Machine Learning-Based Intelligent Auscultation Techniques in Congenital Heart Disease:Application and Development

Congenital heart disease(CHD),the most prevalent congenital ailment,has seen advancements in the“dual indi-cator”screening program.This facilitates the early-stage diagnosis and treatment of children with CHD,subse-quently enhancing their survival rates.While cardiac auscultation offers an objective reflection of cardiac abnormalities and function,its evaluation is significantly influenced by personal experience and external factors,rendering it susceptible to misdiagnosis and omission.In recent years,continuous progress in artificial intelli-gence(AI)has enabled the digital acquisition,storage,and analysis of heart sound signals,paving the way for intelligent CHD auscultation-assisted diagnostic technology.Although there has been a surge in studies based on machine learning(ML)within CHD auscultation and diagnostic technology,most remain in the algorithmic research phase,relying on the implementation of specific datasets that still await verification in the clinical envir-onment.This paper provides an overview of the current stage of AI-assisted cardiac sounds(CS)auscultation technology,outlining the applications and limitations of AI auscultation technology in the CHD domain.The aim is to foster further development and refinement of AI auscultation technology for enhanced applications in CHD.

Synthesis of Reviews on Auscultation, Approaches, and Methods for Engineering Structures

Topometric auscultation is used to monitor the durability of structures, measure deformations linked to the structure of a structure or to the movement of the ground over a part of the globe, set up warning systems, etc. It first appeared as a visual method and rapidly evolved through the various techniques used. Some of these techniques using topography are used in several fields (civil engineering, geodesy, topography, mechanics, nuclear engineering, hydraulics, physics, etc.). These topometric techniques have undergone major changes as a result of technological advances, growing needs in the monitoring of movements or deformations, increased requirements and new challenges. The methodology adopted depends on the measuring instrument used, the parameters to be estimated and access to the area to be measured. There are two types of methods: destructive and non-destructive. In addition to the visual method, they can also be classified as mechanical, physico-chemical, dynamometric, electrophysical and geometric. The estimated parameter varies according to the methodology adopted. It can be defined by coordinates, distances, potential, electrical resistance, etc.

Auscultation transformed:the ingenious invention of the stethoscope by René Théophile Hyacinthe Laennec

This study delves into the life and significant contributions of René Théophile Hyacinthe Laennec,a prominent French physician of the 19^(th) century,and thoroughly examines his revolutionary creation,the stethoscope.Laennec’s innovative spirit not only revolutionized medical diagnosis during his time but also left a lasting imprint on the broader field of medicine,influencing healthcare for generations.This extensive inquiry covers various aspects,including his historical context,the development of the stethoscope,its profound implications for medical diagnosis,and its enduring impact on the history of medicine.

Accuracy of abdominal auscultation for bowel obstruction

AIM:To investigate the accuracy and inter-observer variation of bowel sound assessment in patients with clinically suspected bowel obstruction.METHODS:Bowel sounds were recorded in patients with suspected bowel obstruction using a Littmann® Electronic Stethoscope. The recordings were processed to yield 25-s sound sequences in random order on PCs. Observers,recruited from doctors within the department,classified the sound sequences as either normal or pathological. The reference tests for bowel obstruction were intraoperative and endoscopic findings and clinical follow up. Sensitivity and specificity were calculated for each observer and compared between junior and senior doctors. Interobserver variation was measured using the Kappa statistic.RESULTS:Bowel sound sequences from 98 patients were assessed by 53(33 junior and 20 senior) doctors. Laparotomy was performed in 47 patients,35 of whom had bowel obstruction. Two patients underwent colorectal stenting due to large bowel obstruction. The median sensitivity and specificity was 0.42(range:0.19-0.64) and 0.78(range:0.35-0.98),respectively. T h e re wa s n o s i g n i f i c a n t d i ffe re n c e i n a cc u ra c y between junior and senior doctors. The median frequency with which doctors classified bowel sounds as abnormal did not differ significantly between patients with and without bowel obstruction(26% vs 23%,P = 0.08). The 53 doctors made up 1378 unique pairs and the median Kappa value was 0.29(range:-0.15-0.66).CONCLUSION:Accuracy and inter-observer agreement was generally low. Clinical decisions in patients with possible bowel obstruction should not be based on auscultatory assessment of bowel sounds.

