Digital Stethoscopes in the Age of AI and Connected Medicine: Clinical Implications for Practice

Keywords

Digital stethoscope; Auscultation; Artificial intelligence; Telemedicine; Phonogram; Spectrogram; Cardiac diagnosis; Respiratory diagnosis; Medicine 3.0; Precision medicine.

Abstract

For over two centuries, the stethoscope has been a cornerstone of clinical medicine, yet traditional acoustic models are limited by environmental noise, user experience, and the subjective nature of auscultation. Digital stethoscopes, augmented by signal processing, visualization tools, and Artificial Intelligence (AI), represent a transformative evolution in auscultatory practice. These devices convert acoustic signals into digital data, enabling amplification, noise reduction, and objective analysis through phonograms and spectrograms. AI integration enhances diagnostic accuracy by detecting and classifying cardiac and respiratory abnormalities, while connectivity features facilitate telemedicine, remote monitoring, and longitudinal patient care. Clinical studies consistently demonstrate the superiority of digital over acoustic stethoscopes in detecting subtle heart murmurs, lung sounds, and arrhythmias, particularly in complex or noisy settings. Beyond clinical diagnostics, digital stethoscopes serve as educational tools, providing visualized, recordable, and analyzable auscultatory data. As part of the emerging Medicine 3.0 ecosystem, these devices align with predictive, preventive, personalized, participatory, and precision (5P) medicine, offering new opportunities for global health equity, chronic disease management, and medical education. This review synthesizes current evidence on the technology, clinical performance, AI applications, and telemedicine integration of digital stethoscopes, highlighting their potential to redefine auscultation in the 21st century.

Abstract

For over two centuries, the stethoscope has been a cornerstone of clinical medicine, yet traditional acoustic models are limited by environmental noise, user experience, and the subjective nature of auscultation. Digital stethoscopes, augmented by signal processing, visualization tools, and Artificial Intelligence (AI), represent a transformative evolution in auscultatory practice. These devices convert acoustic signals into digital data, enabling amplification, noise reduction, and objective analysis through phonograms and spectrograms. AI integration enhances diagnostic accuracy by detecting and classifying cardiac and respiratory abnormalities, while connectivity features facilitate telemedicine, remote monitoring, and longitudinal patient care. Clinical studies consistently demonstrate the superiority of digital over acoustic stethoscopes in detecting subtle heart murmurs, lung sounds, and arrhythmias, particularly in complex or noisy settings. Beyond clinical diagnostics, digital stethoscopes serve as educational tools, providing visualized, recordable, and analyzable auscultatory data. As part of the emerging Medicine 3.0 ecosystem, these devices align with predictive, preventive, personalized, participatory, and precision (5P) medicine, offering new opportunities for global health equity, chronic disease management, and medical education. This review synthesizes current evidence on the technology, clinical performance, AI applications, and telemedicine integration of digital stethoscopes, highlighting their potential to redefine auscultation in the 21st century.

Keywords

Digital stethoscope; Auscultation; Artificial intelligence; Telemedicine; Phonogram; Spectrogram; Cardiac diagnosis; Respiratory diagnosis; Medicine 3.0; Precision medicine.

Citation

Andrès E, El Hassani HA, Talha S, Lavigne T, Terrade JE et al. (2025) Digital Stethoscopes in the Age of AI and Connected Medicine: Clini cal Implications for Practice. SM J Pulm Med 7: 9.

INTRODUCTION

For over two centuries, the stethoscope has symbolized the essence of clinical medicine—a bridge between physician and patient, ear and heart, observation and intuition [1]. Introduced by René Laennec in 1816, the acoustic stethoscope was not merely a diagnostic tool but a transformation of clinical method, allowing physicians to “see” within the body through sound. Despite its iconic status, the acoustic stethoscope has remained largely unchanged while medicine has progressed into the digital age. Today, digital stethoscopes stand at the forefront of a technological revolution in auscultation [2]. By converting acoustic signals into digital data, providing visualization via phonograms and spectrograms, integrating Artificial Intelligence (AI) for automated analysis, and enabling telemedicine applications, these devices enhance diagnostic accuracy, reduce human error, and extend access to care across diverse settings. Beyond technical advancement, this evolution invites a rethinking of what it means to “listen” in modern medicine. This review aims to provide a comprehensive overview of digital stethoscopes, including their technological components, signal-processing capabilities, clinical performance compared with acoustic models, AI integration, telemedicine applications, and future directions in the era of connected, data-driven healthcare.

