J. Eric Jelovsek’s research while affiliated with Duke University Medical Center and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (174)


Validation and Recalibration of a Model for Predicting Surgical-Site Infection After Pelvic Organ Prolapse Surgery
  • Article

January 2025

·

5 Reads

International Urogynecology Journal

Stephen Rhodes

·

Amine Sahmoud

·

J. Eric Jelovsek

·

[...]

·

The objective was to externally validate and recalibrate a previously developed model for predicting postoperative surgical-site infection (SSI) after pelvic organ prolapse (POP) surgery. This study utilized a previously validated model for predicting post-POP surgery SSI within 90 days of surgery using a Medicare population. For this study, the model was externally validated and recalibrated using the Premier Healthcare Database (PHD) and the National Surgical Quality Improvement Project (NSQIP) database. Discriminatory performance was assessed via the c-statistic and calibration was assessed using calibration curves. Methods of recalibration in the large and logistic recalibration were used to update the models. The PHD contained 420,277 POP procedures meeting the inclusion criteria and 1.6% resulted in SSI. The NSQIP dataset contained 62,553 POP surgeries and 1.4% resulted in SSI. Discrimination of the original model was comparable with that seen in the initial validation (c-statistic = 0.57 in PHD, 0.59 in NSQIP vs 0.60 in the original Medicare data). Recalibration greatly improved model calibration when evaluated in NSQIP data. A previously developed model for predicting SSI after POP surgery demonstrated stable discriminatory ability when externally validated on the PHD and NSQIP databases. Model recalibration was necessary to improve prediction. Prospective studies are needed to validate the clinical utility of such a model.


FIGURE 1 | Radar plots of identified clusters. The most statistically significant different across clusters variables were identified and built into a radar plot to give a visual representation of the distinct symptom signatures for each cluster. Variables were normalized to the mean (SD) of the full cohort of male participants. The mean of the full cohort is represented as the black circle on the radar plots. Values outside of the circle indicate higher levels of symptoms than the full cohort, while values inside the circle indicate lower levels of symptoms than the full cohort. All values have been scaled so higher values represent worse or more severe symptoms.
FIGURE 4 | Affected pathways and affected gene ontology processes highlighted by differentially abundant proteins, as defined in a MetaCore enrichment analysis.
Symptom status at 12 months compared with baseline, using the overall LUTS Tool severity score.
Differentially abundant proteins identified overall and within each cluster. a
Phenotyping Men With Lower Urinary Tract Symptoms: Results From the Symptoms of Lower Urinary Tract Dysfunction Research Network
  • Article
  • Full-text available

October 2024

·

11 Reads

Neurourology and Urodynamics

Aims Men with lower urinary tract symptoms (LUTS) represent a heterogeneous group, and treatment decisions are often based on severity of symptoms and physical examination findings. Identification of clinically meaningful subtypes could allow for more personalized care. This study advances phenotyping efforts from the Symptoms of Lower Urinary Tract Dysfunction Research Network (LURN) by adding data domains to previous phenotyping using urologic symptoms alone. Methods Two‐hundred‐seventeen LUTS, demographics, medical history, and physical examination datapoints from the LURN Observational Cohort study were assessed among 519 men with at least one bothersome LUTS, using weighted Tanimoto indices, semi‐supervised learning, and resampling‐based consensus clustering to identify distinct clusters of participants. Differentially abundant serum proteins of 220 men were compared across identified clusters. Results Five refined male clusters (RM1–RM5) were identified. Two clusters reported mild LUTS (RM1: n = 66; RM2: n = 84). RM1 was older than RM2 (70.3 vs. 56.1 years), had more comorbidities (functional comorbidity index 2.4 vs. 1.5) and erectile dysfunction. Two benign prostatic hyperplasia‐like symptom clusters were identified (RM3: n = 64; RM4: n = 188). RM3 has the largest postvoid residual volume (275 mL); RM4 reported more urinary frequency, urgency, urinary incontinence, pain, and psychosocial symptoms. RM5 ( n = 119) was characterized by urgency urinary incontinence, frequency, and significant comorbidities and psychosocial symptoms. Fifteen (RM2) to 87 (RM1) differentially abundant proteins were identified within each cluster. Minimal overlap was observed between affected proteins and pathways across clusters. Conclusions Protein signatures across newly discovered subgroups suggest identified subtypes are biochemically distinct. Findings should be validated, but may represent populations with separate pathophysiology and therapeutic needs. Clinical Trial Registration The LURN ClinicalTrials.gov Identifier is NCT02485808.

