Computer-aided auscultation

Last updated
Computer-aided auscultation
Synonyms Computerized assisted auscultation
Test ofauscultation via computer assistance

Computer-aided auscultation (CAA), or computerized assisted auscultation, is a digital form of auscultation. It includes the recording, visualization, storage, analysis and sharing of digital recordings of heart or lung sounds. The recordings are obtained using an electronic stethoscope or similarly suitable recording device. Computer-aided auscultation is designed to assist health care professionals who perform auscultation as part of their diagnostic process. Commercial CAA products are usually classified as clinical decision support systems that support medical professionals in making a diagnosis. As such they are medical devices and require certification or approval from a competent authority (e.g. FDA approval, CE conformity issued by notified body).

Contents

Benefits of CAA

Compared to traditional auscultation, computer-aided auscultation (CAA) offers a range of improvements beneficial to multiple stakeholders:

Functional principle

In a CAA system, sounds are recorded through an electronic stethoscope. The audio data is transferred to an electronic device via Bluetooth or an audio cable connection. Special software on that device visualizes, stores and analyzes the data. With some of the more sophisticated CAA systems, the CAA analysis yields results that can be used to objectify diagnoses (decision support system).[ citation needed ]

Components in a CAA system

The components of a CAA system depend on its complexity. Whereas some of the simpler systems provide only visualization or storage options, other systems combine visualization, storage, analysis and the ability to electronically manage said data.

Electronic stethoscope

Electronic stethoscopes (also digital stethoscopes) convert acoustic sound waves into digital electrical signals. These signals are then amplified by means of transducers and currently reach levels up to 100 times higher than traditional acoustic stethoscopes. Additionally, electronic stethoscopes can be used to filter out background noise, a feature that can be safety-relevant and facilitate more accurate diagnoses. Whereas sound amplification and filtering are the main functions of an electronic stethoscope, the ability to access the sounds through external means via Bluetooth or audio cables makes them an ideal sound-capturing device for CAA systems.[ citation needed ]

Device running graphical user interface

Devices that can be used to connect to an electronic stethoscope and record the audio signal (e.g. heart or lung sounds) include PC, laptop and mobile devices like smartphones or tablets. Generally, CAA systems include software that can visualize the incoming audio signal. More sophisticated CAA systems include live noise detection algorithms, designed to help the user achieve the best possible recording quality.

Graphical user interface of the eMurmur CAA system showing the incoming signal in real time. This CAA system includes live noise detection algorithms that ensure that the recorded signal is of sufficient quality. EMurmur-recording-screen.jpg
Graphical user interface of the eMurmur CAA system showing the incoming signal in real time. This CAA system includes live noise detection algorithms that ensure that the recorded signal is of sufficient quality.

Analysis software

A key feature of CAA systems is the automated analysis of the recorded audio signals by signal processing algorithms. Such algorithms can run directly on the device used for making the recording, or be hosted in a cloud connected to the device. The degree of autonomy of currently available analysis algorithms varies greatly. While some systems operate fully autonomously, [7] early PC-based systems required significant user interaction and interpretation of results, [8] and other analysis systems require some degree of assistance by the user like manual confirmation/correction of estimated heart rates. [9]

The mobile device based result screen of the eMurmur CAA system, showing the AHA classification, murmur analysis results (no murmur, innocent or pathologic murmur, additional descriptive data), heart rate, and playback option of the recordings. EMurmur-screen.jpg
The mobile device based result screen of the eMurmur CAA system, showing the AHA classification, murmur analysis results (no murmur, innocent or pathologic murmur, additional descriptive data), heart rate, and playback option of the recordings.
The laptop based SensiCardiac CAA software program, showing the recorded heart sounds and ECG signal, as well as the analysis results. Sensi-Screen.jpg
The laptop based SensiCardiac CAA software program, showing the recorded heart sounds and ECG signal, as well as the analysis results.