Chip Layout for Adaptive Line Enhancer Design using Adaptive Filtering Algorithms and Metrics Computation for Auscultation Signal Separation

Currently,the growth of micro and nano(very large scale integration-ultra large-scale integration)electronics technology has greatly impacted biomedical signal processing devices.These high-speed micro and nano technology devices are very reliable despite their capacity to operate at tremendous speed,and can be designed to consume less power in minimum response time,which is particularly useful in biomedical products.The rapid technological scaling of the metal-oxide-semi-conductor(MOS)devices aids in mapping multiple applications for a specific purpose on a single chip which motivates us to design a sophisticated,small and reliable application specific integrated circuit(ASIC)chip for future real time medical signal separation and processing(digital stetho-scopes and digital microelectromechanical systems(MEMS)microphone).In this paper,ASIC level implementation of the adaptive line enhancer design using adaptive filtering algorithms(least mean square(LMS)and normalized least mean square(NLMS))integrated design is used to separate the real-time auscultation sound signals effectively.Adaptive line enhancer(ALE)design is imple-mented in Verilog hardware description language(HDL)language to obtain both the network and adaptive algorithm in cadence Taiwan Semiconductor Manufacturing Company(TSMC)90 nm standard cell library environment for ASIC level implementation.Native compiled simulator(NC)sim and RC lab were used for functional verification and design constraints and the physical design is implemented in Encounter to obtain the Geometric Data Stream(GDS II).In this architecture,the area occupied is 0.08 mm,the total power consumed is 5.05 mW and the computation time of the proposed system is 0.82μs for LMS design and the area occupied is 0.14 mm,the total power consumed is 4.54 mW and the computation time of the proposed system is 0.03μs for NLMS design that will pave a better way in future electronic stethoscope design.

Lung sounds auscultation technology based on ANC - ICA algorithm in high bat- tlefield noise environment

AIM:To explore the more accurate lung sounds auscultation technology in high battlefield noise environment.METHODS: In this study, we restrain high background noise using a new method-adaptive noise canceling based on independent component analysis (ANC-ICA), the method, by incorporating both second-order and higher-order statistics can remove noise components of the primary input signal based on statistical independence.RESULTS:The algorithm retained the local feature of lung sounds while eliminating high background noise, and performed more effectively than the conventional LMS algorithm.CONCLUSION:This method can cancel high battlefield noise of lung sounds effectively thus can help diagnose lung disease more accurately.

Development of a signal collecting system for double-channel auscultation

As is known to all, many auscultations of human body, such as heart, lung and carotid artery sound, play a major role in clinic. And their signal frequency is in the range that computer sound card can handle, so we can use analog-to-digital (A/D) conversion of sound card as A/D conversion (ADC) of auscultation signals, and double-channel auscultation signals (DCASs) can be input into personal computer(PC) by sound card that every computer has, and it makes the hardware design more simple. Because auscultation signals are input from sound card, any common music processing software (CMPS) can be used to process received auscultative signals, and it is not necessary to write special processing software for them. Therefore, only a double-channel and front-end analog signal processing circuit of auscultation is needed to be designed. By this method of constituting the signal collecting system for double-channel auscultation, it is simple and low cost, and needs no special software, so it has very important values and a broad market prospect.

Using Geometry Data from Ground Penetrating Radar to Improve Pavement Layers Auscultation Using Seismic Surface Waves Inversion Method

In order to reduce the unknown parameters during the inversion of the dispersion curve in the aim to obtain more precise Vs and VP profiles, the Multi-Channel Analysis of Surface Waves (MASW) method was combined with the Ground Penetrating Radar (GPR) method. First, a 2D GPR profile was made on the pavement, then 1D MASW profiles spaced by 0.2 m apart in the perpendicular direction and centered on the intersection with the Radar profile. The GPR measurements, made with a 1600 Hz antenna, allowed to calculate the dielectric permittivities then velocities in order to convert the times profiles to depth. Thus, the thicknesses of the layers are directly read on the radar profile. MASW measurements were performed by simulating the Multi-Channel Simulation with One Receiver (MSOR) method in Land Streamer mode. Six 4.5 Hz pointless geophones are connected to the seismograph consisting of an Arduino Due microcontroller and a nano-computer type Raspberry Pi 4. The results of the dispersion analysis showed a fundamental mode located between approximately 70 Hz and 200 Hz and an inverted dispersion, characteristic of pavements with higher frequencies propagating at higher velocities. The results show that the integration of the number of layers and the thicknesses obtained from the GPR measurements in the inversion parameters makes it possible to obtain a more precise Vs and VP velocity profile. All profiles, seismic and radar, have shown that velocities decrease with depth. The detected heterogeneities appear to be related to differences in water content inside the pavement.

