https://drpwchen.com/en/categories/evidence-based-medicine/Recent content in Evidence-Based Medicine on Po-Wei Chen, MD — Physiatrist & Builderhttps://drpwchen.com/og-default.pnghttps://drpwchen.com/og-default.pngHugoenSun, 30 Jun 2024 13:31:27 +0000https://drpwchen.com/en/posts/ebm-post-hoc-power-analysis/Fri, 11 Nov 2022 09:26:00 +0000https://drpwchen.com/en/posts/ebm-post-hoc-power-analysis/Calculating post-hoc power when statistics are non-significant is actually a misleading practice: it's inherently tied to the p-value. When p > 0.05, post-hoc power will inevitably be low—the two are basically circular reasoning. A more practical alternative is to interpret the 95% confidence interval alongside MCID, which aligns with the latest 2022 Cochrane GRADE guidelines.https://drpwchen.com/en/posts/systematic-review-workshop-1-pico/Thu, 13 Dec 2018 06:43:00 +0000https://drpwchen.com/en/posts/systematic-review-workshop-1-pico/PICO is actually only suitable for therapeutic studies. For diagnostic studies, change it to PIGO (adding Gold standard); for harmfulness studies, use PEO (random assignment is impossible due to ethical concerns); for prognostic studies, just PO is needed. This was the most rewarding lesson from Prof. Edwin Chan of Cochrane Singapore's workshop. You need to figure out the study type before setting your keywords so your search can be precise.https://drpwchen.com/en/posts/systematic-review-workshop-2-search/Wed, 12 Dec 2018 11:55:00 +0000https://drpwchen.com/en/posts/systematic-review-workshop-2-search/Getting only 5 papers in your search results doesn't mean your search was highly accurate—you might have missed a lot of important articles instead. When you get too many results, use title search, filter, and NOT to narrow things down; when there are too few, use MeSH terms, similar articles, or free text to broaden your criteria. Mastering the trade-off between sensitivity and specificity is the only way to find the literature you actually need.