Storage of auscultation based data

Recorded sounds and associated analytical and patient data can be electronically stored, managed or archived. Patient identifying information might be handled or stored in the process. If the stored data classifies as PHI (protected health information), a system hosting such data must be compliant with country-specific data protection laws like HIPAA for the US or the Data Protection Directive for the EU. Storage options for current CAA systems range from the basic ability to retrieve a downloadable PDF report to a comprehensive cloud-based interface for electronic management of all auscultation-based data.[ citation needed ]

Cloud-based user interface

The user can review all their patient records (including replaying the audio files) via a user interface, e.g. via a web-portal in the browser or stand-alone software on the electronic device. Other functionalities include sharing records with other users, exporting patient records and integration into EHR systems.

CAA of the heart

Computer-aided auscultation aimed at detecting and characterizing heart murmurs is called computer-aided heart auscultation (also known as automatic heart sound analysis).

Motivation

Auscultation of the heart using a stethoscope is the standard examination method worldwide to screen for heart defects by identifying murmurs. It requires that an examining physician have acute hearing and extensive experience. An accurate diagnosis remains challenging for various reasons including noise, high heart rates, and the ability to distinguish innocent from pathological murmurs. Properly performed, the auscultatory examination of the heart is commonly regarded as an inexpensive, widely available tool in the detection and management of heart disease. [10] The auscultation skills of physicians, however, have been reported to be declining. [11] [12] [13] [14] [15] [16] [17] This leads to missed disease diagnoses and/or excessive costs for unnecessary and expensive diagnostic testing. A study suggests that more than one third of previously undiagnosed congenital heart defects in newborns are missed by their 6-week examination. [18] More than 60% of referrals to medical specialists for costly echocardiography are due to a misdiagnosis of an innocent murmur. [14] CAA of the heart thus has the potential to become a cost-effective screening and diagnostic tool, provided that its underlying algorithms have been clinical tested in stringent, blinded fashions for their ability to detect the difference between normal and abnormal heart sounds.

Heart murmurs and CAA

Heart murmurs (or cardiac murmurs) are audible noises through a stethoscope, generated by a turbulent flow of blood. Heart murmurs need to be distinguished from heart sounds which are primarily generated by the beating heart and the heart valves snapping open and shut. Generally, heart murmurs are classified as innocent (also called physiological or functional) or pathological (abnormal). Innocent murmurs are usually harmless, often caused by physiological conditions outside the heart, and the result of certain benign structural defects. Pathological murmurs are most often associated with heart valve problems but may also be caused by a wide array of structural heart defects. Various characteristics constitute a qualitative description of heart murmurs, including timing (systolic murmur and diastolic murmur), shape, location, radiation, intensity, pitch and quality. CAA systems typically categorize heart sounds and murmurs as Class I and Class III according to the American Heart Association: [19]

More sophisticated CAA systems provide additional descriptive murmur information like murmur timing, grading, or the ability to identify the positions of the S1/S2 heart sounds.

Heart sound analysis

The detection of heart murmurs in CAA systems is based on the analysis of digitally recorded heart sounds. Most approaches use the following four stages:

  1. Heart rate detection: In the first stage, the heart rate is determined based on the audio signal of the heart. It is a crucial step for the following stages and high accuracy is required. Automated heart rate determination based on acoustic recordings is challenging because the heart rate can range from 40-200bpm, noise and murmurs can camouflage the peaks of the heart sounds (S1 and S2), and irregular heartbeats can disturb the quasi-periodic nature of the heartbeat.
  2. Heart sound segmentation: After the heart rate has been detected, the two main phases of the heartbeat (systole and diastole) are identified. This differentiation is important since most murmurs occur in specific phases during the heartbeat. External noise from the environment or internal noise from the patient (e.g. breathing) make heart sound segmentation challenging.
  3. Feature extraction: Having identified the phases of the heartbeat, information (features) from the heart sound is extracted that enters a further classification stage. Features can range from simple energy-based approaches to higher-order multi-dimensional quantities.
  4. Feature classification: During classification, the features extracted in the previous stage are used to classify the signal and assess the presence and type of a murmur. The main challenge is to differentiate no-murmur recordings from low-grade innocent murmurs, and innocent murmurs from pathological murmurs. Usually machine-learning approaches are applied to construct a classifier based on training data.

