Estimating Time-Varying Exposure Effects Through Continuous-Time Modelling in Mendelian Randomization.

Mendelian randomization is an instrumental variable method that utilizes genetic information to investigate the causal effect of a modifiable exposure on an outcome. In most cases, the exposure changes over time. Understanding the time-varying causal effect of the exposure can yield detailed insights into mechanistic effects and the potential impact of public health interventions. Recently, a growing number of Mendelian randomization studies have attempted to explore time-varying causal effects. However, the proposed approaches oversimplify temporal information and rely on overly restrictive structural assumptions, limiting their reliability in addressing time-varying causal problems. This article considers a novel approach to estimate time-varying effects through continuous-time modelling by combining functional principal component analysis and weak-instrument-robust techniques. Our method effectively utilizes available data without making strong structural assumptions and can be applied in general settings where the exposure measurements occur at different timepoints for different individuals. We demonstrate through simulations that our proposed method performs well in estimating time-varying effects and provides reliable inference when the time-varying effect form is correctly specified. The method could theoretically be used to estimate arbitrarily complex time-varying effects. However, there is a trade-off between model complexity and instrument strength. Estimating complex time-varying effects requires instruments that are unrealistically strong. We illustrate the application of this method in a case study examining the time-varying effects of systolic blood pressure on urea levels.

Multimodal functional deep learning for multiomics data.

With rapidly evolving high-throughput technologies and consistently decreasing costs, collecting multimodal omics data in large-scale studies has become feasible. Although studying multiomics provides a new comprehensive approach in understanding the complex biological mechanisms of human diseases, the high dimensionality of omics data and the complexity of the interactions among various omics levels in contributing to disease phenotypes present tremendous analytical challenges. There is a great need of novel analytical methods to address these challenges and to facilitate multiomics analyses. In this paper, we propose a multimodal functional deep learning (MFDL) method for the analysis of high-dimensional multiomics data. The MFDL method models the complex relationships between multiomics variants and disease phenotypes through the hierarchical structure of deep neural networks and handles high-dimensional omics data using the functional data analysis technique. Furthermore, MFDL leverages the structure of the multimodal model to capture interactions between different types of omics data. Through simulation studies and real-data applications, we demonstrate the advantages of MFDL in terms of prediction accuracy and its robustness to the high dimensionality and noise within the data.

Longitudinal activity monitoring and lifespan: quantifying the interface.

Understanding the relationship between activity over the entire lifespan and longevity is an important facet of aging research. We present a comprehensive framework for the statistical analysis of longitudinal activity and behavioral monitoring and their relationship with age-at-death at the individual level, highlighting the importance of advanced methodological approaches in aging research. The focus is on animal models, where continuous monitoring activity in terms of movement, reproduction and behaviors over the entire lifespan is feasible at the individual level. We specifically demonstrate the methodology with data on activity monitoring for Mediterranean fruit flies. Advanced statistical methodologies to explore the interface between activity and age-at-death include functional principal component analysis, concurrent regression, Fréchet regression and point processes. While the focus of this perspective is on relating age-at-death with data on movement, reproduction, behavior and nutrition of Mediterranean fruit flies, the methodology equally pertains to data from other species, including human data.

Data-knowledge co-driven feature based prediction model via photoplethysmography for evaluating blood pressure.

BACKGROUND: Knowledge feature (KF) with clear physiological significance of photoplethysmography are widely used in predicting blood pressure. However, KF primarily focus on local information of photoplethysmography, which may struggle to capture the overall characteristics. METHODS: Firstly, functional data analysis (FDA) was introduced to extract two types of data feature (DF). Furthermore, data-knowledge co-driven feature (DKCF) was proposed by combining FDA and constraints of KF. Finally, random forest, ada boost, gradient boosting, support vector machine and deep neural network were adopted, to compare the abilities of KF, DFs and DKCF in predicting blood pressure with two datasets (A published dataset and a self-collected dataset). RESULTS: Under the premise of extracting only 9 features, the average mean absolute errors (MAE) of systolic blood pressure (SBP) and diastolic blood pressure (DBP) obtained by DKCF are both the smallest in dataset 1. In dataset 2, DKCF acquires the smallest MAE in predicting SBP and obtains the second smallest MAE in predicting DBP. CONCLUSIONS: The results demonstrate that low-dimensional DKCF of photoplethysmography is closely correlated with blood pressure, which may serve as an important indicator for health assessment.

