Medical Records PALS Malaysia website blog is my personal communications blogging platform in health information management / medical records management professional matters.

The letters in “PALS” identifies to “Practice, Advocacy, Learning, and Sharing (PALS)”. Each initial component (first letter) of the phrase “Practice, Advocacy, Learning, and Sharing” will share the acronym “PALS”, that is PALS will be an abbreviation formed from the initial components in the phrase “Practice, Advocacy, Learning and Sharing”.

This website blog was originally started to bring closer Malaysian HIM / MR practitioners through planned social meets along with the sharing of health information management / medical records management articles and news. Hence I adopted the best acronym I could think of then, that is “pals” to include all of Malaysian HIM / MR practitioners, both the ex-colleagues and colleagues who served and still serving in Health Information Management (HIM) services, primarily in the Medical Records Management services, with the Ministry of Health Malaysia (MoHM) and surely not forgetting those HIM / MR practitioners who served or still with the Malaysian private healthcare industry.

However, as much as my intuition defibrillates, I think I am not expecting much of meetups, or the social kinds among Malaysian HIM / MR practitioners in the distant future.

Thus, stimulated by the disinclination for change on the horizon, this website blog is a new dimension where I intend to continue to blog using this same website blog. This website blog continues to use the same blog segments (actually categories) I used in all previous posts – with active posts and room for interactive discussion and knowledge sharing among discerning HIM / MR practitioners in health information management / medical records practice, advocacy, learning and sharing for HIM / MR practitioners in Malaysia first, and then reaching out internationally, minus the social component.

Each blog segment/category title will begin with a small “b” denoting that it is a blog with posts. The 8 blog segments/categories are titled as:

1. bMeetup – Blog posts on meetup sessions, an extension from the page “Meetup” with sub-segments or called sub-categories; this segment/category will cease to continue to carry posts on any meetup;

2. bRound-ups – Here in this blog segment/category, you will find list-style posts, posted weekly or monthly, all of them put together with a list of links to other blog posts recently posted in the medical records niche. Sure, it’s going to be a bit of a cop-out but I hope it keeps this blog segment blog fresh, and I hope to bring this blog to the attention of other bloggers in the medical records niche and give readers access to other material they might find interesting. I like these because they’re a way to show readers trends in what bloggers in a certain niche are talking about during a given week/month;

3. bBig-List – Big List blog segment/category is longer than the top ten types of lists. This is a compilation of a large number of resources that readers would be interested in, all in one place. It’s a segment showing lists my niche audience may frequently look for. I hope to help them find it;

4. bBig-Ten – Some people love them and some people hate them, but the top 10 lists everything medical records;

5. bReviews – Every niche has something that’s available to review. Review of books, services, products, other websites, and blogs for the medical records niche!;

6. bViews – Blog posts sharing my viewpoint on issues with links to the original news. It can be a great way to ignite some cross-blog or comment discussions;

7. bNews – Presenting a blog segment/category, sharing with readers of the detailed post(s), or just link(s) to the news source and a brief summary write up after news engines search for news on what’s going on in the medical records niche; and

8. bTechno – News on enabling technology affecting medical records management.

As I have hinted above, this website blog will no longer remain the domain for social contact, rather it moves into a professional discussion with blog posts from me allowing insights into developments in enabling technology, and news from many facets of the medical records and health information management niche.

To remind of its previous version of this website blog, the Meetup Page will remain available until further notice. Nonetheless, the Contacts Page is modified to allow new contacts to join the contacts list, both among HIM / MR practitioners in Malaysia and globally.

I must also add that given the limitations of a free blogging environment from WordPress.com, I am curtailed to keep within its confines, but I intend to keep the website blog as evolving as ever, considering the volatility of the changing and challenging times we live in.

Finally, the Uniform Resource Locator (URL) of this website-blog will remain as http://mrpalsmy.com/ so as not to lose it original identity and route. Thank you for being part of this website blog and do care to leave your comments after each blog post.

EHR data and AI to predict response to antidepressant treatment

Posted on 27/04/2023 by VIJAYAN RAGAVAN

Antidepressants are frequently prescribed for adults with depression, a common and often disabling psychiatric condition. However, identifying the most effective treatment for a particular patient is often a trial-and-error process that can result in prolonged morbidity, disability, and exposure to adverse effects, as well as substantial healthcare costs. Precision psychiatry aims to optimise treatment matching using patient-specific profiles, but there are few evidence-based predictors available to clinicians initiating antidepressant treatment.

Although average response rates are similar across different antidepressant classes, individual responses can vary widely in clinical practice. Therefore, accurately and scalably guiding antidepressant selection presents specific challenges. The gold standard for characterising antidepressant response from electronic health records (EHRs) remains expert chart review, which is labor- and time-intensive.

However, advances in machine learning (ML) and the growing availability of large-scale health data, such as EHRs, offer new opportunities for developing clinical decision-support tools that may address this challenge. In a recent study published in the peer-reviewed open-access medical journal Nature Partner Journals (npc) Digital Medicine, researchers used machine learning models to accurately predict differential treatment response probabilities for patients and between antidepressant classes based on real-world EHR data. The pipeline incorporated AI and non-AI features, as well as unstructured data (i.e. clinical notes) to maximize the use of information contained in EHRs.

The study included 17,556 patients who received a new antidepressant prescription from non-psychiatrists, and data were obtained from 20 years of EHRs spanning from January 1990 to August 2018. The patients had at least one International Classification of Diseases (ICD) code for depression and at least one ICD code for non-recurrent depression during their history.

ICD codes from EHR data were obtained for adult patients (age ≥ 18 years) with at least one visit (the first visit with an antidepressant prescription is defined as the “index visit” for each patient) with a diagnostic ICD code for a depressive disorder (defined as ICD-9-CM: 296.20–6, 296.30–6, and 311; ICD-10-CM: F32.0–9, F33.0–9) co-occurring with an antidepressant prescription, and at least one ICD code for non-recurrent depression (ICD-9-CM: 296.20–6 and 311; ICD-10-CM: F32.0–9) any time during their history.

The resulting models achieved good accuracy, discrimination, and positive predictive value, which could be valuable for further efforts aiming to provide clinical decision support for prescribers. However, the researchers noted several limitations, including missing data in EHRs(e.g. patients who may receive some of their care outside of the healthcare system), and secular trends in clinician prescribing or documentation practices that may have affected model performance.

In summary, the study presents a novel computational pipeline based on real-world EHR data for predicting differential responses to commonly used classes of antidepressants. The approach demonstrated here could be adapted to a wide variety of other clinical applications for optimising and individualising treatment selection.

REFERENCES:

Sheu, Yh., Magdamo, C., Miller, M. et al. AI-assisted prediction of differential response to antidepressant classes using electronic health records. npj Digit. Med. 6, 73 (2023). https://doi.org/10.1038/s41746-023-00817-8

About

Like this:

Recent Posts

EHR data and AI to predict response to antidepressant treatment

REFERENCES:

Like this:

Share this:

Like this:

Recent Posts

REFERENCES:

Share this:

Like this: