PKPramit Khetrapal

Pramit Khetrapal

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Pramit Khetrapal has a total of 257 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Artificial Intelligence Remote Patient Monitoring for Predicting Overall Survival for Patients Undergoing Radical Cystectomy for Bladder Cancer: Exploratory Analysis of the Prospective Trial

    by Yansong Liu, Pramit Khetrapal, Ronnie Strafford, Adamos Hadjivasilou, Nikhil Vasdev, Philip Charlesworth, Muhamaad Shamim Khan, Ahmed Abdulaal, Zhaoyan Dong, James W F Catto, et al.

    Background: Previous studies have highlighted the benefits of using artificial intelligence–powered remote patient monitoring (AI RPM) in detecting health changes across various disease cohorts. However, the use of AI RPM for identifying health deteriorations in patients following major surgical procedures remains underexplored. Objective: This exploratory analysis of a prospective trial aims to assess how AI RPM can enhance the predictive performance of 35-month post–radical cystectomy (RC) mortality risk. Our approach highlights the importance of RPM features in improving prediction accuracy and provides interpretable model outputs to enhance clinical understanding and transparency. Methods: We used patient data from a multicenter RC trial conducted in the United Kingdom for model training and validation. Two gradient-boosted machine learning models were developed: one using only clinical-pathological (CP) features and another incorporating both CP and remote patient monitoring (RPM) features (CP+RPM). RPM features are measured by wrist-worn pedometers and surveys. The predictive accuracy of the CP+RPM model was compared with both the CP model and a clinically used nomogram, both of which relied solely on traditional clinical features. We used 200 bootstrap iterations, with 70% of the data used for training and 30% for testing. Shapley Additive Explanations were applied to interpret model results and provide insights into the relative importance of features, improving transparency and understanding of the predictions. Results: A total of 252 patients (33 deaths) from 9 UK centers were included in the analysis. We examined 108 RPM features and 24 CP features for model training. In correlation analysis, only 9 CP features showed coefficients larger than 0.1, compared with 36 RPM features with stronger correlations. The CP+RPM model achieved an area under the receiver operating characteristic curve of 0.77, reflecting a 9% and 10% absolute (13% and 15% relative) improvement over the CP and nomogram models, respectively. Similarly, it outperformed in terms of the area under the precision-recall curve, with a score of 0.44, marking a 6% and 17% absolute (16% and 63% relative) increase compared with the CP and nomogram model. Shapley Additive Explanations analysis revealed that the most significant contributors to mortality prediction were mobility-related RPM features, such as the 30-second chair-to-stand test results and daily step count variance, which reflected the general activity levels of individuals. Conclusions: Our study demonstrates that RPM features significantly enhance long-term survival prediction for post-RC patients, offering a valuable addition to traditional clinical data. The integration of AI with RPM enables more individualized and dynamic tracking of recovery, improving prediction accuracy and fostering a patient-centered care model that has the potential to be applied across a broader range of surgeries and conditions.


  • Open Access

    Artificial Intelligence Remote Patient Monitoring (AI RPM) for predicting overall survival for patients undergoing radical cystectomy for bladder cancer: an exploratory analysis of the prospective trial iROC (Preprint)

    by Yansong Liu, Pramit Khetrapal, Ronnie Strafford, Adamos Hadjivasilou, Nikhil Vasdev, Philip Charlesworth, Muhamaad Shamim Khan, Ahmed Abdulaal, Zhaoyan Dong, James W.F. Catto, et al.

    BACKGROUND Previous studies have highlighted the benefits of using artificial intelligence powered remote patient monitoring (AI RPM) in detecting health changes across various disease cohorts. However, the use of AI RPM for identifying health deteriorations in patients following major surgical procedures remains underexplored. OBJECTIVE This exploratory analysis of a prospective trial aims to assess how AI RPM can enhance the predictive performance of 35-month post-radical cystectomy (RC) mortality risk. Our approach highlights the importance of RPM features in improving prediction accuracy and provides interpretable model outputs to enhance clinical understanding and transparency. METHODS We used patient data from a multi-centre RC trial conducted in the United Kingdom (UK) for model training and validation. Two gradient-boosted machine learning models were developed: one using only clinical-pathological (CP) features and another incorporating both CP and remote patient monitoring (RPM) features (CP+RPM). RPM features are measured by wrist-worn pedometers and surveys. The predictive accuracy of the CP+RPM model was compared to both the CP model and a clinically used nomogram, both of which relied solely on traditional clinical features. We employed 200 bootstrap iterations, with 70% of the data used for training and 30% for testing. Shapley Additive Explanations (SHAP) were applied to interpret model results and provide insights into the relative importance of features, improving transparency and understanding of the predictions. RESULTS A total of 252 patients (33 deaths) from 9 UK centres were included in the analysis. We examined 108 RPM features and 24 CPM features for model training. In correlation analysis, only 10 traditional features showed coefficients larger than 0.1, compared to 36 RPM features with stronger correlations. The CP+RPM model achieved an area under receiver operator characteristic curve (AUC-ROC) of 0.77, reflecting a 9% and 10% absolute (13% and 15% relative) improvement over the CP and nomogram models, respectively. Similarly, it outperformed in terms of the area under precision-recall curve, with a score of 0.44, marking a 6% and 17% absolute (16% and 63% relative) increase compared to the CP and nomogram model. SHAP analysis revealed that the most significant contributors to mortality prediction were mobility-related RPM features, such as the 30-second chair-to-stand test results and daily step count variance, which reflected the general activity levels of individuals. CONCLUSIONS Our study demonstrates that RPM features significantly enhance long-term survival prediction for post-RC patients, offering a valuable addition to traditional clinical data. The integration of AI with RPM enables more individualised and dynamic tracking of recovery, improving prediction accuracy and fostering a patient-centred care model that has the potential to be applied across a broader range of surgeries and conditions.