Peak vertical ground reaction force used to identify sub-groups of individuals with differing biomechanical gait profiles post-anterior cruciate ligament reconstruction.

Lesser peak vertical ground reaction force (vGRF) has been widely reported among individuals with anterior cruciate ligament reconstruction (ACLR). Peak vGRF remains less than uninjured controls and relatively stable during the first year following ACLR. However, it is unknown whether there are subgroups of individuals exhibiting consistently greater peak vGRF in the first 6-months following ACLR and if individuals with consistently greater peak vGRF exhibit kinematic and kinetic gait differences compared to individuals with low vGRF. The purpose of this study was to determine if distinct clusters exist based upon magnitude of peak vGRF 2- and 6-months post-ACLR. Subsequently, we explored between cluster differences in vGRF, knee flexion angle, and sagittal and frontal plane knee kinetics throughout stance between clusters. Forty-three individuals (58.1%female, 21.4 ± 4.4 years-old, 95.3% patellar-tendon autograft) completed five gait trials at their habitual walking speed 2- and 6-months post-ACLR. A single K-means cluster analysis was used to identify clusters of individuals based on peak vGRF at 2- and 6-months post-ACLR. Functional waveform analyses were used to compare gait outcomes between clusters with and without controlling for gait speed and age. We identified two clusters that included a subgroup with high vGRF (n = 16) and low vGRF (n = 27). The cluster with high vGRF demonstrated greater vGRFs, knee flexion angles, and knee extension moments during early stance as compared to the low vGRF cluster 2- and 6-months post-ACLR. Individuals with peak vGRF ≥1.02 times body-weight 2-months post-ACLR had 35.4 times greater odds of being assigned to the high vGRF cluster.

Regression and alignment for functional data and network topology.

In the brain, functional connections form a network whose topological organization can be described by graph-theoretic network diagnostics. These include characterizations of the community structure, such as modularity and participation coefficient, which have been shown to change over the course of childhood and adolescence. To investigate if such changes in the functional network are associated with changes in cognitive performance during development, network studies often rely on an arbitrary choice of preprocessing parameters, in particular the proportional threshold of network edges. Because the choice of parameter can impact the value of the network diagnostic, and therefore downstream conclusions, we propose to circumvent that choice by conceptualizing the network diagnostic as a function of the parameter. As opposed to a single value, a network diagnostic curve describes the connectome topology at multiple scales-from the sparsest group of the strongest edges to the entire edge set. To relate these curves to executive function and other covariates, we use scalar-on-function regression, which is more flexible than previous functional data-based models used in network neuroscience. We then consider how systematic differences between networks can manifest in misalignment of diagnostic curves, and consequently propose a supervised curve alignment method that incorporates auxiliary information from other variables. Our algorithm performs both functional regression and alignment via an iterative, penalized, and nonlinear likelihood optimization. The illustrated method has the potential to improve the interpretability and generalizability of neuroscience studies where the goal is to study heterogeneity among a mixture of function- and scalar-valued measures.

A Data-Driven Approach for Leveraging Inline and Offline Data to Determine the Causes of Monoclonal Antibody Productivity Reduction in the Commercial-Scale Cell Culture Process.

The monoclonal antibody (mAb) manufacturing process comes with high profits and high costs, and thus mAb productivity is of vital importance. However, many factors can impact the cell culture process, and lead to mAb productivity reduction. Nowadays, the biopharma industry is actively employing manufacturing information systems, which enable the integration of both online data and offline data. Although the volume of data is large, related data mining studies for mAb productivity improvement are rare. Therefore, a data-driven approach is proposed in this study to leverage both the inline and offline data of the cell culture process to discover the causes of mAb productivity reduction. The approach consists of four steps, namely data preprocessing, phase division, feature extraction and fusion, and cluster comparing. First, data quality issues are solved during the data preprocessing step. Next, the inline data are divided into several phases based on the moving window k-nearest neighbor method. Then, the inline data features are extracted via functional data analysis and combined with the offline data features. Finally, the causes of mAb productivity reduction are identified using the contrasting clusters via the principal component analysis method. A commercial-scale cell culture process case study is provided in this research to verify the effectiveness of the approach. Data from 35 batches were collected, and each batch contained nine inline variables and seven offline variables. The causes of mAb productivity reduction were identified to be the lack of nutrients, and recommended actions were taken according to the result, which was subsequently proven by six validation batches.

