قالب وردپرس درنا توس
Home / SmartTech / Researchers develop AI that estimates

Researchers develop AI that estimates



Acute kidney injury (AKI) – a condition in which the kidney suddenly fails to filter waste from the blood – can devastate the renal system of critically ill patients. The mortality rate can approach 89 percent if it progresses beyond stage 2 (AKI is categorized into three stages). And if AKI develops after major abdominal surgery, the risk of death is increased 12-fold.

Fortunately, early diagnosis has been made. Northwestern University and the University of Texas Health Science Center (ECA) describes the artificially intelligent (AI) system health records (EHRs), and predict the liking of AKI within the first 24 hours of intensive care unit (ICU).

"We developed data-driven prediction models to estimate the risk of new AKI onset," the researchers wrote. AKI soon after ICU admission. "

To train the AI ​​system, the team sourced records from Medical Information Mart for Intensive Care III (MIMIC-III), in an ICUs of the Beth Israel Deaconess Medical Center. They developed a script that scraped age, gender, race and ethnicity, and clinical notes during the first day of ICU admission and 72-hour serum creatinine levels (post-admission) and signs of kidney dysfunction

ICU stays, which they split into two sets: one for training and another for testing.

Some of the papers are in the process of being read and are being read by the National Library of Medicine's MetaMap toolset , Extracted features came in the form of Concept Unique Identifiers (CUIs) ̵

1; concepts associated with words and terms – from Unified Medical Language System (UMLS).

Five algorithms were used to classify the ICU stays and estimate AKI risk from scikit-learn, an open-source machine learning library for the Python programming language. AKI more than 50 percent of the time and with precision "competitive" with previous methods.

Still, it was not perfect. It incorrectly flagged AKI onset in a patient who contained highly associative words such as "chest tube" and "labile." And in another case, it failed to predict AKI in a patient who later developed it.

The Research Leave to Future Research on Alternative Phenotyping Systems, Clinical Notes Databases, and Validation on Additional Patient Datasets.

19659002] Anto's party of note applying to AKI detection is Google subsidiary DeepMind, which was announced in February Department of Veterans Affairs said that it gained more than 700,000 medical records.


Source link