  • Digital Tracking of Patients Undergoing Radical Cystectomy for Bladder Cancer: Daily Step Counts Before and After Surgery Within the iROC Randomised Controlled Trial

    by Pramit Khetrapal, Parasdeep S. Bains, Ibrahim Jubber, Gareth Ambler, Norman R. Williams, Chris Brew-Graves, Ashwin Sridhar, Anthony Ta, John D. Kelly, James W.F. Catto


  • Global Variation in Magnetic Resonance Imaging Quality of the Prostate

    by Francesco Giganti, Alexander Ng, Aqua Asif, Vinson Wai-Shun Chan, Marimo Rossiter, Arjun Nathan, Pramit Khetrapal, Louise Dickinson, Shonit Punwani, Chris Brew-Graves, et al.

    Background High variability in prostate MRI quality might reduce accuracy in prostate cancer detection. Purpose To prospectively evaluate the quality of MRI scanners taking part in the quality control phase of the global PRIME (Prostate Imaging Using MRI ± Contrast Enhancement) trial using the Prostate Imaging Quality (PI-QUAL) standardized scoring system, give recommendations on how to improve the MRI protocols, and establish whether MRI quality could be improved by these recommendations. Materials and Methods In the prospective clinical trial (PRIME), for each scanner, centers performing prostate MRI submitted five consecutive studies and the MRI protocols (phase I). Submitted data were evaluated in consensus by two expert genitourinary radiologists using the PI-QUAL scoring system that evaluates MRI diagnostic quality using five points (1 and 2 = nondiagnostic; 3 = sufficient; 4 = adequate, 5 = optimal) between September 2021 and August 2022. Feedback was provided for scanners not achieving a PI-QUAL 5 score, and centers were invited to resubmit new imaging data using the modified protocol (phase II). Descriptive comparison of outcomes was made between the MRI scanners, feedback provided, and overall PI-QUAL scores. Results In phase I, 41 centers from 18 countries submitted a total of 355 multiparametric MRI studies from 71 scanners, with nine (13%) scanners achieving a PI-QUAL score of 3, 39 (55%) achieving a score of 4, and 23 (32%) achieving a score of 5. Of the 48 (n = 71 [68%]) scanners that received feedback to improve, the dynamic contrast-enhanced sequences were those that least adhered to the Prostate Imaging Reporting and Data System, version 2.1, criteria (44 of 48 [92%]), followed by diffusion-weighted imaging (20 of 48 [42%]) and T2-weighted imaging (19 of 48 [40%]). In phase II, 36 centers from 17 countries resubmitted revised studies, resulting in a total of 62 (n = 64 [97%]) scanners with a final PI-QUAL score of 5. Conclusion Substantial variation in global prostate MRI acquisition parameters as a measure of quality was observed, particularly with DCE sequences. Basic evaluation and modifications to MRI protocols using PI-QUAL can lead to substantial improvements in quality. Clinical trial registration no. NCT04571840 Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Almansour and Chernyak in this issue.


  • Corrigendum to “Robot-assisted Radical Cystectomy Versus Open Radical Cystectomy: A Systematic Review and Meta-analysis of Perioperative, Oncological, and Quality of Life Outcomes Using Randomized Controlled Trials” [Eur Urol. 2023;84:393–405]

    by Pramit Khetrapal, Joanna Kae Ling Wong, Wei Phin Tan, Thiara Rupasinghe, Wei Shen Tan, Stephen B. Williams, Stephen A. Boorjian, Carl Wijburg, Dipen J. Parekh, Peter Wiklund, et al.


  • Top Cited Papers
    Open Access

    Robot-assisted Radical Cystectomy Versus Open Radical Cystectomy: A Systematic Review and Meta-analysis of Perioperative, Oncological, and Quality of Life Outcomes Using Randomized Controlled Trials

    by Pramit Khetrapal, Joanna Kae Ling Wong, Wei Phin Tan, Thiara Rupasinghe, Wei Shen Tan, Stephen B. Williams, Stephen A. Boorjian, Carl Wijburg, Dipen J. Parekh, Peter Wiklund, et al.


