 LCa cases, using the same HMLS techniques. Furthermore, principal component analysis (PCA) linked with four survival prediction algorithms were utilized in the survival hazard ratio analysis.

RESULTS

The SSL strategy outperformed the SL method (p << 0.001), achieving an average accuracy of 0.85 ± 0.05 with DRFs from PET and PCA + Multi-Layer Perceptron (MLP), compared to 0.69 ± 0.06 for the SL strategy using DRFs from CT and PCA + Light Gradient Boosting (LGB). Additionally, PCA linked with Component-wise Gradient Boosting Survival Analysis on both HRFs and DRFs, as extracted from CT, had an average C-index of 0.80, with a log rank p-value << 0.001, confirmed by external testing.

CONCLUSIONS

Shifting from HRFs and SL to DRFs and SSL strategies, particularly in contexts with limited data points, enabling CT or PET alone, can significantly achieve high predictive performance.

Utilizing Feature Selection Techniques for AI-Driven Tumor Subtype Classification: Enhancing Precision in Cancer Diagnostics

Cancer's heterogeneity presents significant challenges in accurate diagnosis and effective treatment, including the complexity of identifying tumor subtypes and their diverse biological behaviors. This review examines how feature selection techniques address these challenges by improving the interpretability and performance of machine learning (ML) models in high-dimensional datasets. Feature selection methods-such as filter, wrapper, and embedded techniques-play a critical role in enhancing the precision of cancer diagnostics by identifying relevant biomarkers. The integration of multi-omics data and ML algorithms facilitates a more comprehensive understanding of tumor heterogeneity, advancing both diagnostics and personalized therapies. However, challenges such as ensuring data quality, mitigating overfitting, and addressing scalability remain critical limitations of these methods. Artificial intelligence (AI)-powered feature selection offers promising solutions to these issues by automating and refining the feature extraction process. This review highlights the transformative potential of these approaches while emphasizing future directions, including the incorporation of deep learning (DL) models and integrative multi-omics strategies for more robust and reproducible findings.

Prediction of prolonged mechanical ventilation in the intensive care unit via machine learning: a COVID-19 perspective

Early recognition of risk factors for prolonged mechanical ventilation (PMV) could allow for early clinical interventions, prevention of secondary complications such as nosocomial infections, and effective triage of hospital resources. This study tested the hypothesis that an ensemble machine learning (ML) analysis of clinical data at time of intubation could identify patients at risk of PMV, using a COVID-19 dataset to classify patients into PMV (> 14 days) and non-PMV (≤ 14 days) groups. While several factors are known to cause PMV, including acid-base, weakness, and delirium, lesser-utilized but routinely measured parameters such as platelet count, glucose levels and fevers may also be relevant. Patient data from a single University Hospital were analyzed via the ML workflow to predict patients at risk of PMV and identify key clinical markers. Model performance was evaluated on a chronologically distinct cohort. The ML workflow identified patients at risk of PMV with AUROCTRAIN=0.960 (F1TRAIN = 0.935) and AUROCTEST=0.804 (F1TEST = 0.800). Top key features for classification included glucose, platelet count, temperature, LVEF, bicarbonate (arterial blood gas), and BMI. Data analysis at intubation time via the proposed workflow offers the potential to accurately predict patients at risk of PMV, with the goal to improve patient management and triage of hospital resources.

Leveraging segmentation-guided spatial feature embedding for overall survival prediction in glioblastoma with multimodal magnetic resonance imaging

BACKGROUND AND OBJECTIVE

Patients with glioblastoma have a five-year relative survival rate of less than 5 %. Thus, accurately predicting the overall survival (OS) of patients with glioblastoma is crucial for effective treatment planning.

METHODS

To fully leverage the imaging characteristics of glioblastomas, we propose a segmentation-guided regression method for predicting OS of patients with brain tumors using multimodal magnetic resonance imaging. Specifically, a brain tumor segmentation network was first pre-trained without leveraging survival information. Subsequently, the survival regression network was jointly trained with the guidance of brain tumor segmentation, focusing on tumor voxels and suppressing irrelevant backgrounds.

RESULTS

Our proposed framework, based on the well-known backbone of UNETR++, achieved a Dice score of 0.7910, Spearman correlation of 0.4112, and Harrell's concordance index of 0.6488. The model consistently showed promising results compared with baseline methods on two different datasets (BraTS and UCSF-PDGM). Furthermore, ablation studies on our training configurations demonstrated that both the pre-training segmentation network and contrastive loss significantly improved all metrics for OS prediction.