TERMINOLOGY AND DEVICE CLASSIFICATION

The terminology surrounding stethoscopes has evolved to reflect the expanding technological diversity of modern auscultatory devices [3].

Acoustic Stethoscopes

Remain the traditional standard. They consist of a chest piece—typically with a diaphragm and/or bell—connected to flexible tubing transmitting sound to earpieces. Operating purely on mechanical principles, they provide reliable auscultation without electronic amplification or signal processing, making them simple, robust, and widely accessible.

Electronic Stethoscopes

Introduce an initial layer of technology. A built-in microphone converts mechanical sound waves into electronic signals, which are amplified and filtered to improve audibility, particularly in noisy environments. While the output is still analog, internal digitization enhances clarity, reduces distortion, and facilitates sound storage. Additional features such as volume control and selective noise filtering make electronic stethoscopes particularly suitable for busy clinical settings.

Digital Stethoscopes

Represent a significant advance by converting sound into fully digital data via analog-to-digital converters (ADCs) [3]. This enables visualization of sounds through phonograms and spectrograms, long-term storage, advanced filtering, and wireless transmission for telemedicine. Digital models frequently incorporate noise reduction algorithms to enhance subtle cardiac or pulmonary sounds, supporting more precise detection of abnormalities.

Smart or AI-Enabled Stethoscopes

Integrate artificial intelligence algorithms, either embedded or cloud based, to assist clinicians in detecting and classifying pathological sounds, such as murmurs, wheezes, and crackles [3]. AI enhances diagnostic precision, reduces inter-observer variability, and can serve as a training tool for clinicians by providing feedback on auscultation technique.

Numerical Stethoscopes

Quantify auscultatory data, converting sounds into measurable metrics such as frequency, amplitude, and heart or respiratory rates [3,4]. When combined with AI, these devices offer objective, data-driven support for diagnosis, longitudinal monitoring, and chronic disease management. Although these categories overlap, distinguishing between them is essential for evaluating regulatory requirements, clinical performance, and application in patient care. As innovation continues, the boundaries between electronic, digital, and AI-enabled stethoscopes are increasingly blurred, redefining the practice of auscultation in modern medicine.

TECHNOLOGICAL OVERVIEW: FROM SOUND TO SIGNAL

Digital stethoscopes combine several advanced technological components to augment traditional auscultation, overcoming limitations inherent to acoustic devices [3,4]. Understanding these elements is essential to appreciating their clinical utility and diagnostic potential.

Transducers and Microphones

The transducer is the initial interface with the patient, housing microphones designed to capture a broader range of frequencies than conventional diaphragms. Some models integrate dual microphones optimized for low-frequency heart sounds (bell) and high-frequency lung sounds (diaphragm), electronically merging signals for comprehensive auscultation. Modern microphones minimize ambient noise while enhancing subtle physiological sounds.

Amplification and Filtering

Unlike acoustic stethoscopes, where sound intensity diminishes along the tubing, digital stethoscopes use electronic amplification to enhance volume. Clinicians can adjust sound levels to detect faint murmurs or subtle respiratory sounds. Digital signal processing (DSP) further applies frequency-specific filters—low, mid, and high—to isolate clinically relevant sounds, improving clarity in noisy environments or in patients with thick chest walls.

Analog-to-Digital Conversion (ADC)

Captured sounds are digitized using ADCs, typically with 16–24 bit resolution. The sampling rate and bit depth determine the fidelity of the digital signal, preserving subtle variations in heart and lung sounds [3 5]. High-resolution digitization ensures precise representation, enabling advanced analysis and storage.

Digital Signal Processing (DSP)

DSP algorithms enhance the digitized audio in real time, applying filtering, compression, and noise reduction. DSP also optimizes signals for storage, transmission, and visualization. Spectral analysis generates phonograms and spectrograms, providing graphical representations of sound amplitude and frequency over time [6,7]. These visualizations facilitate detection of abnormal patterns and support objective clinical assessment.

Data Storage and Connectivity

Many digital stethoscopes include onboard memory for storing auscultation recordings. Wireless connectivity via Bluetooth or Wi-Fi allows transmission to Electronic Health Records (EHRs), remote devices, or telemedicine platforms, enabling expert consultation without physical presence. Real-time streaming supports synchronous tele-auscultation, improving accessibility in remote or underserved areas.

