Heart sound classification based on improved mel frequency cepstrum coefficient and integrated decision network method / 生物医学工程学杂志

Heart sound analysis is significant for early diagnosis of congenital heart disease. A novel method of heart sound classification was proposed in this paper, in which the traditional mel frequency cepstral coefficient (MFCC) method was improved by using the Fisher discriminant half raised-sine function (F-HRSF) and an integrated decision network was used as classifier. It does not rely on segmentation of the cardiac cycle. Firstly, the heart sound signals were framed and windowed. Then, the features of heart sounds were extracted by using improved MFCC, in which the F-HRSF was used to weight sub-band components of MFCC according to the Fisher discriminant ratio of each sub-band component and the raised half sine function. Three classification networks, convolutional neural network (CNN), long and short-term memory network (LSTM), and gated recurrent unit (GRU) were combined as integrated decision network. Finally, the two-category classification results were obtained through the majority voting algorithm. An accuracy of 92.15%, sensitivity of 91.43%, specificity of 92.83%, corrected accuracy of 92.01%, and F score of 92.13% were achieved using the novel signal processing techniques. It shows that the algorithm has great potential in early diagnosis of congenital heart disease.

Artificial intelligence and dichotomy on benefits and challenges: what do healthcare providers say?

Background: In a developing country like India, with a vibrant information technology (IT) sector, employing Artificial Intelligence (AI) should be carefully weighed before its introduction in healthcare with relation to perception of healthcare providers (HCP's/Doctors).  Methods: This qualitative study was conducted in medical college and affiliated hospital in India. Initially a pilot study was conducted for reliability and internal consistency of questionnaire. Thereafter, pre-tested questionnaire was distributed to 153 healthcare providers and their responses were analyzed on SPSS version 20.0 (IBM) to identify the demographic and job-related differences in their perception regarding the benefits and challenges of using AI in healthcare.Results: Most of respondent were agreed upon the benefits of using AI in healthcare and most cited benefits were speedy decision making, better resource utilization and improvement in staff satisfaction. Similarly most cited challenges were lack of training on AI enabled machines, lack of skilled technical support, high cost of AI and data privacy issue. Further, Age and Job experience were significantly associated with benefits like timely and speedy decision making, improvement in the patient and staff satisfaction respectively. Furthermore, Age, Department, Job experience, Job profile were significantly associated with challenges like high cost of AI, lack of skilled technical support, lack of training in AI enabled machines and lack of trust in AI among patients.Conclusions: Significant challenges of using AI in healthcare with demographic and job related variable based on the results of this research paper need to be resolved first in order to overcome the initial resistance in employing AI in healthcare.