Electronic Medical Records Research Articles

Examining Whether Patient Portal and Video Visit Use Differs by Race and Ethnicity Among Older Adults in a US Integrated Health Care Delivery System: Cross-Sectional Electronic Health Record and Survey-Based Study.

Health care systems are increasingly encouraging patients to use patient portals and participate in video visits. However, there is limited information about how portal use differs among older adults. This study aimed to understand how patient portal and video visit use differed by age, race, and ethnicity among older adult patients with access to the same digital health resources. This cross-sectional study used electronic health record and survey data for adults aged 65 to 85 years who were members of a large Northern California health care delivery system throughout 2019 and 2020. The electronic health record cohort (N=471,152) included 320,686 White, 35,892 Black, 44,922 Latino, 20,786 Chinese, 28,732 Filipino, 8473 South Asian, 6716 Japanese, 2930 Vietnamese, and 2015 Korean adults. Racial and ethnic group and age group (65 to 75 years vs 76 to 85 years) differences in having a patient portal account by December 2020, the performance of 2 portal activities (sending ≥1 message to a clinician in 2019 or 2020 and viewing ≥1 laboratory test result in 2020), and having ≥1 video visit during 2020 were examined. Modified log-Poisson regression was used to examine prevalence ratios for portal and video visit use, comparing racial and ethnic groups to White adults and Asian ethnic groups to Chinese adults after adjusting for sex and age. Data from a 2020 member survey were used to compare internet use factors among 2867 White, 306 Black, 343 Latino, 225 Chinese, and 242 Filipino adults. Black, Latino, and Filipino adults were less likely to have a patient portal account than White adults, and Filipino adults were less likely to have a patient portal account than Chinese adults. Black, Latino, Filipino, Korean, Vietnamese, and South Asian adults were less likely to have sent messages and viewed test results than White adults, while Chinese and Japanese adults' use of these features was similar to that of White adults. Filipino, Vietnamese, and Korean adults were less likely to have performed the aforementioned activities than Chinese adults. Video visit use was lower among Black and Latino adults and higher among Chinese and South Asian adults compared with White adults (aged 76 to 85 years) and lower among Filipino, Korean, and Vietnamese adults compared to Chinese adults. Survey data suggested that underlying differences in internet use may partially explain the lower use of messaging by Black, Latino, and Filipino adults compared with White and Chinese adults. Patient portal and video visit use differed by race, ethnicity, and age group among older adult patients with access to the same patient portal. Internet use factors may contribute to these differences. Differences in patient portal and video visit use across Asian subgroups underscore the importance of disaggregating use data by Asian ethnicity.

Identification of atypical pediatric diabetes mellitus cases using electronic medical records

IntroductionThere are no established methods to identify children with atypical diabetes for further study. We aimed to develop strategies to systematically ascertain cases of atypical pediatric diabetes using electronic medical...

Pronouns in the Electronic Medical Record: A Potential Pitfall

Pronouns in the Electronic Medical Record: A Potential Pitfall

Predictive Factors for Clean Intermittent Catheterization after Intravesical OnabotulinumtoxinA Injections in Women with Overactive Bladder: a Danish Retrospective Cohort Study.

