Changing stroke rehab and research worldwide now.Time is Brain! trillions and trillions of neurons that DIE each day because there are NO effective hyperacute therapies besides tPA(only 12% effective). I have 523 posts on hyperacute therapy, enough for researchers to spend decades proving them out. These are my personal ideas and blog on stroke rehabilitation and stroke research. Do not attempt any of these without checking with your medical provider. Unless you join me in agitating, when you need these therapies they won't be there.

What this blog is for:

My blog is not to help survivors recover, it is to have the 10 million yearly stroke survivors light fires underneath their doctors, stroke hospitals and stroke researchers to get stroke solved. 100% recovery. The stroke medical world is completely failing at that goal, they don't even have it as a goal. Shortly after getting out of the hospital and getting NO information on the process or protocols of stroke rehabilitation and recovery I started searching on the internet and found that no other survivor received useful information. This is an attempt to cover all stroke rehabilitation information that should be readily available to survivors so they can talk with informed knowledge to their medical staff. It lays out what needs to be done to get stroke survivors closer to 100% recovery. It's quite disgusting that this information is not available from every stroke association and doctors group.

Tuesday, November 23, 2021

Development and Validation of a Deep Learning Model for Earlier Detection of Cognitive Decline From Clinical Notes in Electronic Health Records

Is your doctor proactively testing for MCI? Or is s/he just doing the status quo of nothing? You have a good chance of getting dementia, hopefully your doctor has protocols to prevent that. 

Your risk of dementia, has your doctor told you of this?

1. A documented 33% dementia chance post-stroke from an Australian study?   May 2012.

2. Then this study came out and seems to have a range from 17-66%. December 2013.`    

3. A 20% chance in this research.   July 2013.

4. Dementia Risk Doubled in Patients Following Stroke September 2018 

The latest here:

 

Development and Validation of a Deep Learning Model for Earlier Detection of Cognitive Decline From Clinical Notes in Electronic Health Records

 
JAMA Netw Open. 2021;4(11):e2135174. doi:10.1001/jamanetworkopen.2021.35174
Key Points

Question  Can a deep learning algorithm applied to clinical notes detect evidence of cognitive decline before a mild cognitive impairment (MCI) diagnosis?

Findings  In this diagnostic study, using clinical notes on 2166 patients preceding an MCI diagnosis, a deep learning algorithm was trained and validated for detecting cognitive decline using data sets with and without keyword filtering. The model trained in the data set with keyword filtering performed satisfactorily in the data sets without keyword filtering.

Meaning  The results of this study suggest that a deep learning model can detect evidence of cognitive decline from notes preceding an MCI diagnosis, potentially facilitating earlier detection of cognitive decline in electronic health records.

Abstract

Importance  Detecting cognitive decline earlier among older adults can facilitate enrollment in clinical trials and early interventions. Clinical notes in longitudinal electronic health records (EHRs) provide opportunities to detect cognitive decline earlier than it is noted in structured EHR fields as formal diagnoses.

Objective  To develop and validate a deep learning model to detect evidence of cognitive decline from clinical notes in the EHR.

Design, Setting, and Participants  Notes documented 4 years preceding the initial mild cognitive impairment (MCI) diagnosis were extracted from Mass General Brigham’s Enterprise Data Warehouse for patients aged 50 years or older and with initial MCI diagnosis during 2019. The study was conducted from March 1, 2020, to June 30, 2021. Sections of notes for cognitive decline were labeled manually and 2 reference data sets were created. Data set I contained a random sample of 4950 note sections filtered by a list of keywords related to cognitive functions and was used for model training and testing. Data set II contained 2000 randomly selected sections without keyword filtering for assessing whether the model performance was dependent on specific keywords.

Main Outcomes and Measures  A deep learning model and 4 baseline models were developed and their performance was compared using the area under the receiver operating characteristic curve (AUROC) and area under the precision recall curve (AUPRC).

Results  Data set I represented 1969 patients (1046 [53.1%] women; mean [SD] age, 76.0 [13.3] years). Data set II comprised 1161 patients (619 [53.3%] women; mean [SD] age, 76.5 [10.2] years). With some overlap of patients deleted, the unique population was 2166. Cognitive decline was noted in 1453 sections (29.4%) in data set I and 69 sections (3.45%) in data set II. Compared with the 4 baseline models, the deep learning model achieved the best performance in both data sets, with AUROC of 0.971 (95% CI, 0.967-0.976) and AUPRC of 0.933 (95% CI, 0.921-0.944) for data set I and AUROC of 0.997 (95% CI, 0.994-0.999) and AUPRC of 0.929 (95% CI, 0.870-0.969) for data set II.

Conclusions and Relevance  In this diagnostic study, a deep learning model accurately detected cognitive decline from clinical notes preceding MCI diagnosis and had better performance than keyword-based search and other machine learning models. These results suggest that a deep learning model could be used for earlier detection of cognitive decline in the EHRs.

Introduction

There are nearly 6 million people diagnosed with Alzheimer disease (AD) at the stage of dementia in the US, and the prevalence increases dramatically with age.1 Mild cognitive impairment (MCI) and subjective cognitive decline (SCD) represent precursor stages that can serve as targets for early treatment.2-4 Early detection of cognitive decline can facilitate enrollment in clinical trials and early interventions.5,6 The US Food and Drug Administration recently approved aducanumab, a drug directed at the underlying pathologic characteristics of AD that clears amyloid plaques in the brain, to treat patients with AD.7 However, detecting patients with cognitive decline is challenging. There is an insufficient number of specialists with the necessary expertise (behavioral or cognitive neurologists, geriatric psychiatrists, geriatricians, and neuropsychologists) to see all at-risk patients. Instead, primary care physicians and other nondementia specialists have direct contact with these patients but not necessarily the time or tools needed for diagnosis.8

Systematically reviewing large electronic health record (EHR) data collected across patients’ full visit history within a health care system can facilitate early detection of cognitive decline by identifying when patients first reported signs or symptoms of cognitive decline to any health care professional. This documentation in turn may help trigger a more detailed evaluation in primary care settings and beyond and facilitate participant enrollment in clinical trials and early interventions. However, many obstacles exist to identifying patients with cognitive decline in the EHR. For early stages of cognitive decline, such as SCD, self-reported concerns about cognitive status do not imply a diagnosis of cognitive decline by a health care professional. Cognitive symptoms, concerns, and cognitive assessments may be merely documented in the health care professional’s notes, leaving such information difficult to identify and analyze. For later stages, when the decline becomes substantial enough to be measurable, patients may still have missed or delayed diagnosis of MCI or dementia.8,9

Current approaches to identifying cognitive decline from the EHR have limitations. These approaches commonly rely on billing codes or medications and are likely to be insensitive. Prior studies primarily focused on the stages of cognitive decline from MCI to dementia.10-12 Limited research has focused on detection of early cognitive decline preceding MCI or use of unstructured EHR data (clinical notes).

Clinical notes contain information that other EHR fields may not capture,13 and identifying evidence of cognitive decline from clinical notes can be complementary to evidence from structured EHR data. Detecting evidence of cognitive decline from clinical notes using manually curated keywords can be limited and lack accuracy, and manual medical record review is costly and nonscalable. In the present study, we aimed to develop and validate a deep learning model to automatically detect evidence of cognitive decline from clinical notes. Such an automated approach might be used to screen a large population of adults aged 50 years or older to identify early evidence of cognitive decline. We hypothesized that a deep learning algorithm can be trained with a relatively small set of manually labeled notes and applied to achieve this task.

More at link.

No comments:

Post a Comment