Is Pulmonary Auscultation Alone Sufficient for Clinical Practice?

Objective: The clinical examination is the basis for the diagnosis and rational choice of complementary tests. The aim of the study was to evaluate the performance of auscultation of the chest for screening of disease and for predicting the presence of abnormalities in the other domains of the chest examination. Methods: Patients with COPD, atelectasis, pleural effusion, pneumonia and controls were evaluated by two examiners in the absence of any clinical information, initially only with pulmonary auscultation, and then in the other domains of chest examination. Results: 192 physical examinations were performed in 104 patients. An abnormal pulmonary auscultation had a sensitivity of 85.2%, positive predictive value (PPV) of 84.1%, positive likelihood reason (LR) of 1.53 (95% CI;1.16 to 2.01) and negative LR of 0.33 (95% CI;0.2 to 0.56) to identify the presence of any disease, and also a positive LR of 2.23 (95% CI;1.02 to 4.9) and a negative LR of 0.3 (95% CI;0.17 to 0.51) to predict additional abnormalities. A normal auscultation showed low accuracy to identify healthy individuals, with sensitivity, specificity, NPV and PPV, respectively, of 44%, 43%, 41% and 46%. The agreement between the examiners considering normal versus abnormal findings showed kappa = 0.76 for any changes in the physical examination present (p < 0.0001). Conclusions: Auscultation of the chest alone, may not be a sufficient strategy to track diseases or establish whether continuity of the examination is necessary or not.

Characterization and cross-comparison of digital stethoscopes for telehealthremote patient auscultation

Stethoscopes are commonly used to diagnose cardiac and respiratory diseases.The advent of digital stethoscopes added the capability to remotely monitor the cardiorespiratory well-being of patients and facilitate digital remote auscultations for physicians to examine their patients outside of the clinic.To increase the adoption of a hybrid diagnosis between in-person and remote auscultations,it is important to characterize the frequency response of different configurations of digital stethoscopes.A standard testing platform was adopted from the literature and re-validated by seven physicians.Two wearable and two non-wearable digital stethoscopes were investigated.A similarity factor score was used to analyze select time-synchronized acoustic events that achieved high fidelity between stethoscopes.The frequency responses between devices were compared using the correlation coefficient.Two devices reported the highest correlation coefficient of 0.72 and 0.75 in the wearable and non-wearable categories,respectively.The correlation coefficient of the frequency responses between the same pair of devices on the human chest was 0.91.With such a high agreement in the frequency response between the wearable and non-wearable digital stethoscope,it can be concluded that the configuration of digital stethoscope is not a limiting factor of performance,and both are acceptable and desirable for physicians to adopt either configuration in remote delivery of healthcare.

Detecting Non-Stationarity for Auscultation Signal of Traditional Chinese Medicine

The information about the nonstationarity of the aus-cultation signal is utilized in this paper to objectively and auto-matically identify healthy people and patients with qi-deficiency or yin-deficiency. In order to characterize the nonstationarity of the sound signal,the nonlinear cross-prediction method is used to extract features from the signal. A feature selection method based on conditional mutual information maximization criterion （CMIM） is implemented to find an optimal feature set. By means of the support vector machine （SVM） classifier,three common states （healthy,qi-deficiency and yin-deficiency） in traditional Chinese medicine are distinguished using the feature set,and a satisfactory classification accuracy of 80% is achieved in the experiment. In conclusion,the analysis based on the nonstationarity of the sound signal provides an alternative and outstanding approach to the objective auscultation of traditional Chinese medicine （TCM）.

Long-lasting symptoms and diagnostics in a patient with unrecognized right sided heart failure: Why listening to the heart is so important

M Ebstein is usually diagnosed in early childhood or ad-olescence. The young woman in our case complainted of fatigue and shortness of breath, on physical exami-nation she showed signs of heart failure with raised central venous pressure, palpable liver, an a cardiac murmer. Based on these findings she should have been referred to a cardiologist in an early stage after which transthoracic echocardiography resulted in the correct diagnosis. In this case the anomaly was missed for many years by different specialists and the patient was treated for liver disease, while she was suffering from liver congestion due to right-sided heart failure.