We aimed to evaluate the clean intermittent catheterization (CIC) rate in women undergoing their first OnabotulinumtoxinA (BTX-A) treatment and to investigate factors predictive of initiating CIC. This was a retrospective cohort of women, who had their first BTX-A treatment for symptoms of overactive bladder (OAB) syndrome, with a pretreatment urodynamic study (UDS). We reviewed demographic, medical and gynecological history, UDS, pretreatment bladder diaries, objective examinations, BTX-A treatment details, and post-void residual (PVR) reports in the electronic medical record. Botox® Allergan 100 International Units were injected into the detrusor at 10-20 sites. Statistical analyses included univariate and multivariate logistic regression analyses. We included 397 women. Median age was 68 (Q1-Q3: 54-76) years. CIC rate was 8.6% (n = 34) following the first BTX-A treatment. Urgency urinary incontinence (UUI) reduced the risk of undergoing CIC (OR 0.30, 95% CI 0.09-0.97). A bladder capacity of 500ml or greater in the bladder diary increased the risk of CIC (OR 2.46, 95% CI 1.06-5.70), whereas reported leakages were associated with a decreased risk of CIC (OR 0.24, 95% CI 0.10-0.57). Multivariate logistic regression analysis showed that anterior colporrhaphy (OR 3.71, 95% CI 1.52-9.06) and 10-ml increments in median maximum cystometric capacity (OR 1.03, 95% CI 1.00-1.06) predicted CIC, whereas UUI was a protective factor for CIC (OR 0.23, 95% CI 0.07-0.79). A history of anterior colporrhaphy, large bladder capacity, and absence of incontinence episodes in bladder diary or UDS were risk factors for CIC after the first BTX-A treatment.

Special Section on Patient-Reported Outcomes and Informatics: Collection of Patient-Reported Outcome Measures in Rural and Underserved Populations.

The NIH Pragmatic Trials Collaboratory supports the design and conduct of 31 embedded pragmatic clinical trials, and many of these trials use patient-reported outcome measures (PROMs) to provide valuable information about their patients' health and wellness. Often these trials enroll medically underserved patients, including people with incomes below the federal poverty threshold, racial or ethnically minoritized groups, or rural or frontier communities. In this series of trial case reports, we provide lessons learned about collecting PROMs in these populations. The unbiased collection of PROM data is critical to increase the generalizability of trial outcomes and to address health inequities. Use of electronic health records (EHRs) and other digital modes of PROM administration have gained traction. However, engagement with these modes is often low among disparities prone populations due to lessened digital proficiency, device access, and uptake of EHR portals and web interfaces. To maximize the completeness and representativeness of their trial outcome data, study teams tested a range of strategies to improve PROM response rates with emphasis on disparities prone and underserved patient groups. This manuscript describes the approaches, their implementation, and the targeted populations. Optimized PROM collection required hybrid approaches with multiple outreach modes, high-touch methods, creativity in promoting digital uptake, multi-modal participant engagement, and text messaging.

Applying Natural Language Processing to Electronic Health Record Data—From Text to Triage

Applying Natural Language Processing to Electronic Health Record Data—From Text to Triage

Postpartum Acute Care Utilization in a Health Care System in the Southeastern United States.

Introduction: Postpartum acute care utilization (PACU), including visits to an emergency department, obstetric triage, or urgent care ("outpatient"), and hospital readmissions, may indicate medical complications and signal unmet health needs. Methods: We estimated the incidence of PACU and examined patterns by sociodemographic factors, pregnancy and birth characteristics, time since discharge from the birth hospitalization, and medical indications. We constructed a retrospective cohort of people aged ≥18 years who delivered ≥1 liveborn infant >20 weeks of gestation from July 1, 2021, to December 31, 2022, using electronic health record data from a quaternary maternity hospital in the Southeastern United States PACU data throughout the health care system were collected through March 31, 2023. We excluded people with a hospital stay >6 days (n = 29). Results: In this cohort of 6,041 birthing people, 11.3% had ≥1 outpatient encounters(range 0-6) and 3.2% had ≥1 hospital readmissions (range 0-4) within 12 weeks of discharge from the birth hospitalization. Median time to first outpatient PACU was 10 days post-discharge and 6 days for first hospital readmission. Among encounters for the top five medical indications, time to first postpartum acute care encounter varied by medical indication (log-rank test of equality over strata Chi-square = 69.93, degrees of freedom = 4, p < 0.0001). Complications specified during the puerperium (n = 234) and hypertension and hypertensive-related conditions complicating the puerperium (n = 87) were the two most frequent indications. Conclusion: These findings can inform efforts to direct health resources to improve postpartum health care and health outcomes.

