Modeling Blood Pressure Transitions Using an Integrated Multistate Markov Chain–Logistic Model with a Web-Based Application: Basis for Hypertension Prevention Programs

Allocation at minting

The anchored record

Canonical JSON (keys sorted, no spaces, UTF-8). Its SHA-256 is the hash on chain.

{"abstract":"This study aimed to model blood pressure transitions among 440 public school teachers in the Division of El Salvador City by integrating Multistate Markov Chain and Multinomial Logistic Regression models. A quantitative longitudinal design was employed using health records collected from 2021 to 2023. Data quality assessment showed that missing values across all demographics, lifestyle, clinical, and blood pressure variables were minimal, with proportions consistently below 5%, and these were effectively addressed using Random Forest imputation, preserving data structure and minimizing bias. Multistate Markov chain modeling was applied to estimate blood pressure state transitions and generate sex specific projections for 2025 to 2027. Results revealed distinct transition patterns by sex: male teachers were projected to remain predominantly in elevated and hypertensive blood pressure states, characterized by low normotensive stability and limited reversibility once hypertension developed, whereas female teachers exhibited greater stability in normal blood pressure and higher probabilities of reverting from elevated states. Across sexes, elevated blood pressure emerged as the central transitional state driving future hypertension risk. Model validation demonstrated adequate predictive accuracy, with no statistically significant differences observed between predicted and actual blood pressure distributions in 2023, indicating that the multistate Markov model effectively captured short-term blood pressure dynamics. Ridge penalized multinomial logistic regression identified smoking, medication use, body mass index, and age as significant factors influencing blood pressure state transitions, reflecting the combined influence of behavioral, clinical, and demographic determinants. To enhance practical applicability, the integrated modeling framework was implemented through a web-based blood pressure transition application that enables users to generate personalized projections from 2026 to 2030. Overall, the study provides a robust empirical foundation to support improved hypertension monitoring, early risk identification, and evidence-based prevention strategies among public school teachers.","abstract_source":"original","authors":["Rheil Evans Lunio","Jun Mark Rey Nob","Liza May Nob"],"date":"2026-06-07","doi":"10.70838/pemj.570705","id":8060,"issue":7,"journal":{"issn":"2822-4353","name":"Psychology and Education: A Multidisciplinary Journal"},"pdf_sha256":"951c0fda49e8379056f994955646e310955ec413f85770ed410f2db5a83a777c","schema":"scimatic-article/1","title":"Modeling Blood Pressure Transitions Using an Integrated Multistate Markov Chain–Logistic Model with a Web-Based Application: Basis for Hypertension Prevention Programs","volume":57}

Check it yourself

1. The record, from the token's own metadata:

printf '%s' "$(curl -s https://scimatic.org/nft/articles/8060.json | jq -r .canonical_record)" | sha256sum

2. The hash stored on chain (contentHash(8060)):

curl -s https://rpc.scimatic.net -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"eth_call","params":[{"to":"0x0E596B4bb924937aA35D9b342A90347ed6F05eF8","data":"0xf3e0c2900000000000000000000000000000000000000000000000000000000000001f7c"},"latest"]}'

The two must be equal (the second with a 0x in front).