Search

Huxford, Charly; Dunsmuir, Dustin; Pillay, Yashodani; Ashebukara, Ivan Aye; Tusingwire, Fredson; Novakowski, Stefanie; Behan, Justine; Hwang, Bella; Ansermino, Mark; Lester, Deborah; Kissoon, Niranjan; Tagoola, Abner — 2023-11-15 <br /><strong>Objective(s):</strong> The Smart Triage Quality Improvement Training Program covers the basic concepts of the Quality Improvement process and provides a framework and tools that can be used to train staff on QI. Core learning components include: 1) understanding what QI is; 2) the QI model for improvement; and 3) QI methods and tools. <br /> <br /><strong>Data Description:</strong> This dataset includes the following materials for use in the Smart Triage Quality Improvement Training Program: 1) Quality Improvement Guide; 2) QI Activities Workbook. Materials were originally developed through a partnership with Walimu and the University of British Columbia. All materials are provided in the English language. <br /> <br /><strong>Data Limitations:</strong> These materials were designed for the Ugandan context and may not be generalizable to other settings. <br /> <br /><strong>Data Ethics Declaration:</strong> NA <br /> <br /><strong>Funding Source(s):</strong> BC Children's Hospital Foundation; Grand Challenges Canada; Mining4Life; Wellcome <br /><strong>NOTE for restricted files:</strong> If you are not yet a CoLab member, please complete our <a href = "https://rc.bcchr.ca/redcap/surveys/?s=EDCYL7AC79">membership application survey</a> to gain access to restricted files within 2 business days. <br />Some files may remain restricted to CoLab members. These files are deemed more sensitive by the file owner and are meant to be shared on a case-by-case basis. Please contact the CoLab coordinator at <a href = mailto:sepsiscolab@bccchr.ca>sepsiscolab@bcchr.ca</a> or visit our <a href = "https://wfpiccs.org/pediatric-sepsis-colab/">website</a>.

Huxford, Charly; Nguyen, Vuong; Trawin, Jessica; Johnson, Teresa; Kissoon, Niranjan; Wiens, Matthew; Ogilvie, Gina; Murthy, Srinivas; Dhugga, Gurm; Kinshella, Maggie Woo; Ansermino, J Mark — 2023-04-18 <strong>Objective(s):</strong> Momentum for open access to research is growing. Funding agencies and publishers are increasingly requiring researchers make their data and research outputs open and publicly available. However, this introduces many challenges, especially when managing confidential clinical data.<br /> <br />The aim of this 1 hr virtual workshop is to provide participants with knowledge about what synthetic data is, methods to create synthetic data, and the 2023 Pediatric Sepsis Data Challenge.<br /> <br />Workshop Agenda:<br /> <br />1. Introduction - Speaker: Mark Ansermino, Director, Centre for International Child Health <br /> <br />2. "Leveraging Synthetic Data for an International Data Challenge" - Speaker: Charly Huxford, Research Assistant, Centre for International Child Health <br /> <br />3. "Methods in Synthetic Data Generation." - Speaker: Vuong Nguyen, Biostatistician, Centre for International Child Health and The HIPpy Lab <br /> <br />This workshop draws on work supported by the Digital Research Alliance of Canada.<br /> <br /><strong>Data Description:</strong> Presentation slides, Workshop Video, and Workshop Communication<br /> <br />Charly Huxford: Leveraging Synthetic Data for an International Data Challenge presentation and accompanying PowerPoint slides.<br /> <br />Vuong Nguyen: Methods in Synthetic Data Generation presentation and accompanying Powerpoint slides.<br /> <br />This workshop was developed as part of Dr. Ansermino's Data Champions Pilot Project supported by the <a href = "https://alliancecan.ca/en">Digital Research Alliance of Canada</a>.<br /> <br /><strong>NOTE for restricted files:</strong> If you are not yet a CoLab member, please complete our <a href = "https://rc.bcchr.ca/redcap/surveys/?s=EDCYL7AC79">membership application survey</a> to gain access to restricted files within 2 business days. <br />Some files may remain restricted to CoLab members. These files are deemed more sensitive by the file owner and are meant to be shared on a case-by-case basis. Please contact the CoLab coordinator on <a href = "https://www.bcchr.ca/pediatric-sepsis-data-colab">this page</a> under "collaborate with the pediatric sepsis colab."

Huxford, Charly; Dunsmuir, Dustin; Pillay, Yashodani; Ashebukara, Ivan Aye; Tusingwire, Fredson; Novakowski, Stefanie; Behan, Justine; Pallot, Katija; Hwang, Bella; Ansermino, Mark — 2023-11-08 <br /><strong>Objective(s):</strong> The Smart Triage Health Worker Training Program uses a train-the-trainer model to improve the quality of triage care. Core learning components include: 1) understanding what triage is; 2) effective triaging using the Smart Triage platform; and 3) best practices for health workers. <br /> <br /><strong>Data Description:</strong> This dataset includes the following materials for use in the Smart Triage Training Program: 1) Health Workers Guide; 2) Smart Triage Handbook; 3) Caregivers counselling card Materials were originally developed through a partnership with Walimu and the University of British Columbia. All materials are provided in the English language. <br /> <br /><strong>Data Limitations:</strong> These materials were designed for the Ugandan context and may not be generalizable to other settings. <br /> <br /><strong>Data Ethics Declaration:</strong> NA <br /> <br /><strong>Funding Source(s):</strong> BC Children's Hospital Foundation; Grand Challenges Canada; Mining4Life; Wellcome <br /><strong>NOTE for restricted files:</strong> If you are not yet a CoLab member, please complete our <a href = "https://rc.bcchr.ca/redcap/surveys/?s=EDCYL7AC79">membership application survey</a> to gain access to restricted files within 2 business days. <br />Some files may remain restricted to CoLab members. These files are deemed more sensitive by the file owner and are meant to be shared on a case-by-case basis. Please contact the CoLab coordinator at <a href = mailto:sepsiscolab@bccchr.ca>sepsiscolab@bcchr.ca</a> or visit our <a href = "https://wfpiccs.org/pediatric-sepsis-colab/">website</a>.