Disparities in cervical cancer screening rates and electronic health record completeness among All of Us Research Program participants

Disparities in cervical cancer screening rates and electronic health record completeness among All of Us Research Program participants

Eliminating Error in Central Line Scheduling and Placement Using Quality Improvement Methods.

The Joint Commission defines a sentinel event as "surgery or other invasive procedure performed at the wrong site, on the wrong patient, or that is the wrong (unintended) procedure for a patient regardless of the type of procedure or the magnitude of the outcome." At our institution, we observed a low but consistent rate of incorrect surgical line placement for pediatric patients with cancer. Following quality improvement methodology and using the resources available on a large academic medical campus we designed and implemented a new multi-factorial process to schedule and place surgical central lines for pediatric patients with cancer. Changes included re-defining responsibilities, adding staff, and redesigning the process with workflows supported by modifications to the electronic medical record. Our primary outcome measures were incorrect central line placement or near miss event per quarter and days between these events. After implementation the rate of incorrect line placement and near miss events was reduced to zero with 1018 days since the last incorrect line placement. As a result of our multi-factorial quality improvement initiative in the scheduling and placement of central lines, we were able to eliminate surgical line placement sentinel events and improve care for pediatric patients with cancer.

Algorithms for the identification of prevalent diabetes in the All of Us Research Program validated using polygenic scores

The All of Us Research Program (AoU) is an initiative designed to gather a comprehensive and diverse dataset from at least one million individuals across the USA. This longitudinal cohort study aims to advance research by providing a rich resource of genetic and phenotypic information, enabling powerful studies on the epidemiology and genetics of human diseases. One critical challenge to maximizing its use is the development of accurate algorithms that can efficiently and accurately identify well-defined disease and disease-free participants for case-control studies. This study aimed to develop and validate type 1 (T1D) and type 2 diabetes (T2D) algorithms in the AoU cohort, using electronic health record (EHR) and survey data. Building on existing algorithms and using diagnosis codes, medications, laboratory results, and survey data, we developed and implemented algorithms for identifying prevalent cases of type 1 and type 2 diabetes. The first set of algorithms used only EHR data (EHR-only), and the second set used a combination of EHR and survey data (EHR+). A universal algorithm was also developed to identify individuals without diabetes. The performance of each algorithm was evaluated by testing its association with polygenic scores (PSs) for type 1 and type 2 diabetes. We demonstrated the feasibility and utility of using AoU EHR and survey data to employ diabetes algorithms. For T1D, the EHR-only algorithm showed a stronger association with T1D-PS compared to the EHR + algorithm (DeLong p-value = 3 × 10−5). For T2D, the EHR + algorithm outperformed both the EHR-only and the existing T2D definition provided in the AoU Phenotyping Library (DeLong p-values = 0.03 and 1 × 10−4, respectively), identifying 25.79% and 22.57% more cases, respectively, and providing an improved association with T2D PS. We provide a new validated type 1 diabetes definition and an improved type 2 diabetes definition in AoU, which are freely available for diabetes research in the AoU. These algorithms ensure consistency of diabetes definitions in the cohort, facilitating high-quality diabetes research.

Electronic Health Record Data Quality and Performance Assessments: Scoping Review.

Electronic health records (EHRs) have an enormous potential to advance medical research and practice through easily accessible and interpretable EHR-derived databases. Attainability of this potential is limited by issues with data quality (DQ) and performance assessment. This review aims to streamline the current best practices on EHR DQ and performance assessments as a replicable standard for researchers in the field. PubMed was systematically searched for original research articles assessing EHR DQ and performance from inception until May 7, 2023. Our search yielded 26 original research articles. Most articles had 1 or more significant limitations, including incomplete or inconsistent reporting (n=6, 30%), poor replicability (n=5, 25%), and limited generalizability of results (n=5, 25%). Completeness (n=21, 81%), conformance (n=18, 69%), and plausibility (n=16, 62%) were the most cited indicators of DQ, while correctness or accuracy (n=14, 54%) was most cited for data performance, with context-specific supplementation by recency (n=7, 27%), fairness (n=6, 23%), stability (n=4, 15%), and shareability (n=2, 8%) assessments. Artificial intelligence-based techniques, including natural language data extraction, data imputation, and fairness algorithms, were demonstrated to play a rising role in improving both dataset quality and performance. This review highlights the need for incentivizing DQ and performance assessments and their standardization. The results suggest the usefulness of artificial intelligence-based techniques for enhancing DQ and performance to unlock the full potential of EHRs to improve medical research and practice.