A model of Korotkoff sounds method electronic sphygmomanometer equivalent to the mercury one

Mercury sphygmomanometer (MSM) is reliable and widely used in clinics and hospitals. The principle of Korotkoff sounds method (KSM) applied in the MSM is also a gold standard to measure blood pressure. Many efforts have been made attempting to replace MSM, which is criticized for being not healthy and safe. In this research, an electronic blood pressure monitor, named K-sounds electronic sphygmomanometer (KESM), was designed as a substitute to MSM. The three key elements of KSM were proposed for the first time. We used appropriate electronic components to build the KESM which can fulfill the functions related to the three key elements. The KESM, which was easy to operate and free of mercury, followed the same principle as MSM. The same principle guaranteed the comparable accuracy. We took equivalence test and the results showed that the designed KESM was as accurate as the calibrated standard MSM. The designed KESM passed the certifications of SFDA and is qualified in clinics or hospitals for diagnostic purposes.

Acoustic and Intraluminal Ultrasonic Technologies in the Diagnosis of Diseases in Gastrointestinal Tract: A Review

Gastrointestinal (GI) auscultation (listening to sounds from stomach and bowel) has been applied for abdominal physical assessment for many years. This article evaluates the technique involved in listening to both bowel and stomach sounds and the significance of both normal and abnormal GI auscultation findings. Moreover, intraluminal ultrasonic techniques have been widely used for gastrointestinal disease diagnosis by providing intraluminal images since 1980s, this article also reviews the existing intraluminal ultrasonic technology for diagnosing of GI disorders.

Accidental esophageal intubation via a large type C congenital tracheoesophageal fistula:A case report

BACKGROUND Tracheoesophageal fistula(TEF)is a congenital anomaly characterized by interruptions in esophageal continuity with or without fistulous communication to the trachea.Anesthetic management during TEF repair is challenging because of the difficulty of perioperative airway management.It is important to determine the appropriate position of the endotracheal tube(ETT)for proper ventilation and to prevent excessive gastric dilatation.Therefore,the tip of the ETT should be placed immediately below the fistula and above the carina.CASE SUMMARY A full-term,one-day-old,2.4 kg,50 cm male neonate was diagnosed with TEF type C.During induction,an ETT was inserted using video laryngoscope and advanced deeply to ensure that the tip passed over the fistula,according to known strategies.The passage of the ETT through the vocal cords was confirmed via video laryngoscope.However,after inflating the ETT cuff,breath sounds were not heard on bilateral lung auscultation.Instead,gastric sounds were heard.Considering that a large fistula(approximately 6.60 mm×4.54 mm)located 10.2mm above the carina was confirmed on preoperative tracheal computed tomography,the possibility of unintentional esophageal intubation was highly suspected.Therefore,we decided to uncuff and withdraw the ETT carefully for repositioning,while monitoring auscultation and end-tidal CO2 simultaneously.At a certain point(9.5 cm from the lip),clear breath sounds and proper end-tidal CO_(2) readings were suddenly achieved,and adequate ventilation was possible.CONCLUSION Preanesthetic anatomical evaluation with imaging studies in TEF is necessary to minimize complications related to airway management.

Trends in point-of-care ultrasound protocols in the emergency department and intensive care unit:a review

Together with the development of the focused assessment with sonography for trauma protocol for ultrasound in trauma patients,point-of-care ultrasound is widely used in the field of emergency and critical care medicine.Researchers have established several classic operating protocols for different diseases,such as acute respiratory failure,shock,and cardiac arrest,in the emergency department and intensive care unit.With further development in the portability and popularity of ultrasonic equipment,it is expected to be used as a new type of technology for physical examination,including inspection,palpation,percussion,auscultation,and insonation,which will improve the clinical medicine practice in the future.

Detection and identification of S1 and S2 heart sounds using wavelet decomposition method

Phonocardiogram （PCG）, the digital recording of heart sounds is becoming increasingly popular as a primary detection system for diagnosing heart disorders and it is relatively inexpensive. Electrocardiogram （ECG） is used during the PCG in order to identify the systolic and diastolic parts manually. In this study a heart sound segmentation algorithm has been developed which separates the heart sound signal into these parts automa- tically. This study was carried out on 100 patients with normal and abnormal heart sounds. The algorithm uses discrete wavelet decomposition and reconstruction to pro- duce PCG intensity envelopes and separates that into four parts： the first heart sound, the systolic period, the second heart sound and the diastolic period. The performance of the algorithm has been evaluated using 14,000 cardiac periods from 100 digital PCG recordings, including normal and abnormal heart sounds. In tests, the algorithm was over93% correct in detecting the first and second heart sounds. The presented automatic seg- mentation Mgorithm using w^velet decomposition and reconstruction to select suitable frequency band for envelope calculations has been found to be effective to segment PCG signals into four parts without using an ECG.