Utilising raw psycho-physiological data and functional data analysis for estimating mental workload in human drivers.

Recent studies have focused on accurately estimating mental workload using machine learning algorithms and extracting features from physiological measures. However, feature extraction leads to the loss of valuable information and often results in binary classifications that lack specificity in the identification of optimum mental workload. This study investigates the feasibility of using raw physiological data (EEG, facial EMG, ECG, EDA, pupillometry) combined with Functional Data Analysis (FDA) to estimate the mental workload of human drivers. A driving scenario with five tasks was employed, and subjective ratings were collected. Results demonstrate that the FDA applied nine different combinations of raw physiological signals achieving a maximum 90% accuracy, outperforming extracted features by 73%. This study shows that the mental workload of human drivers can be accurately estimated without utilising burdensome feature extraction. The approach proposed in this study offers promise for mental workload assessment in real-world applications.

This study aimed to estimate the mental workload of human drivers using physiological signals and Functional Data Analysis (FDA). By comparing models using raw data and extracted features, the results show that the FDA with raw data achieved a high accuracy of 90%, outperforming the model with extracted features (73%).

Extracting actigraphy-based walking features with structured functional principal components.

Objective.We extract walking features from raw accelerometry data while accounting for varying cadence and commonality of features among subjects. Walking is the most performed type of physical activity. Thus, we explore if an individual's physical health is related to these walking features.Approach.We use data collected using ActiGraph GT3X+ devices (sampling rate = 80 Hz) as part of the developmental epidemiologic cohort study,I= 48, age =78.7±5.7years, 45.8% women. We apply structured functional principal component analysis (SFPCA) to extract features from walking signals on both, the subject-specific and the subject-spectrum-specific level of a fast-paced 400 m walk, an indicator of aerobic fitness in older adults. We also use the subject-specific level feature scores to study their associations with age and physical performance measures. Specifically, we transform the raw data into the frequency domain by applying local Fast Fourier Transform to obtain the walking spectra. SFPCA decomposes these spectra into easily interpretable walking features expressed as cadence and acceleration, which can be related to physical performance.Main results.We found that five subject-specific and 19 subject-spectrum-specific level features explained more than 85% of their respective level variation, thus significantly reducing the complexity of the data. Our results show that 54% of the total data variation arises at the subject-specific and 46% at the subject-spectrum-specific level. Moreover, we found that higher acceleration magnitude at the cadence was associated with younger age, lower BMI, faster average cadence and higher short physical performance battery scores. Lower acceleration magnitude at the cadence and higher acceleration magnitude at cadence multiples 2.5 and 3.5 are related to older age and higher blood pressure.Significance.SFPCA extracted subject-specific level empirical walking features which were meaningfully associated with several health indicators and younger age. Thus, an individual's walking pattern could shed light on subclinical stages of somatic diseases.

DeepIDA-GRU: a deep learning pipeline for integrative discriminant analysis of cross-sectional and longitudinal multiview data with applications to inflammatory bowel disease classification.

Biomedical research now commonly integrates diverse data types or views from the same individuals to better understand the pathobiology of complex diseases, but the challenge lies in meaningfully integrating these diverse views. Existing methods often require the same type of data from all views (cross-sectional data only or longitudinal data only) or do not consider any class outcome in the integration method, which presents limitations. To overcome these limitations, we have developed a pipeline that harnesses the power of statistical and deep learning methods to integrate cross-sectional and longitudinal data from multiple sources. In addition, it identifies key variables that contribute to the association between views and the separation between classes, providing deeper biological insights. This pipeline includes variable selection/ranking using linear and nonlinear methods, feature extraction using functional principal component analysis and Euler characteristics, and joint integration and classification using dense feed-forward networks for cross-sectional data and recurrent neural networks for longitudinal data. We applied this pipeline to cross-sectional and longitudinal multiomics data (metagenomics, transcriptomics and metabolomics) from an inflammatory bowel disease (IBD) study and identified microbial pathways, metabolites and genes that discriminate by IBD status, providing information on the etiology of IBD. We conducted simulations to compare the two feature extraction methods.

Gradient synchronization for multivariate functional data, with application to brain connectivity.

