Mateo Alzate Aguirre

Mateo Alzate Aguirre

Auto-generated profile, based on publicly available information

Mateo Alzate Aguirre

Ascension St. John Hospital, Detroit, MI, United States

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
24 February 2023 in JMIR Medical Informatics
Verified
Journal Article
Open access
SGSimon Gaviria-Valencia
Simon Gaviria-Valencia
SMSean P Murphy
Sean P Murphy
VKVinod C Kaggal
Vinod C Kaggal
RIRobert D McBane II
Robert D McBane II
TRThom W Rooke
Thom W Rooke
AAAdelaide M Arruda-Olson
Adelaide M Arruda-Olson
Background: Management of abdominal aortic aneurysms (AAAs) requires serial imaging surveillance to evaluate the aneurysm dimension. Natural language processing (NLP) has been previously developed to retrospectively identify patients with AAA from electronic health records (EHRs). However, there are no reported studies that use NLP to identify patients with AAA in near real-time from radiology reports. Objective: This study aims to develop and validate a rule-based NLP algorithm for near real-time automatic extraction of AAA diagnosis from radiology reports for case identification. Methods: The AAA-NLP algorithm was developed and deployed to an EHR big data infrastructure for near real-time processing of radiology reports from May 1, 2019, to September 2020. NLP extracted named entities for AAA case identification and classified subjects as cases and controls. The reference standard to assess algorithm performance was a manual review of processed radiology reports by trained physicians following standardized criteria. Reviewers were blinded to the diagnosis of each subject. The AAA-NLP algorithm was refined in 3 successive iterations. For each iteration, the AAA-NLP algorithm was modified based on performance compared to the reference standard. Results: A total of 360 reports were reviewed, of which 120 radiology reports were randomly selected for each iteration. At each iteration, the AAA-NLP algorithm performance improved. The algorithm identified AAA cases in near real-time with high positive predictive value (0.98), sensitivity (0.95), specificity (0.98), F1 score (0.97), and accuracy (0.97). Conclusions: Implementation of NLP for accurate identification of AAA cases from radiology reports with high performance in near real time is feasible. This NLP technique will support automated input for patient care and clinical decision support tools for the management of patients with AAA.

22 August 2022 in Journal of Medical Internet Research
Verified
Journal Article
Open access
MPMichelle Partogi
Michelle Partogi
SGSimon Gaviria-Valencia
Simon Gaviria-Valencia
MAMateo Alzate Aguirre
Mateo Alzate Aguirre
NPNancy Pick
Nancy Pick
Huzefa BhopalwalaHuzefa Bhopalwala
Huzefa Bhopalwala
AAAdelaide Arruda-Olson
Adelaide Arruda-Olson
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). Background: Clinical practice guidelines recommend antiplatelet and statin therapies, as well as blood pressure control and tobacco cessation for secondary prevention in patients with established atherosclerotic cardiovascular diseases (ASCVDs). However, these strategies for risk modification are underused especially in rural communities. Moreover, resources to support delivery of preventive care to rural patients are less than their urban counterparts. Transformative interventions for delivery of tailored preventive cardiovascular care to rural patients are needed. Objective: A multidisciplinary team developed a rural-specific, team-based care intervention assisted by clinical decision support (CDS) technology using participatory design in a sociotechnical conceptual framework. The intervention included redesigned workflows and a novel CDS technology for coordination and delivery of guideline recommendations by primary care teams in a rural clinic. Methods: Intervention design was comprised of three phases: (I) problem identification, (II) experimentation and (III) testing. Input from team members (n=35) required 150 hours, including observations of clinical encounters, provider workshops and interviews of patients and health care professionals. The intervention was prototyped, iteratively refined, and tested with user feedback. In a three-month pilot trial, 369 ASCVD patients were randomized to control or intervention arms. Results: New workflows and a novel CDS tool were created to identify ASCVD patients with gaps in preventive care and assign the right care team member for delivery of tailored recommendations. During the pilot the intervention prototype was iteratively refined and tested. The pilot demonstrated feasibility for successful implementation of the sociotechnical intervention as the proportion of patients who had encounters with advance practice providers (nurse practitioners/physician assistants), pharmacists, or tobacco cessation coaches for delivery of guideline recommendations in the intervention arm was greater compared to the control arm. Conclusions: Participatory design and a sociotechnical conceptual framework enabled development of a rural-specific, team-based care intervention assisted by CDS technology for transformation of preventive health care delivery for ASCVDs.