Nguyen, Vuong; Huxford, Charly; Rafiei, Alireza; Wiens, Matthew; Ansermino, J Mark; Kissoon, Niranjan; Kamaleswaran, Rishikesan — 2023-06-21 <p><br /><strong>Objective(s):</strong> The 2024 Pediatric Sepsis Data Challenge provides an opportunity to address the lack of appropriate mortality prediction models for LMICs. For this challenge, we are asking participants to develop a working, open-source algorithm to predict in-hospital mortality and length of stay using only the provided synthetic dataset. <br> <br> The original data used to generate the real-world data (RWD) informed synthetic training set available to participants was obtained from a prospective, multisite, observational cohort study of children with suspected sepsis aged 6 months to 60 months at the time of admission to hospitals in Uganda. For this challenge, we have created a RWD-informed synthetically generated training data set to reduce the risk of re-identification in this highly vulnerable population. The synthetic training set was generated from a random subset of the original data (full dataset A) of 2686 records (70% of the total dataset - training dataset B). All challenge solutions will be evaluated against the remaining 1235 records (30% of the total dataset - test dataset C). <br> <br /><strong>Data Description:</strong> Report describing the comparison of univariate and bivariate distributions between the Synthetic Dataset and Test Dataset C. Additionally, a report showing the maximum mean discrepancy (MMD) and Kullback–Leibler (KL) divergence statistics. Data dictionary for the synthetic training dataset containing 148 variables. <br /><strong>NOTE for restricted files:</strong> If you are not yet a CoLab member, please complete our <a href = "https://rc.bcchr.ca/redcap/surveys/?s=EDCYL7AC79">membership application survey</a> to gain access to restricted files within 2 business days. <br />Some files may remain restricted to CoLab members. These files are deemed more sensitive by the file owner and are meant to be shared on a case-by-case basis. Please contact the CoLab coordinator at <a href = mailto:sepsiscolab@bccchr.ca>sepsiscolab@bcchr.ca</a> or visit our <a href = "https://wfpiccs.org/pediatric-sepsis-colab/">website</a>.

Zhang, Cherri; Wiens, Matthew O; Dunsmuir, Dustin; Pillay, Yashodani; Huxford, Charly; Kimutai, David; Tenywa, Emmanuel; Ouma, Mary; Kigo, Joyce; Kamau, Stephen; Chege, Mary; Kenya-Mugisha, Nathan; Mwaka, Savio; Dumont, Guy A; Kisson, Niranjan; Akech, Samuel; Ansermino, J Mark — 2024-06-12 <br /><strong>Background:</strong> Age is an important risk factor among critically ill children with neonates being the most vulnerable. Clinical prediction models need to account for age differences and must be externally validated and updated, if necessary, to enhance reliability, reproducibility, and generalizability. We externally validated the Smart Triage model using a combined prospective baseline cohort from three hospitals in Uganda and two in Kenya using admission, mortality, and readmission. <br/> <br /><strong>Methods:</strong> We evaluated model discrimination using area under the receiver-operator curve (AUROC) and visualized calibration plots. In addition, we performed subsetting analysis based on age groups (< 30 days, ≤ 2 months, ≤ 6 months, and < 5 years). We revised the model for neonates (< 1 month) by re-estimating the intercept and coefficients and selected new thresholds to maximize sensitivity and specificity. 11595 participants under the age of five (under-5) were included in the analysis. <br/> <br /><strong>Results:</strong> The proportion with an outcome ranged from 8.9% in all children under-5 (including neonates) to 26% in the neonatal subset alone. The model achieved good discrimination for children under-5 with AUROC of 0.81 (95% CI: 0.79-0.82) but poor discrimination for neonates with AUROC of 0.62 (95% CI: 0.55-0.70). Sensitivity at the low-risk thresholds (CI) were 0.85 (0.83-0.87) and 0.68 (0.58-0.76) for children under-5 and neonates, respectively. Specificity at the high-risk thresholds were 0.93 (0.93-0.94) and 0.96 (0.94-0.98) for children under-5 and neonates, respectively. After model revision for neonates, we achieved an AUROC of 0.83 (0.79-0.87) with 13% and 41% as the low- and high-risk thresholds, respectively. <br/> <br /><strong>Discussion:</strong> The Smart Triage model showed good discrimination for children under-5. However, a revised model is recommended for neonates due to their uniqueness in disease susceptibly, host response, and underlying physiological reserve. External validation of the neonatal model and additional external validation of the under-5 model in different contexts is required. <br/> <br /><strong>NOTE for restricted files:</strong> If you are not yet a CoLab member, please complete our <a href = "https://rc.bcchr.ca/redcap/surveys/?s=EDCYL7AC79">membership application survey</a> to gain access to restricted files within 2 business days. <br />Some files may remain restricted to CoLab members. These files are deemed more sensitive by the file owner and are meant to be shared on a case-by-case basis. Please contact the CoLab coordinator at <a href = mailto:sepsiscolab@bccchr.ca>sepsiscolab@bcchr.ca</a> or visit our <a href = "https://wfpiccs.org/pediatric-sepsis-colab/">website</a>.