Artificial Intelligence Integration

Advanced digital stethoscopes incorporate AI modules—either embedded or cloud-based—to assist in pattern recognition and diagnostic suggestions. AI algorithms can detect heart murmurs, wheezes, crackles, arrhythmias, and other pathological sounds, enhancing clinician accuracy, reducing inter-observer variability, and supporting training [4].

Power Source

Most devices rely on rechargeable lithium-ion batteries, offering several hours of continuous use. Battery life is a critical consideration to ensure reliable performance in clinical practice.

Comparative Advantages

Table 1 summarizes the differences between acoustic and digital stethoscopes, highlighting enhancements in sound amplification, frequency range, noise reduction, data storage, and connectivity [3,4]. These features collectively represent a transformative step forward in auscultatory medicine, enabling clinicians to combine auditory, visual, and data-driven approaches for improved patient care.

THE INFORMATIVE POWER OF SPECTROGRAMS AND PHONOGRAMS: LISTENING WITH THE EYES

The digitization of auscultatory sounds has enabled the creation of visual representations, providing objective, quantifiable data that complement traditional auditory assessment [4] (Figure 1). This innovation allows clinicians to “see” sounds, enhancing diagnostic precision, documentation, and education.

Phonograms

Phonograms graphically display sound amplitude over time, with the x-axis representing time and the y-axis showing sound intensity. These representations allow detailed analysis of timing, duration, and intensity of heart and respiratory sounds [7]. For instance, the crescendo decrescendo pattern of an aortic stenosis murmur or the flat holosystolic profile of mitral regurgitation can be clearly visualized. Phonograms also facilitate differentiation of normal heart sounds (S1, S2) from abnormal sounds such as S3, S4, clicks, and snaps. This visual documentation improves communication among healthcare providers and enhances clinical decision-making (Figure 1).

Figure 1: Educational visualization of cardiac sounds as a cardio-phonogram and cardio-spectrogram. Legand: Left: image generated by artificial intelligence. Right: image from auscultation of a patient with aortic stenosis - the latter is indicated by a white arrow during a cardiac cycle materialized by B1-B2 (personal data; ASAP project).

Table 1: Comparison between Acoustic and Digital stethoscopes.

facilitate differentiation of normal heart sounds (S1, S2) from abnormal sounds such as S3, S4, clicks, and snaps. This visual documentation improves communication among healthcare providers and enhances clinical decision-making (Figure 1).

Spectrograms

Spectrograms provide frequency-based visualizations, with the x-axis as time, the y-axis as frequency (Hz), and color intensity representing amplitude. This allows clinicians to analyze harmonic content and energy distribution across frequencies, which is invaluable in distinguishing sounds with similar temporal patterns but differing frequency profiles. For example, spectrograms can help differentiate wheezes from crackles or classify various cardiac murmurs by their unique frequency signatures [7] (Figure 1).

Clinical Utility

Visual representations enable longitudinal monitoring of disease progression, response to treatment, and objective evaluation of interventions [4]. They also serve as powerful educational tools, allowing medical students and trainees to learn auscultation with visual feedback, improving pattern recognition and diagnostic accuracy.

Telemedicine Integration

Phonograms and spectrograms can be transmitted remotely for expert review, facilitating tele-auscultation and collaborative diagnosis. This is particularly valuable in resource-limited settings or for patients in rural areas where access to specialists is limited.

Evidence

Recent studies indicate that incorporating visual representations of heart and lung sounds improves inter-observer agreement in murmur classification and supports remote education and training [7]. By combining auditory and visual information, clinicians gain a more precise and reproducible understanding of auscultatory findings. In summary, phonograms and spectrograms transform auscultation from a purely auditory skill into a multimodal, data-driven process, enhancing diagnostic accuracy, clinical education, and remote healthcare capabilities.

THE AUGMENTING ROLE OF ARTIFICIAL INTELLIGENCE IN AUSCULTATION

The integration of Artificial Intelligence (AI) into digital stethoscopes is transforming auscultation by enabling automated analysis of cardiac and pulmonary sounds, enhancing both accuracy and efficiency in clinical practice [3,4]. AI acts as an augmentative “second ear,” supporting clinicians in detecting subtle or complex abnormalities that may be challenging to identify with conventional auscultation.

Table 2: Overview of Commercial Digital Stethoscopes in USA and Europe

Automated Detection of Cardiac Abnormalities

AI algorithms trained on extensive datasets of normal and pathological heart sounds can detect murmurs, arrhythmias, atrial fibrillation, and valvular heart diseases with high precision [3,4]. These algorithms analyze timing, amplitude, and spectral patterns, providing real-time alerts for subtle anomalies that may otherwise go unnoticed, particularly in early-stage disease or noisy clinical environments.