CONCLUSIONS

In this study, we propose a joint learning framework based on a pre-trained segmentation backbone for OS prediction by leveraging a brain tumor segmentation map. By utilizing a spatial feature map, our model can operate using a sliding-window approach, which can be adopted by varying the matrix sizes and resolutions of the input images.

Molecular and immune pathobiology of human angiosarcoma

Angiosarcoma is a rare endothelial-derived malignancy that is extremely diverse in anatomy, aetiology, molecular and immune characteristics. While novel therapeutic approaches incorporating targeted agents and immunotherapy have yielded significant improvements in patient outcomes across several cancers, their impact on angiosarcoma remains modest. Contributed by its heterogeneous nature, there is currently a lack of novel drug targets in this disease entity and no reliable biomarkers that predict response to conventional treatment. This review aims to examine the molecular and immune landscape of angiosarcoma in association with its aetiology, anatomical sites, prognosis and therapeutic options. We summarise current efforts to characterise angiosarcoma subtypes based on molecular and immune profiling. Finally, we highlight promising technologies such as single-cell spatial "omics" that may further our understanding of angiosarcoma and propose strategies that can be similarly applied for the study of other rare cancers.

Identification of Idiopathic Pulmonary Fibrosis and Prediction of Disease Severity via Machine Learning Analysis of Comprehensive Metabolic Panel and Complete Blood Count Data

BACKGROUND

Diagnosis of idiopathic pulmonary fibrosis (IPF) typically relies on high-resolution computed tomography imaging (HRCT) or histopathology, while monitoring disease severity is done via frequent pulmonary function testing (PFT). More reliable and convenient methods of diagnosing fibrotic interstitial lung disease (ILD) type and monitoring severity would allow for early identification and enhance current therapeutic interventions. This study tested the hypothesis that a machine learning (ML) ensemble analysis of comprehensive metabolic panel (CMP) and complete blood count (CBC) data can accurately distinguish IPF from connective tissue disease ILD (CTD-ILD) and predict disease severity as seen with PFT.

METHODS

Outpatient data with diagnosis of IPF or CTD-ILD (n = 103 visits by 53 patients) were analyzed via ML methodology to evaluate (1) IPF vs CTD-ILD diagnosis; (2) %predicted Diffusing Capacity of Lung for Carbon Monoxide (DLCO) moderate or mild vs severe; (3) %predicted Forced Vital Capacity (FVC) moderate or mild vs severe; and (4) %predicted FVC mild vs moderate or severe.

RESULTS

ML methodology identified IPF from CTD-ILD with AUCTEST = 0.893, while PFT was classified as DLCO moderate or mild vs severe with AUCTEST = 0.749, FVC moderate or mild vs severe with AUCTEST = 0.741, and FVC mild vs moderate or severe with AUCTEST = 0.739. Key features included albumin, alanine transaminase, %lymphocytes, hemoglobin, %eosinophils, white blood cell count, %monocytes, and %neutrophils.

CONCLUSION

Analysis of CMP and CBC data via proposed ML methodology offers the potential to distinguish IPF from CTD-ILD and predict severity on associated PFT with accuracy that meets or exceeds current clinical practice.

[Screening of immune related gene and survival prediction of lung adenocarcinoma patients based on LightGBM model]

Lung cancer is one of the malignant tumors with the greatest threat to human health, and studies have shown that some genes play an important regulatory role in the occurrence and development of lung cancer. In this paper, a LightGBM ensemble learning method is proposed to construct a prognostic model based on immune relate gene (IRG) profile data and clinical data to predict the prognostic survival rate of lung adenocarcinoma patients. First, this method used the Limma package for differential gene expression, used CoxPH regression analysis to screen the IRG to prognosis, and then used XGBoost algorithm to score the importance of the IRG features. Finally, the LASSO regression analysis was used to select IRG that could be used to construct a prognostic model, and a total of 17 IRG features were obtained that could be used to construct model. LightGBM was trained according to the IRG screened. The K-means algorithm was used to divide the patients into three groups, and the area under curve (AUC) of receiver operating characteristic (ROC) of the model output showed that the accuracy of the model in predicting the survival rates of the three groups of patients was 96%, 98% and 96%, respectively. The experimental results show that the model proposed in this paper can divide patients with lung adenocarcinoma into three groups [5-year survival rate higher than 65% (group 1), lower than 65% but higher than 30% (group 2) and lower than 30% (group 3)] and can accurately predict the 5-year survival rate of lung adenocarcinoma patients.