Leveraging the Electronic Health Record to Measure Resident Clinical Experiences and Identify Training Gaps: Development and Usability Study.

Competence-based medical education requires robust data to link competence with clinical experiences. The SARS-CoV-2 (COVID-19) pandemic abruptly altered the standard trajectory of clinical exposure in medical training programs. Residency program directors were tasked with identifying and addressing the resultant gaps in each trainee's experiences using existing tools. This study aims to demonstrate a feasible and efficient method to capture electronic health record (EHR) data that measure the volume and variety of pediatric resident clinical experiences from a continuity clinic; generate individual-, class-, and graduate-level benchmark data; and create a visualization for learners to quickly identify gaps in clinical experiences. This pilot was conducted in a large, urban pediatric residency program from 2016 to 2022. Through consensus, 5 pediatric faculty identified diagnostic groups that pediatric residents should see to be competent in outpatient pediatrics. Information technology consultants used International Classification of Diseases, Tenth Revision (ICD-10) codes corresponding with each diagnostic group to extract EHR patient encounter data as an indicator of exposure to the specific diagnosis. The frequency (volume) and diagnosis types (variety) seen by active residents (classes of 2020-2022) were compared with class and graduated resident (classes of 2016-2019) averages. These data were converted to percentages and translated to a radar chart visualization for residents to quickly compare their current clinical experiences with peers and graduates. Residents were surveyed on the use of these data and the visualization to identify training gaps. Patient encounter data about clinical experiences for 102 residents (N=52 graduates) were extracted. Active residents (n=50) received data reports with radar graphs biannually: 3 for the classes of 2020 and 2021 and 2 for the class of 2022. Radar charts distinctly demonstrated gaps in diagnoses exposure compared with classmates and graduates. Residents found the visualization useful in setting clinical and learning goals. This pilot describes an innovative method of capturing and presenting data about resident clinical experiences, compared with peer and graduate benchmarks, to identify learning gaps that may result from disruptions or modifications in medical training. This methodology can be aggregated across specialties and institutions and potentially inform competence-based medical education.

"Pushed to Their Limits": Health Care Provider Perspectives on Barriers and Facilitators to Implementing a Mind-Body and Activity Program for Older Adults With Chronic Pain in a Community Clinic for the Underserved.

Older adults from underserved backgrounds experience chronic pain at a rate of 60% to 75%. Pharmacological treatments have limited efficacy and involve considerable risks. Mind-body interventions hold promise to improve pain outcomes but are typically not implemented in community clinics in which they are needed most, thus contributing to health disparities in chronic pain treatment. We conducted qualitative focus groups and interviews with 20 providers (eg, primary care doctors, nurses, administrators). We sought their perspectives on barriers and facilitators to implementing an evidence based mind-body activity program for older adults with chronic pain at an underserved community health clinic in Massachusetts. Subthemes were identified within 2 superordinate domains (barriers and facilitators) using a hybrid inductive-deductive thematic analysis approach following the Framework Method. Providers discussed facilitators (partner with clinic staff to facilitate referrals and buy-in, integrate referrals through the electronic medical record, offer groups in different languages, post and tailor advertisements) and barriers (limited staff bandwidth, scheduling challenges, inconsistent patient participation). These results will directly inform tailoring and subsequent effectiveness testing and implementation of the pain management program for older underserved adults with chronic pain in this community health care setting.

