Since microorganisms are evolving rapidly, there is a growing need for a new, fast, and precise technique to analyse blood samples and distinguish healthy from pathological samples. Fourier Transform Infrared (FTIR) spectroscopy can provide information related to the biochemical composition and how it changes when a pathological state arises. FTIR spectroscopy has undergone rapid development over the last decades with a promise of easier, faster, and more impartial diagnoses within the biomedical field. However, thus far only a limited number of studies have addressed the use of FTIR spectroscopy in this field. This paper describes the main concepts related to FTIR and presents the latest research focusing on FTIR spectroscopy technology and its integration in lab-on-a-chip devices and their applications in the biological field. This review presents the potential use of FTIR to distinguish between healthy and pathological samples, with examples of early cancer detection, human immunodeficiency virus (HIV) detection, and routine blood analysis, among others. Finally, the study also reflects on the features of FTIR technology that can be applied in a lab-on-a-chip format and further developed for small healthcare devices that can be used for point-of-care monitoring purposes. To the best of the authors’ knowledge, no other published study has reviewed these topics. Therefore, this analysis and its results will fill this research gap.

Machine learning (ML) is a broad term encompassing several methods that allow us to learn from data. These methods may permit large real-world databases to be more rapidly translated to applications to inform patient–provider decision-making. This paper presents a review of articles that discuss the use of Fourier transform infrared (FTIR) spectroscopy and ML for human blood analysis between the years 2019–2023. The literature review was conducted to identify published research of employed ML linked with FTIR for distinction between pathological and healthy human blood cells. The articles’ search strategy was implemented and studies meeting the eligibility criteria were evaluated. Relevant data related to the study design, statistical methods, and strengths and limitations were identified. A total of 39 publications in the last 5 years (2019–2023) were identified and evaluated for this review. Diverse methods, statistical packages, and approaches were used across the identified studies. The most common methods included support vector machine (SVM) and principal component analysis (PCA) approaches. Most studies applied internal validation and employed more than one algorithm, while only four studies applied one ML algorithm to the data. A wide variety of approaches, algorithms, statistical software, and validation strategies were employed in the application of ML methods. There is a need to ensure that multiple ML approaches are used, the model selection strategy is clearly defined, and both internal and external validation are necessary to be sure that the discrimination of human blood cells is being made with the highest efficient evidence.

Early detection of diabetes mellitus (DM) is essential for preventing disease progression and improving clinical outcomes. However, developing robust machine learning (ML) models for diabetes diagnosis is often constrained by limited data availability, privacy regulations, and challenges with data sharing. This study investigates a privacy-preserving synthetic data augmentation framework for classifying diabetic and non-diabetic blood serum samples using Fourier Transform Infrared (FTIR) spectroscopy. Two deep generative approaches, Autoencoders (AEs) and Generative Adversarial Networks (GANs), were evaluated for their ability to generate realistic synthetic FTIR spectra while preserving the statistical and biochemical characteristics of the original dataset. Synthetic datasets generated by the AE and GAN models were assessed using six ML classifiers: Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbors (KNN), Gradient Boosting (GB), Logistic Regression (LoR), and Decision Tree (DT). Model performance was evaluated using accuracy, precision, recall, F1-score, Receiver Operating Characteristic (ROC) curves, and Area Under the Curve (AUC). Results showed that AE-generated spectra retained stronger discriminative characteristics and were more easily distinguished from the original spectra, whereas GAN-generated spectra exhibited lower classifier separability, suggesting closer alignment with the original data distribution and greater realism for privacy-oriented data augmentation. Correlation analysis demonstrated high spectral fidelity for both approaches. Compared with the original spectra, AE-generated spectra achieved r = 0.9990 and R² = 0.9999, whereas GAN-generated spectra achieved r = 0.9982 and R² = 0.9965. The most prominent diabetes related spectral variations were observed in the carbohydrate (1000–1200 cm⁻¹), Amide I (~1650 cm⁻¹), and lipid-associated (3000–3500 cm⁻¹) regions. To explore the transferability of the proposed framework, a preliminary experimental feasibility study was conducted using independently acquired whole blood FTIR spectra. The generated spectra showed strong agreement with the measured whole blood spectra, demonstrating the potential applicability of the framework under alternative sampling conditions. Because the experimental cohort included only one diabetic volunteer, this analysis was intended solely as a proof-of-concept assessment of spectral feasibility and methodological transferability, rather than as a validation of diabetes classification performance. Overall, the findings demonstrate that synthetic data generation can effectively augment limited FTIR datasets while preserving privacy and key spectral characteristics. The proposed framework provides a promising foundation for privacy-aware biomedical data augmentation and future development of robust FTIR diabetes screening systems. The results should be interpreted as methodological evidence of feasibility and synthetic data utility rather than as evidence of clinical diagnostic readiness, as the serum dataset remains modest in size and the independent whole-blood experiment was intentionally exploring.