Clinical evidence of CAA systems

The most common types of performance measures for CAA systems are based on two approaches: retrospective (non-blinded) studies using existing data and prospective blinded clinical studies on new patients. In retrospective CAA studies, a classifier is trained with machine learning algorithms using existing data. The performance of the classifier is then assessed using the same data. Different approaches are used to do this (e.g., k-Fold cross-validation, leave-one-out cross-validation). The main shortcoming of judging the quality (sensitivity, specificity) of a CAA system based on retrospective performance data alone comes from the risk that the approaches used can overestimate the true performance of a given system. Using the same data for training and validation can itself lead to significant overfitting of the validation set, because most classifiers can be designed to analyse known data very well, but might not be general enough to correctly classify unknown data; i.e. the results look much better than they would if tested on new, unseen patients. “The true performance of a selected network (CAA system) should be confirmed by measuring its performance on a third independent set of data called a test set”. [20] In summary, the reliability of retrospective, non-blinded studies are usually considered to be much lower than that of prospective clinical studies because they are prone to selection bias and retrospective bias. Published examples include Pretorius et al. [21] Prospective clinical studies, on the other hand, are better suited to assess the true performance of a CAA system (provided that the study is blinded and well controlled). In a prospective clinical study to evaluate the performance of a CAA system, the output of the CAA system is compared to the gold standard diagnoses. In the case of heart murmurs, a suitable gold standard diagnosis would be auscultation-based expert physician diagnosis, stratified by an echocardiogram-based diagnosis. Published examples include Lai et al. [1]

See also

Related Research Articles

The diagnostic tests in cardiology are methods of identifying heart conditions associated with healthy vs. unhealthy, pathologic heart function.

<span class="mw-page-title-main">René Laennec</span> French physician (1781–1826)

René-Théophile-Hyacinthe Laennec was a French physician and musician. His skill at carving his own wooden flutes led him to invent the stethoscope in 1816, while working at the Hôpital Necker. He pioneered its use in diagnosing various chest conditions. He became a lecturer at the Collège de France in 1822 and professor of medicine in 1823. His final appointments were that of head of the medical clinic at the Hôpital de la Charité and professor at the Collège de France. He went into a coma and subsequently died of tuberculosis on August 13, 1826, at age 45.

<span class="mw-page-title-main">Stethoscope</span> Medical device for auscultation

The stethoscope is a medical device for auscultation, or listening to internal sounds of an animal or human body. It typically has a small disc-shaped resonator that is placed against the skin, with either one or two tubes connected to two earpieces. A stethoscope can be used to listen to the sounds made by the heart, lungs or intestines, as well as blood flow in arteries and veins. In combination with a manual sphygmomanometer, it is commonly used when measuring blood pressure.

In medicine, the pulse is the rhythmic throbbing of each artery in response to the cardiac cycle (heartbeat). The pulse may be palpated in any place that allows an artery to be compressed near the surface of the body, such as at the neck, wrist, at the groin, behind the knee, near the ankle joint, and on foot. The pulse is most commonly measured at the wrist or neck. A sphygmograph is an instrument for measuring the pulse.

<span class="mw-page-title-main">Heart sounds</span> Noise generated by the beating heart

Heart sounds are the noises generated by the beating heart and the resultant flow of blood through it. Specifically, the sounds reflect the turbulence created when the heart valves snap shut. In cardiac auscultation, an examiner may use a stethoscope to listen for these unique and distinct sounds that provide important auditory data regarding the condition of the heart.

<span class="mw-page-title-main">Heart murmur</span> Medical condition

Heart murmurs are unique heart sounds produced when blood flows across a heart valve or blood vessel. This occurs when turbulent blood flow creates a sound loud enough to hear with a stethoscope. The sound differs from normal heart sounds by their characteristics. For example, heart murmurs may have a distinct pitch, duration and timing. The major way health care providers examine the heart on physical exam is heart auscultation; another clinical technique is palpation, which can detect by touch when such turbulence causes the vibrations called cardiac thrill. A murmur is a sign found during the cardiac exam. Murmurs are of various types and are important in the detection of cardiac and valvular pathologies.