Download

Symptoms of Lower Urinary Tract Dysfunction Research Network (LURN): An introduction to the Urinary Urgency Phenotyping Protocol LURN II

July 2024

·

11 Reads

Neurourology and Urodynamics

Aims The Symptoms of Lower Urinary Tract Dysfunction Research Network (LURN) is undertaking a new cohort study in LURN II including cases and controls. Methods This new cohort was enrolled to specifically study urinary urgency and urgency urinary incontinence, lower urinary tract symptoms (LUTSs) that are often difficult to treat due to a lack of understanding of their phenotypes and pathophysiologies. Results This paper will focus on the motivation for the second iteration of LURN and highlight the new research techniques and plans for more thorough phenotyping of this population. Conclusions This paper will outline the gaps in understanding in treating LUTSs, specifically urinary urgency.



Translating ethical and quality principles for the effective, safe and fair development, deployment and use of artificial intelligence technologies in healthcare

November 2023

·

50 Reads

·

14 Citations

Journal of the American Medical Informatics Association

Objective The complexity and rapid pace of development of algorithmic technologies pose challenges for their regulation and oversight in healthcare settings. We sought to improve our institution’s approach to evaluation and governance of algorithmic technologies used in clinical care and operations by creating an Implementation Guide that standardizes evaluation criteria so that local oversight is performed in an objective fashion. Materials and Methods Building on a framework that applies key ethical and quality principles (clinical value and safety, fairness and equity, usability and adoption, transparency and accountability, and regulatory compliance), we created concrete guidelines for evaluating algorithmic technologies at our institution. Results An Implementation Guide articulates evaluation criteria used during review of algorithmic technologies and details what evidence supports the implementation of ethical and quality principles for trustworthy health AI. Application of the processes described in the Implementation Guide can lead to algorithms that are safer as well as more effective, fair, and equitable upon implementation, as illustrated through 4 examples of technologies at different phases of the algorithmic lifecycle that underwent evaluation at our academic medical center. Discussion By providing clear descriptions/definitions of evaluation criteria and embedding them within standardized processes, we streamlined oversight processes and educated communities using and developing algorithmic technologies within our institution. Conclusions We developed a scalable, adaptable framework for translating principles into evaluation criteria and specific requirements that support trustworthy implementation of algorithmic technologies in patient care and healthcare operations.


Longitudinal Fluctuations in Treatment Response After OnabotulinumToxinA and Sacral Neuromodulation for Refractory Urgency Incontinence

October 2023

·

2 Reads

·

1 Citation

The Journal of Urology

Purpose: We compared fluctuations in treatment response after onabotulinumtoxinA and sacral neuromodulation for urgency incontinence using Markov models. Materials and methods: We fit data from a randomized trial to Markov models to compare transitions of success/failure over 6 months between 200 U onabotulinumtoxinA and sacral neuromodulation. Objective failure was <50% reduction in urgency incontinence episodes from baseline; subjective failure "strongly disagree" to "neutral" to the Patient Global Symptom Control questionnaire. Results: Of the 357 participants (median baseline daily urgency incontinence episodes 4.7 [IQR 3.7-6.0]) 61% vs 51% and 3.2% vs 6.1% reported persistent states of objective success and failure over 6 months after onabotulinumtoxinA vs sacral neuromodulation. Participants receiving onabotulinumtoxinA vs sacral neuromodulation had lower 30-day transition probabilities from objective and subjective success to failure (10% vs 14%, ratio 0.75 [95% CI 0.55-0.95]; 14% vs 21%, ratio 0.70 [95% CI 0.51-0.89]). The 30-day transition probability from objective and subjective failure to success did not differ between onabotulinumtoxinA and sacral neuromodulation (40% vs 36%, ratio 1.11 [95% CI 0.73-1.50]; 18% vs 17%, ratio 1.14 [95% CI 0.65-1.64]). Conclusions: Over 6 months after treatment, 2 in 5 women's symptoms fluctuate. Within these initial 6 months, women receiving onabotulinumtoxinA transitioned from success to failure over 30 days less often than sacral neuromodulation. For both treatments, there was an almost 20%-40% probability over 30 days that women returned to subjective and objective success after failure. Markov models add important information to longitudinal models on how symptoms fluctuate after urgency incontinence treatment.



