Researchers Use A.I. To Improve Quality Of End-Of-Life Care

Researchers at Stanford University are using A.I. technology to improve the quality of end-of-life care for patients who may have been diagnosed as terminally ill and have been given a prognosis of having only a certain period of time to live. Essentially, the research is using deep learning to more accurately predict when a person with a terminally ill disease is going to die. As the research states, physicians can over estimate the amount of time a patient may have, which can lead to issues with the end-of-life care and the wishes of the patient. More than just using deep learning technology the researchers are also gathering information from Electronic Health Record data to help narrow down a more precise time frame for death to give a better prognosis.

The reason for this research is tied to information showing that 80 percent of patients in the U.S. who have been given a prognosis of dying soon would want to spend the time they have left at home, which would require palliative care. The research study also points out that only around 20 percent of those who wish to receive palliative care actually get it, and that a big part of that can be due to physicians overlooking certain details that could lead to allowing such care within the home as opposed to the hospital.

The research was said to be conducted with the gathered data coming from two million patient records and that using that data has allowed the researchers to create a model that is about 90 percent accurate in predicting when a patient is going to die. Reaching a mortality prediction apparently starts by ignoring the disease type, the stage of the disease, and the severity of the admission, which the deep learning model then analyzes to ultimately come to the prediction. According to the researchers at Stanford who were part of this project, some pretty powerful computing hardware was needed as the model tests were run using a computer that was outfitted with an NVIDIA TitanX GPU along with 12GB of RAM and CUDA version 8.0. While there is still more work to be done in likely getting to the accuracy rate that the researchers are hoping to achieve, this seems to be a good start in perhaps making it possible for more end-of-life patients to receive palliative care.

Copyright ©2019 Android Headlines. All Rights Reserved
This post may contain affiliate links. See our privacy policy for more information.
You May Like These
More Like This:
About the Author

Justin Diaz

Head Editor
Lover of food, craft beer, movies, travel, and all things tech. Video games have always been a passion of his due to their ability to tell incredible stories, and home automation tech is the next big interest, in large part because of the Philips Hue integration with Razer Chroma. Current Device: Google Pixel.