Trending in the right direction: critical access hospitals increased adoption of advanced electronic health record functions from 2018 to 2023.

We analyzed trends in adoption of advanced patient engagement and clinical data analytics functionalities among critical access hospitals (CAHs) and non-CAHs to assess how historical gaps have changed. We used 2014, 2018, and 2023 data from the American Hospital Association Annual Survey IT Supplement to measure differences in adoption rates (ie, the "adoption gap") of patient engagement and clinical data analytics functionalities across CAHs and non-CAHs. We measured changes over time in CAH and non-CAH adoption of 6 "core" clinical data analytics functionalities, 5 "core" patient engagement functionalities, 5 new patient engagement functionalities, and 3 bulk data export use cases. We constructed 2 composite measures for core functionalities and analyzed adoption for other functionalities individually. Core functionality adoption increased from 21% of CAHs in 2014 to 56% in 2023 for clinical data analytics and 18% to 49% for patient engagement. The CAH adoption gap in both domains narrowed from 2018 to 2023 (both P < .01). More than 90% of all hospitals had adopted viewing and downloading electronic data and clinical notes by 2023. The largest CAH adoption gaps in 2023 were for Fast Healthcare Interoperability Resources (FHIR) bulk export use cases (eg, analytics and reporting: 63% of CAHs, 81% of non-CAHs, P < .001). Adoption of advanced electronic health record functionalities has increased for CAHs and non-CAHs, and some adoption gaps have been closed since 2018. However, CAHs may continue to struggle with clinical data analytics and FHIR-based functionalities. Some crucial patient engagement functionalities have reached near-universal adoption; however, policymakers should consider programs to support CAHs in closing remaining adoption gaps.

Prediction of Healing Trajectory of Chronic Wounds Using a Machine Learning Approach.

Objective: New treatment options are emerging for chronic wounds, which represent a growing problem because of population ageing and increasing burden of chronic disease. While promising, the existing evidence for advanced modalities is commonly derived from small and/or poorly controlled studies and clear criteria for selecting patients, who are likely to benefit from these expensive options are lacking. In this study, we develop and validate a machine learning model to predict if a chronic wound, independent of etiology, is expected to heal within 12 weeks to identify cases in potential need of advanced treatment options. Approach: Retrospective analysis of electronic health record data from 2014 to 2018 covering 532 wound care clinics in the United States and 261,398 patients with 620,356 unique wounds. Prediction of 12-week healing trajectories with a machine learning model. Results: The best-performing model in a training dataset of a randomly drawn 75% subset of wounds contained variables for patient demographics, comorbidities, wound characteristics at initial presentation, and changes in wound dimensions over time, with the latter group being the most influential predictors. The final machine learning model had a high predictive accuracy with area under the receiver operating characteristic curves of 0.9 and 0.92 after 4 and 5 weeks of treatment, respectively. Innovation: A machine learning model can identify chronic wounds at risk of not healing by week 12 with high accuracy in the early weeks of treatment. Conclusions: If embedded in real-world care, the generated information could be able to guide effective and efficient treatment decisions.

Evaluation of Comprehensive Documentation After Obstetric Anal Sphincter Injury.

The incidence of obstetric anal sphincter injuries (OASI) has increased in recent years, which may be due to improved recognition and documentation. There is limited evidence regarding the effects of thorough documentation of obstetric anal sphincter injury repairs on postpartum clinical outcomes. Our objectives were to (1) compare the incidence of perineal wound complications between documentation groups, (2) compare other adverse events, and (3) to describe factors associated with adequate documentation. We hypothesized that better documentation would be associated with improved clinical outcomes. This was a retrospective cohort study of 599 patients with OASI at a tertiary care referral center between January 2015 and December 2020. A priori definitions of documentation adequacy were utilized to stratify delivery notes. On the basis of these criteria, there were preferred, adequate, and inadequate documentation groups. Maternal characteristics, outcomes, and peripartum factors were compared between the groups. There were no significant differences in clinical outcomes between the groups. A higher degree of perineal laceration (p < 0.001), greater blood loss (p = 0.002), and the need for repairs in the operating room (p = 0.019) were significant factors associated with adequate documentation. Clinicians who were comprehensive in their documentation were more likely to refer patients to Urogynecology (p < 0.001) and to add OASI to the electronic medical record problem list (p = 0.005). While certain factors are associated with adequate documentation, this did not improve clinical outcomes for OASI and further research is warranted to explore the importance of medical documentation surrounding OASI.