Adherence to Perioperative Behavioral Therapy With Pelvic Floor Muscle Training in Women Receiving Vaginal Reconstructive Surgery for Pelvic Organ Prolapse

June 2023

·

93 Reads

·

1 Citation

Physical Therapy

Objective The objective of this study was to describe adherence to behavioral and pelvic floor muscle training (BPMT) in women undergoing vaginal reconstructive surgery for organ prolapse (POP) and to examine whether adherence was associated with 24-month outcomes. Methods Participants were women ≥18 years of age with vaginal bulge and stress urinary incontinence symptoms planning to undergo vaginal reconstructive surgery for stage 2–4 vaginal or uterine prolapse. They were randomized to either sacrospinous ligament fixation or uterosacral ligament suspension and to perioperative BPMT or usual care. Measurements included anatomic failure, pelvic floor muscle strength, participant-reported symptoms, and perceived improvement. Analyses compared women with lower versus higher adherence. Results Forty-eight percent of women performed pelvic floor muscle exercises (PFMEs) daily at the 4- to 6-week visit. Only 33% performed the prescribed number of muscle contractions. At 8 weeks, 37% performed PFMEs daily, and 28% performed the prescribed number of contractions. No significant relationships were found between adherence and 24-month outcomes. Conclusions Adherence to a behavioral intervention was low following vaginal reconstructive surgery for pelvic organ prolapse. The degree of adherence to perioperative training did not appear to influence 24-month outcomes in women undergoing vaginal prolapse surgery. Impact This study contributes to the understanding of participant adherence to PFMEs and the impact that participant adherence has on outcomes at 2, 4-to-6, 8, and 12 weeks and 24 months postoperatively. It is important to educate women to follow up with their therapist or physician to report new or unresolved pelvic symptoms.


Calibration plot demonstrating the performance of predicting postpartum hospital readmission for hypertension or preeclampsia. The dash line indicates perfect agreement between the predicted probability of the model and the actual probability.
Decision curve analysis of predicting postpartum hospital readmission for hypertension or pre‐eclampsia. The x‐axis indicates the range of threshold probabilities predicted by the model for risk of postpartum readmission for hypertension or pre‐eclampsia. The y‐axis indicates the standardised net benefit. The net benefit is calculated as true‐positive rate − (false‐positive rate × weighting factor). The weighting factor is calculated as the threshold probability/1 − threshold probability. The decision curves indicate the net benefit of the model as well as two clinical alternatives (classifying no individuals as having the outcome versus classifying all individuals as having the outcome) over a specified range of threshold probabilities of outcome.
Postpartum readmission for hypertension and pre‐eclampsia: development and validation of a predictive model

June 2023

·

37 Reads

·

4 Citations

BJOG An International Journal of Obstetrics & Gynaecology

Objective To develop a model for predicting postpartum readmission for hypertension and pre‐eclampsia at delivery discharge and assess external validation or model transportability across clinical sites. Design Prediction model using data available in the electronic health record from two clinical sites. Setting Two tertiary care health systems from the Southern (2014–2015) and Northeastern USA (2017–2019). Population A total of 28 201 postpartum individuals: 10 100 in the South and 18 101 in the Northeast. Methods An internal‐external cross validation (IECV) approach was used to assess external validation or model transportability across the two sites. In IECV, data from each health system were first used to develop and internally validate a prediction model; each model was then externally validated using the other health system. Models were fit using penalised logistic regression, and accuracy was estimated using discrimination (concordance index), calibration curves and decision curves. Internal validation was performed using bootstrapping with bias‐corrected performance measures. Decision curve analysis was used to display potential cut points where the model provided net benefit for clinical decision‐making. Main outcome measures The outcome was postpartum readmission for either hypertension or pre‐eclampsia <6 weeks after delivery. Results The postpartum readmission rate for hypertension and pre‐eclampsia overall was 0.9% (0.3% and 1.2% by site, respectively). The final model included six variables: age, parity, maximum postpartum diastolic blood pressure, birthweight, pre‐eclampsia before discharge and delivery mode (and interaction between pre‐eclampsia × delivery mode). Discrimination was adequate at both health systems on internal validation (c‐statistic South: 0.88; 95% confidence interval [CI] 0.87–0.89; Northeast: 0.74; 95% CI 0.74–0.74). In IECV, discrimination was inconsistent across sites, with improved discrimination for the Northeastern model on the Southern cohort (c‐statistic 0.61 and 0.86, respectively), but calibration was not adequate. Next, model updating was performed using the combined dataset to develop a new model. This final model had adequate discrimination (c‐statistic: 0.80, 95% CI 0.80–0.80), moderate calibration (intercept −0.153, slope 0.960, Emax 0.042) and provided superior net benefit at clinical decision‐making thresholds between 1% and 7% for interventions preventing readmission. An online calculator is provided here. Conclusions Postpartum readmission for hypertension and pre‐eclampsia may be accurately predicted but further model validation is needed. Model updating using data from multiple sites will be needed before use across clinical settings.


