Deep Neural Networks for Ventilator Pressure Prediction / (Record no. 609133)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 02504nam a22001577a 4500 |
| 082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER | |
| Classification number | 610 |
| 100 ## - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Asif, Ali Raza |
| 245 ## - TITLE STATEMENT | |
| Title | Deep Neural Networks for Ventilator Pressure Prediction / |
| Statement of responsibility, etc. | Ali Raza Asif |
| 264 ## - PRODUCTION, PUBLICATION, DISTRIBUTION, MANUFACTURE, AND COPYRIGHT NOTICE | |
| Place of production, publication, distribution, manufacture | Islamabad : |
| Name of producer, publisher, distributor, manufacturer | SMME- NUST; |
| Date of production, publication, distribution, manufacture, or copyright notice | 2022. |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 55p. |
| Other physical details | Soft Copy |
| Dimensions | 30cm |
| 500 ## - GENERAL NOTE | |
| General note | Invasive mechanical ventilation is a common medical treatment required for applications<br/>spanning anesthesia, neonatal intensive care, and life support for the current COVID-19<br/>pandemic. Despite its importance, the core technology of medical ventilation has remained<br/>largely unchanged for years. It is common for a clinician to continuously monitor and adjust the<br/>ventilator for a patient manually thus increasing workload. With machine learning (ML) taking<br/>center stage in healthcare recently, the question has been asked whether ML based control<br/>methods can be developed to replace manual intervention. The main challenge however remains<br/>the robustness, safety, and the high cost of development. In addition, the controller must be able<br/>to adapt reliably and quickly across varying clinical conditions and requirements not observable<br/>directly to the clinicians. Proportional-Integral-Derivative (PID) controllers have been to go to<br/>method of choice because of its limited parameters size, fewer samples for tuning, and its ability<br/>to generalize over the dynamic lung conditions. Current ventilator or patient simulators are<br/>trained by an ensemble of multiple models each simulating the parameters of a single lung.<br/>However, human lungs and respectively their parameters or attributes are dynamic and form a<br/>continuous space therefore, based on the physiological differences in patient lungs a parametric<br/>approach is better suited to improve generalization. This work centers around the possibility of<br/>developing an ML-based method which can improve performance simultaneously across a wide<br/>range of lung parameters based upon the ISO standard for performance of ventilatory support<br/>equipment (ISO 80601-2-80:2018). The results are compared against previously published data<br/>and closely match the expected outcome. This is a significant improvement towards a more<br/>robust alternative to PID tuning and more importantly cost-effective mechanical ventilators. |
| 650 ## - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | MS Biomedical Engineering (BME) |
| 700 ## - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Supervisor : Dr. Muhammad Asim Waris |
| 856 ## - ELECTRONIC LOCATION AND ACCESS | |
| Uniform Resource Identifier | <a href="http://10.250.8.41:8080/xmlui/handle/123456789/30536">http://10.250.8.41:8080/xmlui/handle/123456789/30536</a> |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Source of classification or shelving scheme | |
| Koha item type | Thesis |
| Withdrawn status | Permanent Location | Current Location | Shelving location | Date acquired | Full call number | Barcode | Koha item type |
|---|---|---|---|---|---|---|---|
| School of Mechanical & Manufacturing Engineering (SMME) | School of Mechanical & Manufacturing Engineering (SMME) | E-Books | 05/15/2024 | 610 | SMME-TH-725 | Thesis |