Quantifying the association between components of multivariate random curves is of general interest and is a ubiquitous and basic problem that can be addressed with functional data analysis. An important application is the problem of assessing functional connectivity based on functional magnetic resonance imaging (fMRI), where one aims to determine the similarity of fMRI time courses that are recorded on anatomically separated brain regions. In the functional brain connectivity literature, the static temporal Pearson correlation has been the prevailing measure for functional connectivity. However, recent research has revealed temporally changing patterns of functional connectivity, leading to the study of dynamic functional connectivity. This motivates new similarity measures for pairs of random curves that reflect the dynamic features of functional similarity. Specifically, we introduce gradient synchronization measures in a general setting. These similarity measures are based on the concordance and discordance of the gradients between paired smooth random functions. Asymptotic normality of the proposed estimates is obtained under regularity conditions. We illustrate the proposed synchronization measures via simulations and an application to resting-state fMRI signals from the Alzheimer's Disease Neuroimaging Initiative and they are found to improve discrimination between subjects with different disease status.

Functional data geometric morphometrics with machine learning for craniodental shape classification in shrews.

This work proposes a functional data analysis approach for morphometrics in classifying three shrew species (S. murinus, C. monticola, and C. malayana) from Peninsular Malaysia. Functional data geometric morphometrics (FDGM) for 2D landmark data is introduced and its performance is compared with classical geometric morphometrics (GM). The FDGM approach converts 2D landmark data into continuous curves, which are then represented as linear combinations of basis functions. The landmark data was obtained from 89 crania of shrew specimens based on three craniodental views (dorsal, jaw, and lateral). Principal component analysis and linear discriminant analysis were applied to both GM and FDGM methods to classify the three shrew species. This study also compared four machine learning approaches (naïve Bayes, support vector machine, random forest, and generalised linear model) using predicted PC scores obtained from both methods (a combination of all three craniodental views and individual views). The analyses favoured FDGM and the dorsal view was the best view for distinguishing the three species.

Multilevel functional data analysis modeling of human glucose response to meal intake.

Glucose meal response information collected via Continuous Glucose Monitoring (CGM) is relevant to the assessment of individual metabolic status and the support of personalized diet prescriptions. However, the complexity of the data produced by CGM monitors pushes the limits of existing analytic methods. CGM data often exhibits substantial within-person variability and has a natural multilevel structure. This research is motivated by the analysis of CGM data from individuals without diabetes in the AEGIS study. The dataset includes detailed information on meal timing and nutrition for each individual over different days. The primary focus of this study is to examine CGM glucose responses following patients' meals and explore the time-dependent associations with dietary and patient characteristics. Motivated by this problem, we propose a new analytical framework based on multilevel functional models, including a new functional mixed R-square coefficient. The use of these models illustrates 3 key points: (i) The importance of analyzing glucose responses across the entire functional domain when making diet recommendations; (ii) The differential metabolic responses between normoglycemic and prediabetic patients, particularly with regards to lipid intake; (iii) The importance of including random, person-level effects when modelling this scientific problem.

Profiling biomechanical abilities during sprint front-crawl swimming using IMU and functional clustering of variabilities.

This study aims to profile biomechanical abilities during sprint front crawl by identifying technical stroke characteristics, in light of performance level. Ninety-one recreational to world-class swimmers equipped with a sacrum-worn IMU performed 25 m all-out. Intra and inter-cyclic 3D kinematical variabilities were clustered using a functional double partition model. Clusters were analysed according to (1) swimming technique using continuous visualisation and discrete features (standard deviation and jerk cost) and (2) performance regarding speed and competition calibre using respectively one-way ANOVA and Chi-squared test as well as Gamma statistics. Swimmers displayed specific technical profiles of intra-cyclic (smoothy and jerky) and inter-cyclic stroke regulation (low, moderate and high repeatability) significantly discriminated by speed (p < 0.001, η2 = 0.62) and performance calibre (p < 0.001, V = 0.53). We showed that combining high levels of both kinds of variability (jerky + low repeatability) are associated with highest speed (1.86 ± 0.12 m/s) and competition calibre (ℽ = 0.75, p < 0.001). It highlights the crucial importance of variabilities combination. Technical skills might be driven by a specific alignment of stroke pattern and its associated dispersion according to the task constraints. This data-driven approach can assist eyes-based technical evaluation. Targeting the development of an explosive swimming style with a high level of body stability should be considered during training of sprinters.

