No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Automated patient monitoring and diagnosis assistance by integrating statistical and artificial intelligence tools
Abstract
Automated data collection from patients has created new challenges
for health care professionals in their efforts to extract useful
information from raw data. Online monitoring devices may generate large
amounts of data that must be interpreted quickly and accurately. The use
of statistical methods and artificial intelligence (AI) tools to
summarize and interpret high frequency physiologic data such as the
electrocardiogram (ECG) are investigated. The development of a
methodology and associated tools for real-time patient data monitoring
and diagnosis assistance was accomplished by using MATLAB and G2, a
real-time knowledge-based system (KBS) development shell. A KBS was
developed that incorporates various DSP and statistical methods with a
rule-based decision system to detect abnormal situations, provide
preliminary interpretation and diagnosis assistance, and to report these
findings to medical personnel
The primary objective is to develop an interactive real time system with the help of speech recognition system to monitor the medical data in addition to manage sensors connected to human body. In this work, the development of a simple system which is capable of transferring the patient's vital parameters such as temperature, heart rate and electrocardiography (ECG) from the remote location to doctor is done through wireless technology. The sensors interfaced with My RIO embedded controller are connected to the human body, which are monitored and controlled through speech recognition system. Sensors gets activated by the doctor's voice command which is in the pre-defined vocabulary. The information from the sensors had been transferred to doctor with help of controller. Real time data processing is performed utilizing the LabVIEW tool.
In remote healthcare process, patient monitoring system is used to collect health data at home and in outdoor scenarios to facilitate disease management. Service Oriented Architecture (SOA) is used to build a comfortable web based management system for integrating distributed wireless sensor network (WSN) and internet. This paper proposes SOA based data architecture for healthcare. As a case study, patient data monitoring system is taken for implementation. It is not feasible for the caregiver to monitor, analyze voluminous data continuously and generate alerts. Data from the physiological sensors and the history data about the patient are used for analysis and alert generation. It is observed that the proposed architecture supports efficient information retrieval. The aggregated data in the server are sliced and diced by customized hand coding ETL (Extract Transform and Load) process. OBIEE (oracle business intelligence enterprise edition) tool is used to develop this application. This novel approach demonstrates data analysis subsystem of SOA for pattern identification and alert generation.
Despite tremendous development in wireless sensor networks, the abilities are by far yet fully leveraged in the case of online analysis of medical sensor data. We investigate how a data stream management system can be used to query and analyze streaming data from different medical sensors in real-time. By using the open source data stream management system Esper, we have implemented queries, based upon earlier work by Elle et al. [9], that can be used for real-time recognition of myocardial ischemia by combining a 3-axis accelerometer on the left ventricle of the heart, with an ECG sensor used for QRS detection. In the queries we use a new type of sliding window; a variable length triggered tumbling window. The window is used for aggregate operations that targets only sensor readings originating from single heartbeats. We show how algorithms that are used for medical analysis can be implemented as custom aggregation functions, thus incorporated into the declarative query language that is more suitable for medical personnel without programming experience. Results from experiments run on data recorded from surgical procedures on pig models show that the queries produce correct results, and can be run in real-time on fairly simple computers, e.g. laptops.
The noise sensitivities for nine different QRS detection algorithms were measured for a normal, single-channel lead II, synthesized ECG corrupted with five different types of synthesized noise. The noise types were electromyographic interference, 60 Hz powerline interference, baseline drift due to respiration, abrupt baseline shift, and a composite noise constructed from all of the other noise types. The percentage of QRS complexes detected, the number of false positives, and the detection delay were measured. None of the algorithms were able to detect all QRS complexes without any false positives for all of the noise types at the highest noise level. Algorithms based on amplitude and slope had the highest performance for EMG-corrupted ECG. An algorithm using a digital filter had the best performance for the composite noise corrupted data.
The algorithm presented is based on the methods of percent of time
above or below thresholds (PTABT), variability of threshold crossing
intervals (TCI) and peak similarity in autocorrelation function (ACF).
The algorithm offers a way to identify the ventricular fibrillation
(VFib) and nonVFib rhythms with several features of electrocardiogram
(ECG) rhythm and achieves a high sensitivity and specificity