Development and validation of models predicting treatment patterns in women with urinary urgency and/or urgency incontinence: A Symptoms of Lower Urinary Tract Dysfunction Research Network observational cohort study

June 2023

·

12 Reads

·

1 Citation

Neurourology and Urodynamics

Purpose: To develop a tool to predict a woman's treatment pattern for bothersome urinary urgency (UU) and/or UU incontinence over 1 year after presenting for care at urology or urogynecology clinics. Methods: The Symptoms of Lower Urinary Tract Dysfunction Research Network observational cohort study enrolled adult women with bothersome UU and/or UU incontinence using the lower urinary tract symptoms (LUTS) Tool who were seeking care for LUTS. Treatments for UU and/or urgency incontinence were ordered from least to most invasive. Ordinal logistic and Cox proportional hazard regression models were fit to predict the most invasive level of treatment during follow-up and overactive bladder (OAB) medication discontinuation, respectively. Binary logistic regression was performed to predict sling treatment during the study follow-up. Clinical tools were then created using the models listed above to predict treatment pattern over 12 months. Results: Among 349 women, 281 reported UU incontinence, and 68 reported UU at baseline. The highest level of treatment during the study was as follows: 20% no treatment, 24% behavioral treatments, 23% physical therapy, 26% OAB medication, 1% percutaneous tibial nerve stimulation, 3% onabotulinumtoxin A, and 3% sacral neuromodulation. Slings were placed in 10% (n = 36) of participants before baseline and in 11% (n = 40) during study follow-up. Baseline factors associated with predicting the most invasive level of treatment included baseline level of treatment, hypertension, UU incontinence severity, stress urinary incontinence (SUI) severity, and anticholinergic burden score. Less severe baseline depression and less severe UU incontinence were associated with OAB medication discontinuation. UU and SUI severity were associated with sling placement during the study period. Three tools are available to predict: (1) highest level of treatment; (2) OAB medication discontinuation; and (3) sling placement. Conclusions: OAB treatment prediction tools developed in this study can help providers individualize treatment plans and identify not only patients at risk for treatment discontinuation but also patients who may not be escalated to potentially beneficial OAB treatments, with the goal to improve clinical outcomes for patients suffering from this chronic and often debilitating condition.


Citations (69)


... Our survey of the literature retrieved 13 healthcare AI lifecycles, which varied in the range of ethical issues they addressed and whether they had been implemented in practice (Supplementary Material S1). [12][13][14][15][16][17][18][19][20][21][22][23][24] We identified a total of 10 themes. Six themes reflect distinct steps, and four themes cut across the lifecycle. ...

Reference:

Addressing ethical issues in healthcare artificial intelligence using a lifecycle-informed process
Translating ethical and quality principles for the effective, safe and fair development, deployment and use of artificial intelligence technologies in healthcare
  • Citing Article
  • November 2023

Journal of the American Medical Informatics Association

... We found the lack of an association between the reduction in UUIE after lead implantation and subjective success at 24 months surprising, especially as it has been used as the determining factor for who receives an IPG since before SNM was granted FDA approval for UUI. 1 This may be because nearly 40% of women who receive SNM will have symptoms that fluctuate. 16 Thus the response at 1−2 weeks or even at 24 months after test stimulation may be temporary. Others have suggested that some people with SNM continue to improve after the first 1−2 weeks post lead-placement. ...