A sphygmomanometer, also known as a blood pressure monitor, or blood pressure gauge, is a device used to measure blood pressure, composed of an inflatable cuff to collapse and then release the artery under the cuff in a controlled manner, and a mercury or aneroid manometer to measure the pressure. Manual sphygmomanometers are used with a stethoscope when using the auscultatory technique.

<span class="mw-page-title-main">Palpitations</span> Perceived cardiac abnormality in which ones heartbeat can be felt

Palpitations are perceived abnormalities of the heartbeat characterized by awareness of cardiac muscle contractions in the chest, which is further characterized by the hard, fast and/or irregular beatings of the heart.

<span class="mw-page-title-main">Mitral valve prolapse</span> Medical condition

Mitral valve prolapse (MVP) is a valvular heart disease characterized by the displacement of an abnormally thickened mitral valve leaflet into the left atrium during systole. It is the primary form of myxomatous degeneration of the valve. There are various types of MVP, broadly classified as classic and nonclassic. In severe cases of classic MVP, complications include mitral regurgitation, infective endocarditis, congestive heart failure, and, in rare circumstances, cardiac arrest.

<span class="mw-page-title-main">Holter monitor</span> Portable device for cardiac monitoring

In medicine, a Holter monitor is a type of ambulatory electrocardiography device, a portable device for cardiac monitoring for at least 24 hours.

<span class="mw-page-title-main">Auscultation</span> Listening to the internal sounds of the body, usually using a stethoscope

Auscultation is listening to the internal sounds of the body, usually using a stethoscope. Auscultation is performed for the purposes of examining the circulatory and respiratory systems, as well as the alimentary canal.

<span class="mw-page-title-main">Ventricular septal defect</span> Medical condition

A ventricular septal defect (VSD) is a defect in the ventricular septum, the wall dividing the left and right ventricles of the heart. The extent of the opening may vary from pin size to complete absence of the ventricular septum, creating one common ventricle. The ventricular septum consists of an inferior muscular and superior membranous portion and is extensively innervated with conducting cardiomyocytes.

<span class="mw-page-title-main">Right ventricular hypertrophy</span> Medical condition

Right ventricular hypertrophy (RVH) is a condition defined by an abnormal enlargement of the cardiac muscle surrounding the right ventricle. The right ventricle is one of the four chambers of the heart. It is located towards the right lower chamber of the heart and it receives deoxygenated blood from the right upper chamber and pumps blood into the lungs.

Still's murmur is a common type of benign or "innocent" functional heart murmur that is not associated with any sort of cardiac disorder or any other medical condition. It can occur at any age although it is most common among children two to seven years of age and it is rare in adulthood.

<span class="mw-page-title-main">Doppler fetal monitor</span>

A Doppler fetal monitor, informally known as sonicaid, is a hand-held ultrasound transducer used to detect the fetal heartbeat for prenatal care. It uses the Doppler effect to provide an audible simulation of the heart beat. Some models also display the heart rate in beats per minute (BPM). Use of this monitor is sometimes known as Doppler auscultation. The Doppler fetal monitor is commonly referred to simply as a Doppler or fetal Doppler. It may be classified as a form of Doppler ultrasonography.

<span class="mw-page-title-main">Phonocardiogram</span>

A phonocardiogram is a plot of high-fidelity recording of the sounds and murmurs made by the heart with the help of the machine called the phonocardiograph; thus, phonocardiography is the recording of all the sounds made by the heart during a cardiac cycle.

<span class="mw-page-title-main">Arrhythmia</span> Group of medical conditions characterized by irregular heartbeat

Arrhythmias, also known as cardiac arrhythmias, are irregularities in the heartbeat, including when it is too fast or too slow. A resting heart rate that is too fast – above 100 beats per minute in adults – is called tachycardia, and a resting heart rate that is too slow – below 60 beats per minute – is called bradycardia. Some types of arrhythmias have no symptoms. Symptoms, when present, may include palpitations or feeling a pause between heartbeats. In more serious cases, there may be lightheadedness, passing out, shortness of breath, chest pain, or decreased level of consciousness. While most cases of arrhythmia are not serious, some predispose a person to complications such as stroke or heart failure. Others may result in sudden death.

