Is Speech the New Blood? Recent Progress in AI-Based Disease Detection From Audio in a Nutshell

Abstract

In recent years, advancements in the field of artificial intelligence (AI) have impacted several areas of research and application. Besides more prominent examples like self-driving cars or media consumption algorithms, AI-based systems have further started to gain more and more popularity in the health care sector, however whilst being restrained by high requirements for accuracy, robustness, and explainability. Health-oriented AI research as a sub-field of digital health investigates a plethora of human-centered modalities. In this article, we address recent advances in the so far understudied but highly promising audio domain with a particular focus on speech data and present corresponding state-of-the-art technologies. Moreover, we give an excerpt of recent studies on the automatic audio-based detection of diseases ranging from acute and chronic respiratory diseases via psychiatric disorders to developmental disorders and neurodegenerative disorders. Our selection of presented literature shows that the recent success of deep learning methods in other fields of AI also more and more translates to the field of digital health, albeit expert-designed feature extractors and classical ML methodologies are still prominently used. Limiting factors, especially for speech-based disease detection systems, are related to the amount and diversity of available data, e. g., the number of patients and healthy controls as well as the underlying distribution of age, languages, and cultures. Finally, we contextualize and outline application scenarios of speech-based disease detection systems as supportive tools for health-care professionals under ethical consideration of privacy protection and faulty prediction.

Discriminating between sick and healthy faces based on early sickness cues: an exploratory analysis of sex differences

“…Besides, in our identification task, participants could base their decision through only one sensory cue. Hence, it still remains plausible that the sex difference may change—that is be greater or smaller—when individuals have the possibility of integrating sickness cues from different sensory modalities, such as body odors [ 11 , 13 , 20 ], voice [ 41 ] or gait [ 14 ]. In line with this, identification of sickness has been more accurate when visual and olfactory cues are presented simultaneously [ 12 , 13 ].…”

Einsatz KI-gestützter Diagnostik von Sprach- und Sprechstörungen bei neurodegenerativen Erkrankungen

“…Wie erwähnt, nimmt die Sprachanalyse, insbesondere bei der Früherkennung, zunehmend an Bedeutung zu und wird treffenderweise auch als das "neue Blut" bezeichnet [24]. Darüber hinaus rücken KI-basierte Ansätze immer mehr in den Fokus der symptomatischen Therapie von neurodegenerativen Erkrankungen, für die es keine kurativen Behandlungsformen gibt.…”

Artificial Intelligence-Based Voice Assessment of Patients with Parkinson’s Disease Off and On Treatment: Machine vs. Deep-Learning Comparison

“…The worldwide diffusion of 6.5 billion of smartphones (owned by about 83% of the population) [ 6 ], with over 11 billion devices connected to the Web including wearables [ 7 ], has allowed for health monitoring from anywhere and at any time [ 8 ].…”