Data-Fusion-Based Quality Enhancement for HR Measurements Collected by Wearable Sensors.

The advancements of Internet of Things (IoT) technologies have enabled the implementation of smart and wearable sensors, which can be employed to provide older adults with affordable and accessible continuous biophysiological status monitoring. The quality of such monitoring data, however, is unsatisfactory due to excessive noise induced by various disturbances, such as motion artifacts. Existing methods take advantage of summary statistics, such as mean or median values, for denoising, without taking into account the biophysiological patterns embedded in data. In this research, a functional data analysis modeling method was proposed to enhance the data quality by learning individual subjects' diurnal heart rate (HR) patterns from historical data, which were further improved by fusing newly collected data. This proposed data-fusion approach was developed based on a Bayesian inference framework. Its effectiveness was demonstrated in an HR analysis from a prospective study involving older adults residing in assisted living or home settings. The results indicate that it is imperative to conduct personalized healthcare by estimating individualized HR patterns. Furthermore, the proposed calibration method provides a more accurate (smaller mean errors) and more precise (smaller error standard deviations) HR estimation than raw HR and conventional methods, such as the mean.

The relationship between joint kinematic patterns during single-leg drop landing and perceived instability in individuals with chronic ankle instability.

BACKGROUND: Perceived instability is a primary symptom among individuals with chronic ankle instability. However, the relationship between joint kinematics during landing remains unclear. Therefore, we investigated the relationships between landing kinematics and perceived instability in individuals with chronic ankle instability. METHODS: In 32 individuals with chronic ankle instability, we recorded ankle, knee, and hip joint angles during a single-leg drop landing. Joint angle waveforms during 200 ms before and after initial contact were summarized into single values using two methods: peak joint angles and principal component scores via principal component analysis. Using Spearman's rank correlation coefficient (ρ), we examined the relationships of peak joint angles and principal component scores with the Cumberland Ankle Instability Tool score, with a lower score indicating a greater perceived instability (α = 0.05). FINDINGS: The second principal component scores of ankle angle in the horizontal and sagittal planes significantly correlated with the Cumberland Ankle Instability Tool score (Horizontal: ρ = 0.507, P = 0.003; Sagittal: ρ = -0.359, P = 0.044). These scores indicated the differences in the magnitude of angles before and after landing. Significant correlations indicated a greater perceived instability correlated with smaller internal rotation and plantarflexion before landing and smaller external rotation and dorsiflexion after landing. In contrast, no peak joint angles correlated with the Cumberland Ankle Instability Tool score (P > 0.05). INTERPRETATION: In individuals with chronic ankle instability, ankle movements during landing associated with perceived instability may be a protective strategy before landing and potentially cause ankle instability after landing.

Strategies for knee stabilising and pivot-shift avoidance in a step-down and cross-over task observed sub-acutely after anterior cruciate ligament reconstruction.

BACKGROUND: Individuals with a recent anterior cruciate ligament reconstruction may demonstrate an altered movement strategy for protecting the knee and maintaining stability. Altered knee movement might lead to abnormal intra-articular load, potentially contributing to early knee osteoarthritis onset. A protective strategy may be particularly evident during active tasks that induce a pivot-shift manoeuvre, such as a step-down and cross-over task. In this study, we investigated whether knee joint mechanics and muscle activity differed between participants early (∼3 months) following reconstruction (n = 35) to uninjured controls (n = 35) during a step-down and cross-over task with a 45° change-of-direction. METHODS: We used motion capture, force plates and surface electromyography to compare time-normalised curves of sagittal and transverse-plane knee mechanics and muscle activity during the cross-over phase between groups using functional t-tests. We also compared knee mechanics between sides within the injured group and compared discrete outcomes describing the cross-over phase between groups. FINDINGS: Compared to controls, the injured participants had greater knee flexion angle and moment, lower internal rotation moment, more preparatory foot rotation of the pivoting leg, a smaller cross-over angle, and a longer cross-over phase for both the injured and uninjured sides. The injured leg also had greater biceps femoris and vastus medialis muscle activity compared to controls and different knee mechanics than the uninjured leg. INTERPRETATION: Individuals with anterior cruciate ligament reconstruction showed a knee-stabilising and pivot-shift avoidance strategy for both legs early in rehabilitation. These results may reflect an altered motor representation and motivate considerations early in rehabilitation.