Automated Analysis of Respiratory Sounds

AI also enhances the identification of abnormal lung sounds, including wheezes, crackles, and pleural rubs, associated with conditions such as pneumonia, COPD, asthma, and pleural effusions [3,4]. Automated analysis supports early detection, continuous monitoring, and timely intervention, improving patient outcomes.

Risk Stratification and Prognosis: Advanced AI models can predict the risk of future cardiac events by analyzing nuanced acoustic features. This predictive capability enables early intervention and personalized treatment planning, shifting auscultation from reactive diagnosis to proactive risk management [3,4].

Reducing Inter-Observer Variability

By providing objective, data-driven analysis, AI reduces inter observer variability in auscultation, particularly benefiting less experienced clinicians. Studies have shown that AI-assisted stethoscopes improve diagnostic confidence and consistency, facilitating standardized clinical assessments across diverse healthcare settings [3,4].

Big Data Integration

Digital auscultation generates large volumes of structured and semi-structured data, including phonocardiograms, spectrograms, and respiratory cycles. AI can aggregate and analyze these data across populations, identifying longitudinal patterns and subtle abnormalities that may be imperceptible to the human ear [3,4,7]. Machine learning models, including convolutional and recurrent neural networks, have demonstrated remarkable accuracy in classifying heart murmurs, detecting atrial fibrillation, and distinguishing between different lung sounds.

Evidence

A 2023 multicenter study analyzed over 1.2 million auscultation recordings and found that a deep learning model outperformed general practitioners in detecting pathological murmurs (AUC 0.93 vs. 0.79), highlighting the potential of AI to enhance diagnostic precision and clinical decision-making [8].

Clinical Considerations

While AI significantly augments auscultation, it should complement, not replace, clinical judgment. Results must be interpreted within the broader clinical context, integrating patient history, physical examination, and additional diagnostic tests. In conclusion, AI-powered digital stethoscopes represent a paradigm shift in clinical auscultation, offering improved detection, risk stratification, and standardization, while supporting telemedicine, longitudinal monitoring, and evidence-based decision-making.

MARKET OVERVIEW AND MODELS OF DIGITAL STETHOSCOPES

The market for digital stethoscopes has expanded rapidly, driven by advances in sound amplification, signal processing, connectivity, and AI integration (4). Modern devices are designed to meet diverse clinical needs, from routine auscultation to specialized cardiology and pulmonology assessments, and increasingly support telemedicine applications. 

Key Features and Functionalities

Digital stethoscopes differentiate themselves from traditional acoustic models through several capabilities: Sound Amplification: Enhances low-intensity cardiac and pulmonary sounds, improving detection of subtle murmurs or faint respiratory noises. Noise Reduction: Active filtering isolates clinically relevant sounds from ambient noise, particularly valuable in emergency departments, ICUs, or outpatient settings. Connectivity: Wireless options such as Bluetooth and Wi-Fi enable seamless integration with mobile devices, telemedicine platforms, and electronic health records (EHRs). Data Storage and Sharing: Onboard memory allows storage of auscultation recordings for longitudinal monitoring, review, or expert consultation. AI-Driven Diagnostics: Certain models include embedded or cloud based AI algorithms for real-time detection and classification of heart and lung sounds, including murmurs, arrhythmias, wheezes, and crackles.

Representative Models in the USA and Europe (including France)

A variety of commercial devices now provide combinations of the above features: Littmann 3200: Wireless transmission, sound amplification, and digital storage, widely used in cardiology and general practice. Thinklabs One: Compact design with high-fidelity amplification and recording capabilities, suitable for pediatrics. Eko Core: Integrates AI-assisted murmur detection and ECG functionality, bridging auscultation with cardiac monitoring. Stemoscope: Consumer-friendly design with Bluetooth connectivity for telemedicine, supporting remote auscultation and patient engagement.

Clinical Applications

These devices have demonstrated utility in improving auscultation in noisy environments, enhancing diagnostic accuracy, supporting teleconsultations, and providing training opportunities for medical students and residents. As connectivity and AI capabilities expand, digital stethoscopes are increasingly becoming essential tools for both clinical practice and telehealth workflows [4]. 

