Low Cost Cuffless Pre-ICU/NICU Monitoring with Heart Rate,Blood Pressure Anomaly Detection

Bangladesh has many rural hospitals that don’t have proper,invasive and accurate ICU equipment or sometimes ICU itself. We aim to create a low cost,battery-run,portable continuous and real-time heart rate,ECG,blood pressure anomaly detector. This will micromanage the load in ICU and NICU and also make the real time monitoring accessible to critical patients.

IDEA AND CONCEPTUAL DESIGN

Though heart rate is currently measured on smart devices,blood pressure is yet to be integrated. There is relationship between pulse transit time(PTT) and blood pressure.

Formulation: BPn = a · lnPTT + b · HR + c · BPn−1 + d

where PTT can be obtained from the time difference between ECG and PPG signals, HR can be easily measured from the ECG, and BPn−1 is the previous BP estimate. The four coefficients (a,b,c and d) can be calculated by applying the least square method.

Non-invasive blood pressure measurement without sphygmomanometer makes is easier to monitor in real time and also store data.

TECHNICAL FEASIBILITY

We plan to use physiological data recorded from patients in the Intensive Care Unit (ICU) from 

MIMIC database, maintained by the Massachusetts Institute of Technology (MIT). The data was used to patient specifically calibrate a,b,c,d coefficients by machine learning. The ECG and PPG data will be collected by mictoprocessor, pulse sensor and ECG sensor. The device will be cheap and easily implementable. The device will be expanded with temperature sensor to control temperature in a portable newborn incubator.

Later an app will be connected using bluetooth which will page doctor instantly when something abnormal happens to any critical patient or new-natal

TARGET AUDIENCE

Major audience are,where there are limited ICU machines are not available in third world countries. The minor audience will be personal portable infant incubator users.

DISCUSSION

The more data we feed our hypothesis, the greater the accuracy will be. As our system is real time, the data are stored and used later. The result may vary, but the precision is high. Thus even if the ECG and PPG readings might be jittery, that will not effect the window of anomaly detected in BP for a specific person. When suddenly BP falls when someone is unattended,the device is assigned to send out notification,commence surgicals.

CONCLUSION

Our device will serve as a buffer for surgery and ICU, monitor when sedated and a useful neo-natal incubator in obstetrics.