An Artificial Intelligence-Based Gout Management System Reduced Chronic Kidney Disease Incident and Improved Target Serum Urate Achievement

Abstract Objectives Stage ≥ 3 chronic kidney disease (CKD) affects ∼25% of people with gout. The effects of urate-lowering therapy (ULT) on CKD incidence and progression have remained inconclusive. Here, we assessed the impact of a gout urate-lowering therapy (ULT) clinic intervention using artificial intelligence (AI) on CKD incidence and achievement of serum urate target. Methods An observational study compared propensity score-matched gout cohorts from an AI-based Gout Intelligent Management System (GIMS) and a standard Electronic Medical Records system (EMRS) clinic database. The GIMS included a mobile application, data fusion interface, and modules for expert consultation and laboratory results management. All patients had gout and a starting eGFR &amp;gt; 60 ml/min. Using a 1:2 propensity score (PS)-matched cohort study design we assessed the impact of the AI-based system on CKD outcomes and ULT effectiveness over 4 years of follow-up. Results Compared with EMRS, GIMS was associated with reduced incidence of CKD stage ≥ 3. Specifically, 169/4117 new onset CKD stage ≥ 3 (incidence 4.1 per 100 person-years) with GIMS compared with 164/2128 with EMRS (incidence 7.7 per 100 person-years) during follow-up. More participants achieved serum urate &amp;lt;6.0 mg/dl with GIMS vs EMRS during follow-up (49.8% vs 25.9%, p &amp;lt; 0.001). Conclusion Application of the AI-based GIMS was associated with lower incidence of CKD stage ≥ 3 and superior target serum urate achievement in people with gout. The AI-based GIMS represents a novel approach to improve real-world renal outcomes and ULT success in gout.

Preoperative Narcotic Education in Spine Surgery: A Retrospective Study

Background/Objectives: The objective of this study was to determine whether preoperative opioid education reduces opioid consumption after spine surgery and which educational methods are the most effective. Orthopedists are the most likely to prescribe opioids among all specialists. To alleviate the prescription opioid crisis, studies have identified ways to taper narcotic dosage and use following surgery. The role of preoperative education and its varying modalities on opioid consumption following spine surgery has yet to be reported in the literature. Methods: The study group received formal education describing the use of opioids, side effects, and alternatives to pain management. Patients were to choose their preferred modality of a 2 min narrated video and two handouts to be watched and read in their individual time, attending a small class led by a physician assistant where they watched the 2 min narrated video along with reading the two handouts or receiving a one-on-one session with the treating spine surgeon. Meanwhile, the control group received standard preoperative education. Refill prescriptions were collected from patients’ electronic medical record charts at the 2-week, 1-month, 3-month, and 6-month postoperative follow-ups. The primary outcome measure was morphine equivalents (MME) of prescription opioids at six months following spine surgery. Results: At 2 weeks postoperatively, there were no statistically significant differences between patients who received any formal narcotic education and those who did not. At 1 and 3 months postoperatively, the video education group (p-value &lt; 0.001), class education group (p-value &lt; 0.001), and the one-on-one education group (p-value &lt; 0.05) all had significant reductions in opioid consumption. At 6 months postoperatively, only the video education group (p-value &lt; 0.001) and the class education group (p-value &lt; 0.01) had significant reductions in opioid consumption. Conclusions: A two-fold approach with a video and handouts significantly decreases the prescription dosage at six months postoperatively and allows for early opioid cessation after undergoing spine surgery.

