Background: Advancements in machine learning (ML) techniques and voice technology offer the potential to harness voice as a new tool for developing decision-support tools in healthcare for the benefit of both healthcare providers and patients. Motivated by technological breakthroughs and the increasing integration of Artificial Intelligence (AI) and Machine Learning (ML) in healthcare, numerous studies aim to investigate the diagnostic potential of ML algorithms in the context of voice-affecting disorders. This thesis focuses on respiratory diseases such as Chronic Obstructive Pulmonary Disease (COPD) and explores the potential of a decision support tool that utilizes voice and ML. This exploration exemplifies the intricate relationship between voice and overall health through the lens of applied health technology (AHT. This interdisciplinary nature of research recognizes the need for accurate and efficient diagnostic tools.

Objective: The objectives of this licentiate thesis are twofold. Firstly, a Systematic Literature Review (SLR) thoroughly investigates the current state of ML algorithms in detecting voice-affecting disorders, pinpointing existing gaps and suggesting directions for future research. Secondly, the study focuses on respiratory health, specifically COPD, employing ML techniques with a distinct emphasis on the vowel "A". The aim is to explore hidden information that could potentially be utilized for the binary classification of COPD vs no COPD. The creation of a new Swedish COPD voice classification dataset is anticipated to enhance the experimental and exploratory dimensions of the research.

Methods: In order to have a holistic view of a research field, one of the commonly utilized methods is to scan and analyze the literature. Therefore, Paper I followed the methodology of an SLR where existing journal publications were scanned and synthesized to create a holistic view in the realm of ML techniques employed to experiment on voice-affecting disorders. Based on the results from the SLR, Paper II focused on the data collection and experimentation for the binary classification of COPD, which was one of the gaps identified in the first study. Three distinct ML algorithms were investigated on the collected datasets through voice features, which consisted of recordings collected through a mobile application from participants 18 years old and above, and the most utilized performance measures were computed for the best outcome. 

Results: The summary of findings from Paper I reveals the dominance of Support Vector Machine (SVM) classifiers in voice disorder research, with Parkinson's Disease and Alzheimer's Disease as the most studied disorders. Gaps in research include underrepresented disorders, limited datasets in terms of number of participants, and a lack of interest in longitudinal studies. Paper II demonstrates promising results in COPD classification using ML and a newly developed dataset, offering insights into potential decision support tools for COPD diagnosis.

Conclusion: The studies covered in this dissertation provide a comprehensive literature summary of ML techniques used to support decision-making on voice-affecting disorders for clinical outcomes. The findings contribute to understanding the diagnostic potential of using ML on vocal features and highlight avenues for future research and technology development. Nonetheless, the experiment reveals the potential of employing voice as a digital biomarker for COPD diagnosis using ML.

Chronic Obstructive Pulmonary Disease (COPD) is a leading cause of morbidity and mortality worldwide, with high underdiagnosis rates due to limitations in current diagnostic methods such as spirometry. This doctoral thesis explores the potential of voice as a digital biomarker to support the assessment of COPD, guided by the principles of Applied Health Technology (AHT), which emphasizes interdisciplinary collaboration and real-world applicability.

The research includes four interconnected studies. Study I presents a systematic literature review of machine learning (ML) applications for voice-affecting disorders, identifying COPD as underrepresented in current research. Study II addresses this gap by collecting a new dataset of vowel [a:] recordings from Swedish-speaking COPD patients and healthy controls once a week in self-determined quiet settings. Voice features, including baseline acoustic (BLA) parameters and Mel-Frequency Cepstral Coefficients (MFCCs), were extracted and used to train three ML classifiers: CatBoost (CB), Random Forest (RF), and Support Vector Machine (SVM). CB demonstrated the highest test accuracy at 78%. 

Study III investigates the effects of signal segmentation on model performance and shows that certain temporal segments of voice recordings contain more informative patterns, enhancing classification outcomes by increasing accuracy to 85%. Study IV applies statistical and practical significance tests to compare voice features between COPD and healthy groups. A total of 34 features, including shimmer measures and higher-order MFCC derivatives, were found to meaningfully differentiate the groups. 

This thesis reframes the human voice as a source of clinically relevant data, demonstrating how it can be digitized, analyzed, and interpreted using ML to aid COPD assessment. The results indicate that voice-based analysis can provide an accessible, non-invasive, and scalable complement to existing diagnostic tools. By integrating technical, clinical, and ethical perspectives, the thesis contributes new knowledge and practical methodologies that align with AHT's goal of creating value-driven, user-centered healthcare solutions. The findings support future development of mobile and remote voice-based screening tools for COPD and other conditions.