A Study of Pupil Response to Light as a Digital Biomarker of Recent Cannabis Use.

Introduction: Given the traffic safety and occupational injury prevention implications associated with cannabis impairment, there is a need for objective and validated measures of recent cannabis use. Pupillary light response may offer an approach for detection. Method: Eighty-four participants (mean age: 32, 42% female) with daily, occasional, and no-use cannabis use histories participated in pupillary light response tests before and after smoking cannabis ad libitum or relaxing for 15 min (no use). The impact of recent cannabis consumption on trajectories of the pupillary light response was modeled using functional data analysis tools. Logistic regression models for detecting recent cannabis use were compared, and average pupil trajectories across cannabis use groups and times since light test administration were estimated. Results: Models revealed small, significant differences in pupil response to light after cannabis use comparing the occasional use group to the no-use control group, and similar statistically significant differences in pupil response patterns comparing the daily use group to the no-use comparison group. Trajectories of pupillary light response estimated using functional data analysis found that acute cannabis smoking was associated with less initial and sustained pupil constriction compared to no cannabis smoking. Conclusion: These analyses show the promise of pairing pupillary light response and functional data analysis methods to assess recent cannabis use.

Utilizing the Glucose and Insulin Response Shape of an Oral Glucose Tolerance Test to Predict Dysglycemia in Children with Overweight and Obesity, Ages 8-18 Years.

Common dysglycemia measurements including fasting plasma glucose (FPG), oral glucose tolerance test (OGTT)-derived 2 h plasma glucose, and hemoglobin A1c (HbA1c) have limitations for children. Dynamic OGTT glucose and insulin responses may better reflect underlying physiology. This analysis assessed glucose and insulin curve shapes utilizing classifications-biphasic, monophasic, or monotonically increasing-and functional principal components (FPCs) to predict future dysglycemia. The prospective cohort included 671 participants with no previous diabetes diagnosis (BMI percentile ≥ 85th, 8-18 years old); 193 returned for follow-up (median 14.5 months). Blood was collected every 30 min during the 2 h OGTT. Functional data analysis was performed on curves summarizing glucose and insulin responses. FPCs described variation in curve height (FPC1), time of peak (FPC2), and oscillation (FPC3). At baseline, both glucose and insulin FPC1 were significantly correlated with BMI percentile (Spearman correlation r = 0.22 and 0.48), triglycerides (r = 0.30 and 0.39), and HbA1c (r = 0.25 and 0.17). In longitudinal logistic regression analyses, glucose and insulin FPCs predicted future dysglycemia (AUC = 0.80) better than shape classifications (AUC = 0.69), HbA1c (AUC = 0.72), or FPG (AUC = 0.50). Further research should evaluate the utility of FPCs to predict metabolic diseases.

Discrimination of Genetic Biomarkers of Disease through Machine-Learning-Based Hypothesis Testing of Direct SERS Spectra of DNA and RNA.

Cancer is globally a leading cause of death that would benefit from diagnostic approaches detecting it in its early stages. However, despite much research and investment, cancer early diagnosis is still underdeveloped. Owing to its high sensitivity, surface-enhanced Raman spectroscopy (SERS)-based detection of biomarkers has attracted growing interest in this area. Oligonucleotides are an important type of genetic biomarkers as their alterations can be linked to the disease prior to symptom onset. We propose a machine-learning (ML)-enabled framework to analyze complex direct SERS spectra of short, single-stranded DNA and RNA targets to identify relevant mutations occurring in genetic biomarkers, which are key disease indicators. First, by employing ad hoc-synthesized colloidal silver nanoparticles as SERS substrates, we analyze single-base mutations in ssDNA and RNA sequences using a direct SERS-sensing approach. Then, an ML-based hypothesis test is proposed to identify these changes and differentiate the mutated sequences from the corresponding native ones. Rooted in "functional data analysis," this ML approach fully leverages the rich information and dependencies within SERS spectral data for improved modeling and detection capability. Tested on a large set of DNA and RNA SERS data, including from miR-21 (a known cancer miRNA biomarker), our approach is shown to accurately differentiate SERS spectra obtained from different oligonucleotides, outperforming various data-driven methods across several performance metrics, including accuracy, sensitivity, specificity, and F1-scores. Hence, this work represents a step forward in the development of the combined use of SERS and ML as effective methods for disease diagnosis with real applicability in the clinic.