The cardiovascular examination is a portion of the physical examination that involves evaluation of the cardiovascular system. The exact contents of the examination will vary depending on the presenting complaint but a complete examination will involve the heart, lungs, belly and the blood vessels.

<span class="mw-page-title-main">Harvey mannequin</span> Medical simulator

Harvey was one of the earliest medical simulators available for training of health care professionals. Harvey was created in 1968 by Dr. Michael S. Gordon at the University of Miami. Harvey is currently sold by the Laerdal Corporation.

In cardiac physiology, the Levine grading scale is a numeric scoring system to characterize the intensity or the loudness of a heart murmur. The eponym is from researcher Samuel A. Levine who studied the significance of systolic heart murmurs. The grading gives a number to the intensity from 1 to 6: The palpable murmur is known as thrill, which can be felt on grade 4 or higher.

  1. The murmur is only audible on listening carefully for some time.
  2. The murmur is faint but immediately audible on placing the stethoscope on the chest.
  3. A loud murmur readily audible but with no thrill.
  4. A loud murmur with a thrill.
  5. A loud murmur with a thrill. The murmur is so loud that it is audible with only the rim of the stethoscope touching the chest.
  6. A loud murmur with a thrill. The murmur is audible with the stethoscope not touching the chest but lifted just off it.

References

  1. 1 2 Lai, Lillian; Andrew N. Redington; Andreas J. Reinisch; Michael J. Unterberger; Andreas J. Schriefl (2016). "Computerized Automatic Diagnosis of Innocent and Pathologic Murmurs in Pediatrics: A Pilot Study". Congenital Heart Disease. 11 (5): 386–395. doi:10.1111/chd.12328. PMID   26990211. S2CID   20921069.
  2. ↑ Vaidyanathan, B; Sathish G; Mohanan ST; Sundaram KR; Warrier KK; Kumar RK (2011). "Clinical screening for Congenital heart disease at birth: a prospective study in a community hospital in Kerala". Indian Pediatrics. 48 (1): 25–30. doi:10.1007/s13312-011-0021-1. PMID   20972295. S2CID   10788521.
  3. ↑ Zühlke, Z; Myer L; Mayosi BM (2012). "The promise of computer-assisted auscultation in screening for structural heart disease and clinical teaching". Cardiovascular Journal of Africa. 23 (7): 405–408. doi:10.5830/CVJA-2012-007. PMC   3721800 . PMID   22358127.
  4. ↑ Mandal, S; Basak K; Mandana KM; Ray AK; Chatterjee J; Mahadevappa M (2011). "Development of cardiac prescreening device for rural population using ultralow-power embedded system". IEEE Transactions on Biomedical Engineering. 58 (3): 745–749. doi:10.1109/TBME.2010.2089457. PMID   21342805. S2CID   7771478.
  5. ↑ Iwamoto, J; Ogawa H; Maki H; Yonezawa Y; Hahn AW; Caldwell WM (2011). "A mobile phone-based ecg and heart sound monitoring system". Biomedical Sciences Instrumentation. 47: 160–164. PMID   21525614.
  6. ↑ Koekemoer, H. L.; Scheffer, C. (2008). "Heart sound and electrocardiogram recording devices for telemedicine environments". 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol. 2008. pp. 4867–4870. doi:10.1109/IEMBS.2008.4650304. ISBN   978-1-4244-1814-5. PMID   19163807. S2CID   32681936.
  7. 1 2 3 "Home". eMURMUR.
  8. ↑ "Zargis Cardioscan".
  9. 1 2 "Diacoustic Medical Devices".