Considerations for Clinicians

Selection of a digital stethoscope should be guided by clinical needs, including patient population (adult, pediatric), frequency of remote consultations, AI diagnostic support, battery life, and device ergonomics. While devices differ in features, all provide enhanced capabilities compared to acoustic stethoscopes, particularly in precision, documentation, and telemedicine integration. The evolving market reflects the growing role of digital stethoscopes as central components of modern, connected healthcare. By combining traditional auscultation with amplification, visualization, AI support, and telemedicine integration, these devices offer a comprehensive approach to cardiac and pulmonary assessment, redefining the clinical experience of listening to the human body (Table 3 and Table 4).

RESULTS OF STUDIES COMPARING ACOUSTIC AND DIGITAL STETHOSCOPES

A growing body of evidence has evaluated the comparative performance of digital versus traditional acoustic stethoscopes, highlighting the clinical advantages of digital devices in diverse settings.

Superior Detection of Low-Intensity Sounds

Digital stethoscopes with amplification capabilities significantly improve the detection of faint heart murmurs (grade 1–2) and subtle respiratory sounds [3,4]. This benefit is particularly evident in noisy environments or in patients with thick chest walls, where acoustic stethoscopes may fail to capture low-intensity signals.

Enhanced Diagnostic Accuracy through Visualization

Devices equipped with phonogram and spectrogram visualization allow clinicians to objectively characterize heart and lung sounds [7]. Visual representations assist in distinguishing S1–S2 from S3–S4, murmurs, clicks, and abnormal respiratory sounds, enhancing diagnostic precision, especially for less experienced practitioners.

AI-Assisted Screening and Diagnosis

AI algorithms integrated into digital stethoscopes have shown high sensitivity and specificity in detecting conditions such as atrial fibrillation, heart murmurs, and pulmonary abnormalities [3,8]. These algorithms act as a “second ear,” alerting clinicians to subtle abnormalities that may be overlooked in routine auscultation.

CONCLUSION

Digital stethoscopes represent a transformative evolution in auscultatory medicine, bridging the gap between traditional clinical  practice and the digital era. Equipped with real-time sound amplification, visual analysis through phonograms and spectrograms, AI-driven diagnostic support, and seamless integration into telehealth platforms, these devices significantly enhance clinicians’ ability to detect, document, and monitor a wide range of cardiac and respiratory conditions.

Clinical studies consistently demonstrate that digital stethoscopes outperform traditional acoustic models in sensitivity, specificity, and diagnostic confidence, particularly in challenging or noisy clinical environments. Features such as active noise reduction, visual sound representation, and AI-assisted interpretation improve diagnostic accuracy, clinician confidence, and inter-observer consistency. Beyond individual clinical encounters, digital stethoscopes facilitate remote care and telemedicine, supporting decentralized healthcare delivery. By enabling high-quality auscultation in underserved or geographically isolated areas, they contribute to improved access, equity, and quality of care. As integral components of Medicine 3.0, these devices function as nodes within a broader ecosystem of real-time monitoring, AI-assisted analysis, and personalized healthcare. Looking ahead, the convergence of AI, wearable technologies, and cloud computing will further expand the predictive and preventive capabilities of digital stethoscopes. They hold the potential to improve global health equity, enhance medical education, and support continuous monitoring, making them indispensable tools for future healthcare professionals. While challenges such as cost, training, and integration remain, the continued refinement and adoption of digital auscultation tools will play a pivotal role in shaping next-generation, patient-centered care.

CONFLICTS OF INTEREST

No conflicts directly related to the content of this text. Professor E. ANDRES has conducted fundamental and clinical research under institutional contracts with Alcatel-Lucent and the French National Technology Agency. 

Figure 2: Digital Stethoscopes: Transforming Auscultation Through AI-Enhanced Precision. Legand: A modern digital stethoscope capturing and analyzing heart and lung sounds through advanced signal processing and AI algorithms. Visualizations such as phonograms and spectrograms highlight how digital auscultation improves diagnostic accuracy, supports telemedicine, and enhances medical education within the Medicine 3.0 ecosystem.