Research in the application of artificial intelligence to lung cancer diagnosis

The morbidity and mortality rates in lung cancer are high worldwide. Early diagnosis and personalized treatment are important to manage this public health issue. In recent years, artificial intelligence (AI) has played increasingly important roles in early screening, auxiliary diagnosis, and prognostic assessment. AI uses algorithms to extract quantitative feature information from high-volume and high-latitude data and learn existing data to predict disease outcomes. In this review, we describe the current uses of AI in lung cancer-focused pathomics, imageomics, and genomics applications.

Spatial metabolomics identifies distinct tumor-specific and stroma-specific subtypes in patients with lung squamous cell carcinoma

Molecular subtyping of lung squamous cell carcinoma (LUSC) has been performed at the genomic, transcriptomic, and proteomic level. However, LUSC stratification based on tissue metabolomics is still lacking. Combining high-mass-resolution imaging mass spectrometry with consensus clustering, four tumor- and four stroma-specific subtypes with distinct metabolite patterns were identified in 330 LUSC patients. The first tumor subtype T1 negatively correlated with DNA damage and immunological features including CD3, CD8, and PD-L1. The same features positively correlated with the tumor subtype T2. Tumor subtype T4 was associated with high PD-L1 expression. Compared with the status of subtypes T1 and T4, patients with subtype T3 had improved prognosis, and T3 was an independent prognostic factor with regard to UICC stage. Similarly, stroma subtypes were linked to distinct immunological features and metabolic pathways. Stroma subtype S4 had a better prognosis than S2. Subsequently, analyses based on an independent LUSC cohort treated by neoadjuvant therapy revealed that the S2 stroma subtype was associated with chemotherapy resistance. Clinically relevant patient subtypes as determined by tissue-based spatial metabolomics are a valuable addition to existing molecular classification systems. Metabolic differences among the subtypes and their associations with immunological features may contribute to the improvement of personalized therapy.

Analyzing omics data by feature combinations based on kernel functions

Defining meaningful feature (molecule) combinations can enhance the study of disease diagnosis and prognosis. However, feature combinations are complex and various in biosystems, and the existing methods examine the feature cooperation in a single, fixed pattern for all feature pairs, such as linear combination. To identify the appropriate combination between two features and evaluate feature combination more comprehensively, this paper adopts kernel functions to study feature relationships and proposes a new omics data analysis method KF-[Formula: see text]-TSP. Besides linear combination, KF-[Formula: see text]-TSP also explores the nonlinear combination of features, and allows hybridizing multiple kernel functions to evaluate feature interaction from multiple views. KF-[Formula: see text]-TSP selects [Formula: see text] > 0 top-scoring pairs to build an ensemble classifier. Experimental results show that KF-[Formula: see text]-TSP with multiple kernel functions which evaluates feature combinations from multiple views is better than that with only one kernel function. Meanwhile, KF-[Formula: see text]-TSP performs better than TSP family algorithms and the previous methods based on conversion strategy in most cases. It performs similarly to the popular machine learning methods in omics data analysis, but involves fewer feature pairs. In the procedure of physiological and pathological changes, molecular interactions can be both linear and nonlinear. Hence, KF-[Formula: see text]-TSP, which can measure molecular combination from multiple perspectives, can help to mine information closely related to physiological and pathological changes and study disease mechanism.

Evaluation of Lung Cancer Patient Response to First-Line Chemotherapy by Integration of Tumor Core Biopsy Metabolomics with Multiscale Modeling

The standard of care for intermediate (Stage II) and advanced (Stages III and IV) non-small cell lung cancer (NSCLC) involves chemotherapy with taxane/platinum derivatives, with or without radiation. Ideally, patients would be screened a priori to allow non-responders to be initially treated with second-line therapies. This evaluation is non-trivial, however, since tumors behave as complex multiscale systems. To address this need, this study employs a multiscale modeling approach to evaluate first-line chemotherapy response of individual patient tumors based on metabolomic analysis of tumor core biopsies obtained during routine clinical evaluation. Model parameters were calculated for a patient cohort as a function of these metabolomic profiles, previously obtained from high-resolution 2DLC-MS/MS analysis. Evaluation metrics were defined to classify patients as Disease-Control (DC) [encompassing complete-response (CR), partial-response (PR), and stable-disease (SD)] and Progressive-Disease (PD) following first-line chemotherapy. Response was simulated for each patient and compared to actual response. The results show that patient classifications were significantly separated from each other, and also when grouped as DC vs. PD and as CR/PR vs. SD/PD, by fraction of initial tumor radius metric at 6 days post simulated bolus drug injection. This study shows that patient first-line chemotherapy response can in principle be evaluated from multiscale modeling integrated with tumor tissue metabolomic data, offering a first step towards individualized lung cancer treatment prognosis.