  10. ↑ Becket Mahnke, C. (2009). "Automated heartsound analysis/Computer-aided auscultation: A cardiologist's perspective and suggestions for future development". 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Vol. 2009. pp. 3115–3118. doi:10.1109/IEMBS.2009.5332551. PMID   19963568. S2CID   630335.{{cite book}}: |journal= ignored (help)
  11. ↑ Alam, Uazman; Omar Asghar; Sohail Q Khan; Sajad Hayat; Rayaz A Malik (2010). "Cardiac auscultation: an essential clinical skill in decline". British Journal of Cardiology. 17: 8–10.
  12. ↑ Kumar, Komal; W. Reid Thompson (2012). "Evaluation of Cardiac Auscultation Skills in Pediatric Residents". Clinical Pediatrics. 52 (1): 66–73. doi:10.1177/0009922812466584. PMID   23185081. S2CID   29237618.
  13. ↑ Vukanovic-Criley, JM; Criley S; Warde CM; Boker JR; Guevara-Matheus L; Churchill WH; Nelson WP; Criley JM (2006). "Competency in cardiac examination skills in medical students, trainees, physicians, and faculty: a multicenter study". Archives of Internal Medicine. 27 (6): 610–616. doi:10.1001/archinte.166.6.610. PMID   16567598.
  14. 1 2 McCrindle, BW; Shaffer KM; Kan JS; Zahka KG; Rowe SA; Kidd L (1995). "Factors prompting referral for cardiology evaluation of heart murmurs in children". Archives of Pediatrics & Adolescent Medicine. 149 (11): 1277–1279. doi:10.1001/archpedi.1995.02170240095018. PMID   7581765.
  15. ↑ Germanakis, I; Petridou ET; Varlamis G; Matsoukis IL; Papadopoulou-Legbelou K.; Kalmanti M (2013). "Skills of primary healthcare physicians in paediatric cardiac auscultation". Acta Paediatrica. 102 (2): 74–78. doi: 10.1111/apa.12062 . PMID   23082851. S2CID   10518559.
  16. ↑ Gaskin, PR; Owens SE; Talner NS; Sanders SP; Li JS (2000). "Clinical auscultation skills in pediatric residents". Pediatrics. 105 (6): 1184–1187. doi:10.1542/peds.105.6.1184. PMID   10835055. S2CID   14993738.
  17. ↑ Caddell, AJ; Wong KK; Barker AP; Warren AE (2015). "Trends in pediatric cardiology referrals, testing, and satisfaction at a Canadian tertiary centre". Canadian Journal of Cardiology. 31 (1): 95–98. doi:10.1016/j.cjca.2014.10.028. PMID   25547558.
  18. ↑ Wren, Christopher; Sam Richmond; Liam Donaldson (1999). "Presentation of congenital heart disease in infancy: implications for routine examination". Arch Dis Child Fetal Neonatal Ed. 80 (1): F49–F53. doi:10.1136/fn.80.1.f49. PMC   1720871 . PMID   10325813.
  19. ↑ Bonow, Robert O.; Blase A. Carabello; Kanu Chatterjee; Antonio C. de Leon; David P. Faxon; Michael D. Freed; William H. Gaasch; Bruce Whitney Lytle; Rick A. Nishimura; Patrick T. O’Gara; Robert A. O’Rourke; Catherine M. Otto; Pravin M. Shah; Jack S. Shanewise (2006). "ACC/AHA 2006 Guidelines for the Management of Patients With Valvular Heart Disease". Circulation. 114 (5): 84–231. doi: 10.1161/CIRCULATIONAHA.106.176857 . PMID   16880336.
  20. ↑ Bishop, Christopher (1995). Neural Networks for Pattern Recognition. Oxford University Press.
  21. ↑ Pretorius, Eugene; Cronje, Matthys L.; Strydom, Otto (2010). "Development of a pediatric cardiac computer aided auscultation decision support system". 2010 Annual International Conference of the IEEE Engineering in Medicine and Biology. Vol. 2010. pp. 6078–6082. doi:10.1109/IEMBS.2010.5627633. ISBN   978-1-4244-4123-5. PMID   21097128. S2CID   27940646.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.