Extracting key features for phenotype classification from high-dimensional and complex mass spectrometry (MS) data presents a significant challenge. Conventional data representation methods, such as traditional peak lists or grid-based imaging strategies, are often hampered by information loss and compromised signal integrity, thereby limiting the performance of downstream deep learning models. To address this issue, we propose a novel data representation framework named MSIMG. Inspired by object detection in computer vision, MSIMG introduces a data-driven, “density-peak-centric” patch selection strategy. This strategy employs density map estimation and non-maximum suppression algorithms to locate the centers of signal-dense regions, which serve as anchors for dynamic, content-aware patch extraction. This process transforms raw mass spectrometry data into a multi-channel image representation with higher information fidelity. Extensive experiments conducted on two public clinical mass spectrometry datasets demonstrate that MSIMG significantly outperforms both the traditional peak list method and the grid-based MetImage approach. This study confirms that the MSIMG framework, through its content-aware patch selection, provides a more information-dense and discriminative data representation paradigm for deep learning models. Our findings highlight the decisive impact of data representation on model performance and successfully demonstrate the immense potential of applying computer vision strategies to analytical chemistry data, paving the way for the development of more robust and precise clinical diagnostic models.

Mass spectrometry (MS) data present challenges for machine learning (ML) classification due to their high dimensionality, complex feature distributions, batch effects, and intensity discrepancies, often hindering model generalization and efficiency. To address these issues, this study introduces the Efficient Quick 1D Lite Convolutional Neural Network (CNN) Ensemble Classifier (EQLC-EC), integrating 1D convolutional networks with reshape layers and dual voting mechanisms for enhanced feature representation and classification performance. Validation was performed on five publicly available MS datasets, each featured in high-impact publications. EQLC-EC underwent comprehensive evaluation against classical machine learning (ML) models (e.g., support vector machine (SVM), random forest) and the leading deep learning methods reported in these studies. EQLC-EC demonstrated dataset-specific improvements, including enhanced classification accuracy (1–5% increase) and reduced standard deviation (1–10% reduction). Performance differences between soft and hard voting mechanisms were negligible (<1% variation in accuracy and standard deviation). EQLC-EC presents a powerful and efficient tool for MS data analysis with potential applications across metabolomics and proteomics.

Mass spectrometry (MS) data presents challenges for machine learning (ML) classification due to its high dimensionality, complex feature distributions, batch effects, and intensity discrepancies, often hindering model generalization and efficiency. To address these issues, this study introduces the Efficient Quick 1D Lite CNN Ensemble Classifier (EQLC-EC), integrating 1D convolutional networks with reshape layers and dual voting mechanisms for enhanced feature representation and classification performance. Validation was performed on five publicly available MS datasets, each featured in high-impact publications. EQLC-EC underwent comprehensive evaluation against classical machine learning (ML) models (e.g., support vector machine [SVM], random forest) and the leading deep learning methods reported in these studies. EQLC-EC demonstrated dataset-specific improvements, including enhanced classification accuracy (1%-5% increase) and reduced standard deviation (1%-10% reduction). Performance differences between soft and hard voting mechanisms were negligible (<1% variation in accuracy and standard deviation). EQLC-EC presents a powerful and efficient tool for MS data analysis with potential applications across metabolomics and proteomics.

Mass spectrometry (MS) analysis plays a crucial role in the biomedical field; however, the high dimensionality and complexity of MS data pose significant challenges for feature extraction and classification. Deep learning has become a dominant approach in data analysis, and while some deep learning methods have achieved progress in MS classification, their feature representation capabilities remain limited. Most existing methods rely on single-channel representations, which struggle to effectively capture structural information within MS data. To address these limitations, we propose a Multi-Channel Embedding Representation Module (MSMCE), which focuses on modeling inter-channel dependencies to generate multi-channel representations of raw MS data. Additionally, we implement a feature fusion mechanism by concatenating the initial encoded representation with the multi-channel embeddings along the channel dimension, significantly enhancing the classification performance of subsequent models. Experimental results on four public datasets demonstrate that the proposed MSMCE module not only achieves substantial improvements in classification performance but also enhances computational efficiency and training stability, highlighting its effectiveness in raw MS data classification and its potential for robust application across diverse datasets.

Mass spectrometry (MS) analysis plays a crucial role in the biomedical field; however, the high dimensionality and complexity of MS data pose significant challenges for feature extraction and classification. Deep learning has become a dominant approach in data analysis, and while some deep learning methods have achieved progress in MS classification, their feature representation capabilities remain limited. Most existing methods rely on single-channel representations, which struggle to effectively capture the structural information within MS data. To address these limitations, we propose a Multi-Channel Embedding Representation Module (MSMCE), which focuses on modeling inter-channel dependencies to generate multi-channel representations of raw MS data. Additionally, we introduce a “residual” connection along the channel dimension, significantly enhancing the classification performance of subsequent models. Experimental results on four public datasets demonstrate that the proposed MSMCE module not only achieves substantial improvements in classification performance but also reduces computational resource consumption and enhances training efficiency, highlighting its effectiveness and generalizability in raw MS data classification.

Published breath examination studies report inconsistent associations between diabetes and exhaled volatile organic compounds, partly because conventional appraisal tools do not assess whether quantitative data are comparable and fit for secondary use. We developed the National Institute of Metrology–Diabetes Breath Assessment (NIM-DBA) framework, drawing on metrological specifications and data-quality principles issued by the International Organization for Standardization (ISO). PubMed, Scopus, Embase, and Web of Science were searched through April 2025 for quantitative human breath data related to diabetes. Breath acetone was used as a case study, and the same literature pool was assessed with the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool. Of 38 eligible studies, six (15.8%) met all NIM-DBA criteria. QUADAS-2 found high risk of bias in patient selection (79%) and unclear risk in index-test reporting (82%). A post-classification comparison of the six criteria-met and 32 criteria-not-met studies identified exploratory enrichment of standardized breath maneuvers, calibration coverage, alveolar or end-expiratory sampling, pre-sampling alcohol control, sample-stability validation, background assessment, and morning sampling. These findings do not establish breath acetone as a standalone diagnostic biomarker. Instead, they show how fitness-for-purpose assessment can identify more comparable evidence and clarify how methodological choices contribute to inconsistent findings. NIM-DBA complements clinical risk-of-bias tools and may support secondary quantitative data use and future study design.