  • Open Access

    Factors Predicting Outcomes of Supine Percutaneous Nephrolithotomy: Large Single-Centre Experience

    by Yasmin Abu-Ghanem, Luke Forster, Pramit Khetrapal, Gidon Ellis, Paras Singh, Rohit Srinivasan, Rajesh Kucheria, Anuj Goyal, Darrell Allen, Antony Goode, et al.

    Objective: Percutaneous nephrolithotomy (PCNL) is the treatment of choice for large renal calculi. The prone position has been considered the preferred position to obtain renal access. However, the supine position has recently gained popularity, which confers several potential advantages. The current study analyses the prognostic factors for successful supine PCNL procedures in a larger tertiary centre. Subjects: Prospective data were collected from all patients undergoing PCNL in the Galdako modified Valdivia position at our institution between February-2007 and September-2020. Surgical outcomes variables collected included: the rate of Endoscopic-combined intra-renal surgery (ECIRS), operative times, surgical effectiveness (no residuals p < 0.001), location (p < 0.001) and Guys-Stone Score (GSS) (p < 0.001) were associated with effectiveness. A Percutaneous nephrostomy tube was sited at the completion of the procedure in 97.3% of patients and a simultaneous double-J stent in 45.3%. Stent insertion was associated with larger stones (p < 0.001), the performance of ECIRS (p < 0.001) and higher GSS (p < 0.001). The overall complication rate was 21.7%. The main type of complication was an infection in 26.2 of the cases followed by the need for repeated nephrostogram in 12.7%. Conclusions: We demonstrate that PCNL in a high-volume centre is safe and efficacious in the Galdalko modified Valdivia position. Patients with smaller stones in the renal pelvis and a low GSS have the highest chance of a successful procedure.


  • Open Access

    Measuring Patient Compliance With Remote Monitoring Following Discharge From Hospital After Major Surgery (DREAMPath): Protocol for a Prospective Observational Study

    by Pramit Khetrapal, Ronnie Stafford, Pádraig Ó Scanaill, Huriye Kocadag, Constantinos Timinis, Angela H L Chang, Adamos Hadjivasiliou, Yansong Liu, Olivia Gibbs, Eleanor Pickford, et al.

    Background: The incidence of major surgery is on the rise globally, and more than 20% of patients are readmitted to hospital following discharge from hospital. During their hospital stay, patients are monitored for early detection of clinical deterioration, which includes regularly measuring physiological parameters such as blood pressure, heart rate, respiratory rate, temperature, and pulse oximetry. This monitoring ceases upon hospital discharge, as patients are deemed clinically stable. Monitoring after discharge is relevant to detect adverse events occurring in the home setting and can be made possible through the development of digital technologies and mobile networks. Smartwatches and other technological devices allow patients to self-measure physiological parameters in the home setting, and Bluetooth connectivity can facilitate the automatic collection and transfer of this data to a secure server with minimal input from the patient. Objective: This paper presents the protocol for the DREAMPath (Domiciliary Recovery After Medicalization Pathway) study, which aims to measure compliance with a multidevice remote monitoring kit after discharge from hospital following major surgery. Methods: DREAMPath is a single-center, prospective, observational, cohort study, comprising 30 patients undergoing major intracavity surgery. The primary outcome is to assess patient compliance with wearable and interactive smart technology in the first 30 days following discharge from hospital after major surgery. Secondary outcomes will explore the relation between unplanned health care events and physiological data collected in the study, as well as to explore a similar relationship with daily patient-reported outcome measures (Quality of Recovery–15 score). Secondary outcomes will be analyzed using appropriate regression methods. Cardiopulmonary exercise testing data will also be collected to assess correlations with wearable device data. Results: Recruitment was halted due to COVID-19 restrictions and will progress once research staff are back from redeployment. We expect that the study will be completed in the first quarter of 2022. Conclusions: Digital health solutions have been recently made possible due to technological advances, but urgency in rollout has been expedited due to COVID-19. The DREAMPath study will inform readers about the feasibility of remote monitoring for a patient group that is at an increased risk of acute deterioration. Trial Registration: ISRCTN Registry ISRCTN62293620; https://www.isrctn.com/ISRCTN62293620 International Registered Report Identifier (IRRID): DERR1-10.2196/30638


  • Open Access

    Choosing appropriate patient‐reported outcome measures for prostate disease

    by Alexander Ng, Pramit Khetrapal, Chris Brew‐Graves, Nicola Muirhead, Aqua Asif, Vinson Wai‐Shun Chan, Arjun Nathan, Veeru Kasivisvanathan


  • Open Access

    Setting up an emergency medical task force to manage the demands of COVID-19: experiences of a London teaching hospital

    by Pramit Khetrapal, Sophie Skarbek, Louis Tapper, Claire Mason, Sarah Davis, Daisy Henderson, Ben Riley, Liam Price, Charlotte Cumby, Caroline Kennedy, et al.