Longitudinal Fluctuations in Treatment Response After OnabotulinumToxinA and Sacral Neuromodulation for Refractory Urgency Incontinence
  • Citing Article
  • October 2023

The Journal of Urology

... This helps advance interventions to decrease maternal morbidity and mortality related to hypertensive disorders in pregnancy. Some groups have worked on creating prediction models for postpartum readmission using variables including age, postpartum BP, diagnosis of preeclampsia, and delivery mode (among others) which we also found to be risk factors for readmission [34,35]. Further model validation is needed by incorporating data from multiple sites across different clinical settings. ...

Postpartum readmission for hypertension and pre‐eclampsia: development and validation of a predictive model

BJOG An International Journal of Obstetrics & Gynaecology

... Our study bridges this gap by investigating PLK1's role in bladder smooth muscle disorders using genomic and in vitro approaches. By identifying PLK1 as a key regulator of proliferation and contraction in bladder smooth muscle cells and demonstrating the efficacy of the PLK1 inhibitor TAK960, we provide novel insights and potential therapeutic avenues for LUTS management (Bretschneider et al., 2023). ...

Development and validation of models predicting treatment patterns in women with urinary urgency and/or urgency incontinence: A Symptoms of Lower Urinary Tract Dysfunction Research Network observational cohort study
  • Citing Article
  • June 2023

Neurourology and Urodynamics

... Damage to autonomic nerve fibres in the sacral nerve can lead to detrusor underactivity and cause neurogenic bladder. [2][3][4] Injury to peripheral nerves with regenerative potential can result in incomplete functional recovery. 5 The prevailing theory focuses on microenvironment, which is initially pro-inflammatory but evolves into the proregeneration state. ...

Intraoperative Predictors of Sacral Neuromodulation Implantation and Treatment Response: Results From the ROSETTA Trial
  • Citing Article
  • April 2023

The Journal of Urology

... Nevertheless, first-line conservative treatments such as antimuscarinic agent therapy do not always lead to sufficient improvement in symptoms of OAB and are often associated with disabling adverse effects [3] with discontinuation rates nearing 50% in the first month of treatment [4,5]. Electrical stimulation of the sacral roots, generically described as 'neuromodulation', has emerged as an alternative and attractive treatment for refractory OAB [4]. ...

Treatment patterns in women with urinary urgency and/or urgency urinary incontinence in the symptoms of Lower Urinary Tract Dysfunction Research Network Observational Cohort Study
  • Citing Article
  • October 2022

Neurourology and Urodynamics

... Pelvic organ prolapse (POP) is a common condition 1-3 affecting women's quality of life. [4][5][6][7] Symptoms associated with POP can impair multiple aspects of a woman's well-being, including physical, psychological, social, occupational, and sexual spheres. 8,9 As life expectancy continues to rise, the prevalence of pelvic floor disorders is expected to grow 10,11 along with the healthcare resources required for both conservative and surgical management of this condition. ...

Natural history of lower urinary tract symptoms in treatment-seeking women with pelvic organ prolapse; the Symptoms of Lower Urinary Tract Dysfunction Research Network (LURN)
  • Citing Article
  • August 2022

American Journal of Obstetrics and Gynecology

... Significant risk factors were presented as a forest plot showing individual odds ratio (OR) with a 95% confidence interval (CI). A nomogram was then developed to represent the prediction model combining significant risk factors graphically [36]. The variable with the largest effect size or regression coefficient was assigned 100 points on the scale, and the remaining variables were given lower points proportional to their effect size [37]. ...

Development and Validation of a Model for Opioid Prescribing Following Gynecological Surgery

JAMA Network Open

... Further data processing and clustering were performed using the clustering pipeline developed and described in detail for subtyping women with LUTS [17]. CASUS data provided by a subset of participants was added into the analysis. ...

Subtyping of common complex diseases and disorders by integrating heterogeneous data. Identifying clusters among women with lower urinary tract symptoms in the LURN study

... Transparency throughout the model life cycle has been strongly emphasized in the guidelines. Detailed documentation is emphasized at each stage of an LLM's life cycle 37 ; for example, during the development and fine-tuning phases, there is an emphasis on disclosing the origins and processing of training data. Moreover, the LLM version and specifics of any fine-tuning or alignment modeling processes on top of existing foundation models must be transparently reported to enable fair comparisons of LLMs. ...

A framework for the oversight and local deployment of safe and high-quality prediction models
  • Citing Article
  • May 2022

Journal of the American Medical Informatics Association