Incidence and Risk Factors of Infection After Fracture Fixation: A Multicenter Cohort Study.

Infection after fracture fixation (IAFF) is a severe complication. There are few multicenter studies targeting IAFF. This paper identifies independent risk factors associated with IAFF by analyzing multicenter clinical data. Appropriate interventions should be implemented to reduce the risk of IAFF. This is a multicenter retrospective cohort study. This study screened medical records of patients who underwent internal fixation for fractures at participating medical institutions from January 1, 2011, to December 31, 2020. Data extraction included demographic characteristics, disease features, surgical variables, and laboratory indicators. Logistic regression analysis was employed to identify the relationship between relevant risk factors and IAFF. Research data were sourced from the hospital's electronic medical record system and self-constructed databases. In our study, 202 patients who underwent internal fixation for fractures experienced postoperative infections, which corresponds to an overall incidence rate of approximately 1.7%. The predominant pathogen identified in these infections was Staphylococcus aureus. A multifactorial analysis indicated that several factors were independently associated with the occurrence of IAFF. These factors included BMI ranges of 24.0-27.9 and 28.0-31.9, smoking, a high ASA score, high-energy trauma, diabetes, open fracture, seasonal timing of the surgery (summer), bone grafting, drainage duration, surgical duration ≥ 180 min, and A/G ratio < 1.2. We strongly recommend that orthopedic surgeons perform comprehensive preoperative assessments on fracture patients to identify factors that may increase the risk of infection. Through the implementation of targeted interventions and beneficial modifications to these modifiable risk factors, it is possible to lower the incidence of IAFF. Additionally, proactive screening, risk stratification, and thorough patient education should be prioritized for patients with high risk but nonmodifiable factors.

Patient-specific multifactorial mortality risk assessment using classification and regression tree analysis in the context of ambulatory blood pressure monitoring.

Ambulatory blood pressure monitoring is essential for understanding blood pressure patterns beyond clinical visits, aiding in risk assessment, treatment evaluation, and managing hypertension. This retrospective cohort study aimed to identify risk factors for all-cause mortality and major cardiovascular events in patients who underwent ambulatory blood pressure monitoring. Eligible participants aged 18 or older, with an estimated glomerular filtration rate (eGFR) > 60ml/min/1.73m2, who underwent ambulatory blood pressure monitoring for various reasons, were included in the study. Data were gathered through telephone interviews, electronic health records, and the national health record system. Descriptive analysis and classification and regression tree modeling were used to uncover significant risk factors related to all-cause mortality and cardiovascular events, and to assess the model's performance compared to traditional Cox survival analysis. The study included 1291 patients, primarily male (51.8%) with a mean age of 61.1 ± 15.2years. During a mean follow-up of 46.9months, 76 (5.9%) patients died of any cause, and 195 (15.1%) had a cardiovascular event. The highest survival rates were observed in patients with a diastolic blood pressure (BP) dipping percentage between -2% and 29%, nighttime systolic BP variability below 32mmHg, and age below 72. Conversely, smokers with a diastolic BP dipping percentage below -10% showed the lowest survival rates. The best cardiovascular outcomes were observed in patients with diastolic BP dipping above -11%, nighttime mean systolic BP < 144mmHg, no statin use, normotensive status, and daytime mean heart rate ≥ 60bpm. Conversely, the worst outcomes were seen in patients with diastolic BP dipping below -11% and a morning surge ≥ 14mmHg. In all-cause mortality and cardiovascular event analysis, the combined model demonstrated excellent calibration and predictive power, like the classification and regression tree model and traditional analysis. These findings highlight the potential of a combined model for assessing mortality and cardiovascular event risk in patients who have undergone ambulatory blood pressure monitoring.