28 March 2025 in JMIR Cardio
Verified
Journal Article
Open access
GFGayle L Flo
Gayle L Flo
MAMateo Alzate Aguirre
Mateo Alzate Aguirre
BGBenjamin R Gochanour
Benjamin R Gochanour
KHKristin J Hynes
Kristin J Hynes
CSChristopher Scott
Christopher Scott
AAAdelaide M Arruda-Olson
Adelaide M Arruda-Olson
Background: Clinical guidelines recommend high-intensity statin therapy for patients with acute coronary syndrome (ACS). However, high-intensity statins have been underused in this population. Objective: The objective of this study was to evaluate the feasibility of a pharmacist-initiated, team-based intervention for the delivery of individualized, guideline-directed, lipid-lowering therapy for patients with ACS. Methods: Patients admitted with ACS to cardiology hospital services at Mayo Clinic from August 1, 2021, to June 19, 2022, were assigned to a pharmacist-initiated, team-based intervention group or control group using a stepped wedge cluster study design. For the intervention group, pharmacists reviewed electronic health records and provided recommendations for lipid lowering therapy in hospital and at follow-up. In the control group, patients received usual care. Neither care team, nor study team were blinded to study assignments. The primary outcome was the proportion of patients with ACS discharged on high-intensity statins in the intervention group compared to controls. Secondary outcomes were (1) proportion of patients in the intervention group with a specific templated pharmacist intervention note in their electronic health records, (2) frequency of low-density lipoprotein (LDL) measurements in hospital, (3) proportion of patients with information related to lipid follow-up in their discharge summary, and (4) proportion of patients that received LDL monitoring at the outpatient follow-up 4 to 12 weeks post discharge. Results: There were 410 patients included in this study (median age 68, IQR 60-78 years) of whom 285 (69.5%) were male. Of the 402 patients alive at discharge, 355 (88.3%) were discharged taking a high-intensity statin, with no significant difference (P=.89) observed between groups. Lipid levels were measured in the hospital for 176/210 (83.8%) patients in the intervention group and 155/200 (77.5%) patients in the control group (P=.14). Fifty-four of 205 (26.3%) intervention patients alive at discharge had lipid-related recommendations in their discharge summary compared to 27/197 (13.7%) controls (P=.002). Forty-seven of 81 (58%) patients with lipid management recommendations provided in the discharge summary had LDL measured in the follow-up period compared with only 119/321 (37.1%) patients without these recommendations (P=.001). Of the 402 patients who survived to discharge, 166 (41.3%) had LDL measured at follow-up; the median LDL level was 63.5 (IQR 49-79) mg/dL, and distributions were similar by group (P=.95). Only 101/166 (60.8%) patients had follow-up LDL values below the target of 70 mg/dL. Conclusions: During hospitalization, there was no group difference in the primary outcome of high-intensity statin therapy. Feasibility of an effective pharmacist-initiated intervention for improvement of lipid management was demonstrated by entry of recommendations in the discharge summary and related adjustment in outpatient statin therapy. The main opportunity for future improvement in lipid management of patients with ACS is in longitudinal patient follow-up.

11 July 2022 in JMIR Preprints
Verified
Preprint
Open access
SGSimon Gaviria-Valencia
Simon Gaviria-Valencia
SMSean P Murphy
Sean P Murphy
VKVinod C Kaggal
Vinod C Kaggal
RIRobert D McBane II
Robert D McBane II
TRThom W Rooke
Thom W Rooke
AAAdelaide M Arruda-Olson
Adelaide M Arruda-Olson
BACKGROUND Management of abdominal aortic aneurysms (AAAs) requires serial imaging surveillance to evaluate the aneurysm dimension. Natural language processing (NLP) has been previously developed to retrospectively identify patients with AAA from electronic health records (EHRs). However, there are no reported studies that use NLP to identify patients with AAA in near real-time from radiology reports. OBJECTIVE This study aims to develop and validate a rule-based NLP algorithm for near real-time automatic extraction of AAA diagnosis from radiology reports for case identification. METHODS The AAA-NLP algorithm was developed and deployed to an EHR big data infrastructure for near real-time processing of radiology reports from May 1, 2019, to September 2020. NLP extracted named entities for AAA case identification and classified subjects as cases and controls. The reference standard to assess algorithm performance was a manual review of processed radiology reports by trained physicians following standardized criteria. Reviewers were blinded to the diagnosis of each subject. The AAA-NLP algorithm was refined in 3 successive iterations. For each iteration, the AAA-NLP algorithm was modified based on performance compared to the reference standard. RESULTS A total of 360 reports were reviewed, of which 120 radiology reports were randomly selected for each iteration. At each iteration, the AAA-NLP algorithm performance improved. The algorithm identified AAA cases in near real-time with high positive predictive value (0.98), sensitivity (0.95), specificity (0.98), F1 score (0.97), and accuracy (0.97). CONCLUSIONS Implementation of NLP for accurate identification of AAA cases from radiology reports with high performance in near real time is feasible. This NLP technique will support automated input for patient care and clinical decision support tools for the management of patients with AAA.