REFERENCES

1. Tavel ME. (2006). Cardiac auscultation: A glorious past—and it does have a future! Circulation. 113: 1255-1259.
2. Lin T, Kline J, Rehman M, Patel A. (2021). Pulmonary auscultation using digital tools in interstitial lung disease. Chest. 160: 1243-1250.
3. Zhao Y, Sun Z, Zhang H, Liu Y, Hu B. (2023). Diagnostic performance of digital stethoscopes: A systematic review and meta-analysis. BMJ Digit Health. 1: e000021.
4. Andrès E, Gass R, Brandt C. (2015). State of the art on electronic stethoscopes in 2015. Médecine Thérapeutique. 21: 319-332.
5. He J, Baxter SL, Xu J, Zhou X, Zhang K. (2019). The practical implementation of artificial intelligence technologies in medicine. Nat Med. 25: 30-36.
6. Price L. (2024). Medicine 3.0: Prevention, Personalisation and Participation as a proposed future of medicine. Rama On Healthcare.
7. Chang A, Koutsiana E. (2022). Spectrograms in cardiac murmur identification: Educational utility and diagnostic accuracy. Heart. 108: 1354-1360.
8. Prince J, Maidens J, Kieu S, Ma M, Baca-Motes K, et al. (2023). Deep learning algorithms to detect murmurs associated with structural heart disease. J Am Heart Assoc. 12: e030377.
9. McLane D, Gakuba C, Little B, Bernhardt J. (2021). Tele-auscultation during COVID-19: Feasibility and diagnostic accuracy in low- resource settings. Telemed J E Health. 27: 1347-1353.
10. Williams K, Stewart R, et al. (2019). Comparison of acoustic and digital stethoscopes in diagnosing heart sounds. J Clin Med. 8: 45.
11. Thompson J, Rojas M, et al. (2020). A comparison of digital and acoustic stethoscopes in detecting pulmonary sounds. Respir Care J. 65: 392-398.
12. Patel A, Lee D, et al. (2021). Impact of digital stethoscopes on diagnostic performance in cardiovascular examination. J Cardiovasc Med. 22: 556-563.
13. Harris S, Smith P, et al. (2022). Comparing acoustic and digital stethoscopes for clinical use in pediatrics. Pediatr Res J. 78: 543-550.
14. Park C, Johnson S, et al. (2023). Acoustic vs. digital stethoscopes inemergency medicine: A comparative study. J Emerg Med.
15. Rayan D, Rochoy M, Caron C, Duhamel A, Gautier S. (2023). Evaluation of a connected digital stethoscope for cardiac auscultation in teleconsultation: A randomized controlled trial. J Telemed Telecare. 29: 37-44.
16. Faust O, Hagiwara Y, Hong TJ, Lih OS, Acharya UR. (2018). Deep learning for healthcare applications based on physiological signals: A review. Comput Methods Programs Biomed. 161: 1-13.
17. Chen S, Wang D, Wu J, Xu B. (2023). A deep learning algorithm for automated cardiac murmur detection via a digital stethoscope platform: Validation study. JMIR Med Inform. 11: e09905.
18. Hassan U, Anwar M, Mahmood N, et al. (2022). Artificial intelligence- based auscultation using digital stethoscope in a resource-limited setting: Validation study. BMJ Innov. 8: 180-187.
19. Hollander JE, Carr BG. (2020). Virtually perfect? Telemedicine for Covid-19. N Engl J Med. 2020;382(18):1679-1681.
20. Ding Z, Wang Z, et al. (2021). Evaluation of digital stethoscopes intelemedicine: A systematic review. Telemed J E Health. 27: 463-474.
21. Yigit G, Ozer M, et al. (2021). Use of digital stethoscopes for teleconsultation in cardiovascular diagnosis: An investigation into diagnostic accuracy. J Telemed Telecare. 27: 153-160.
22. Lindgren F, Linder P, et al. Telemedicine and remote monitoring in chronic respiratory diseases: Exploring the use of digital stethoscopes in telehealth settings. Respir Med. 176: 106209.
23. Boulis M, Kalogeropoulos AP, et al. Digital stethoscopes in teleexpertise: A novel tool for remote cardiology consultations. Eur J Telemed. 28: 125-132.
24. Murray A, Ruiz de la Cruz M, et al. (2022). The role of digital stethoscopes in remote health monitoring and telemedicine. J Telemed Telecare. 28: 380-387.
25. Topol EJ. (2015). The Patient Will See You Now: The Future ofMedicine is in Your Hands. New York: Basic Books.
26. Hood L, Friend SH. (2011). Predictive, personalized, preventive, participatory (P4) cancer medicine. Nat Rev Clin Oncol. 8: 184-187.
27. Johnson AEW, Ghassemi MM, Nemati S, Niehaus KE, Clifton DA, et al. (2016). Machine learning and decision support in critical care. Proc IEEE. 104: 444-466.

Citation

Andrès E, El Hassani HA, Talha S, Lavigne T, Terrade JE et al. (2025) Digital Stethoscopes in the Age of AI and Connected Medicine: Clini cal Implications for Practice. SM J Pulm Med 7: 9.