v3.1.0 ready

Author: rudolfjs

.changes/unreleased/Changed-20251115-095514.yaml

@@ -0,0 +1,6 @@
+## v3.1.0 - 2025-11-15
+### Added
+* Added date field to publications
+### Changed
+* Fixed ordering in publications, will order by month within the year
+* Updated full YYYY-MM-DD dates to all publications

.changes/v3.1.0.md

@@ -6,6 +6,13 @@ adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html),
 and is generated by [Changie](https://github.com/miniscruff/changie).
 
 
+## v3.1.0 - 2025-11-15
+### Added
+* Added date field to publications
+### Changed
+* Fixed ordering in publications, will order by month within the year
+* Updated full YYYY-MM-DD dates to all publications
+
 ## v3.0.3 - 2025-10-02
 ### Changed
 * PDF preview now under `<object>` tags with fallback

CHANGELOG.md

@@ -1,6 +1,7 @@
 ---
 title: "Implementation frameworks for end-to-end clinical AI:
 derivation of the SALIENT framework"
+date: 2023-05-19
 authors:
   - "Anton H. van der Vegt"
   - "Ian A. Scott"

content/publications/2023-salient-framework-clinical-ai.md

@@ -2,6 +2,7 @@
 title: "Deployment of machine learning algorithms to predict
 sepsis: systematic review and application of the SALIENT
 clinical AI implementation framework"
+date: 2023-05-12
 authors:
   - "Anton H. van der Vegt"
   - "Ian A. Scott"

content/publications/2023-sepsis-ml-deployment.md

@@ -1,5 +1,6 @@
 ---
 title: "Hyperkalaemia among hospital admissions: prevalence, risk factors, treatment and impact on length of stay"
+date: 2024-12-18
 authors:
   - "Yalin Yu"
   - "Venkat N. Vangaveti"

content/publications/2024-hyperkalaemia-hospital-admissions.md

@@ -1,5 +1,6 @@
 ---
 title: "Development and implementation of digital solutions in healthcare: insights from the Australian tertiary hospital landscape"
+date: 2025-04-14
 authors:
   - "Rudolf J. Schnetler"
   - "Venkat N. Vangaveti"

content/publications/2025-digital-health-implementation-australia.md

@@ -1,5 +1,6 @@
 ---
 title: "False hope of a single generalisable AI sepsis prediction model: bias and proposed mitigation strategies for improving performance based on a retrospective multisite cohort study"
+date: 2025-03-01
 authors:
   - "Rudolf J. Schnetler"
   - "Anton H. van der Vegt"

content/publications/2025-false-hope-sepsis-prediction.md

@@ -1,5 +1,6 @@
 ---
 title: "Proposing a novel Seriously Deteriorated Patient Indicator (SDPI) for hospitalised ward patients"
+date: 2025-07-10
 authors: 
   - "Anton H. van der Vegt"
   - "Victoria Campbell"

content/publications/2025-seriously-deteriorated-patient-indicator.md

@@ -1,5 +1,6 @@
 ---
 title: "A novel, standardised approach to balancing effectiveness, efficiency and utility of surveillance AI prediction models for hospitalised patients using sepsis prediction as an exemplar"
+date: 2025-11-11
 authors:
   - "Anton H van der Vegt"
   - "Victoria K Campbell"
@@ -19,7 +20,7 @@ authors:
 year: 2025
 month: "November"
 journal: "JAMIA"
-doi: "https://doi.org/10.1093/jamia/ocaf192"
+doi: "10.1093/jamia/ocaf192"
 publication_type: "Journal Article"  
 abstract: "<p><strong>Objective: </strong>To introduce a novel, standardised approach to evaluating AI prediction models in balancing effectiveness, efficiency and utility, using a sepsis prediction model case study.</p><p><strong>Materials and Methods: </strong>Retrospective patient data from electronic medical records of 7 public hospitals was used to retrain and evaluate a machine learning sepsis prediction model. Four conventional metrics—area under the receiver operating curve (AUROC), sensitivity, positive predictive value, and specificity—were compared with a novel graphical display integrating metrics of predictive accuracy (effectiveness), alert burden (efficiency) and lead time of alerts relative to clinical events (utility) for different alert thresholds.</p><p><strong>Results: </strong>The dataset comprised 977,506 inpatient admissions. The novel methodology produced a plot of four vertically aligned graphs that enables decision-makers to identify an alert threshold that optimally balances effectiveness, efficiency and utility (EEU) at the level of an entire admission, and which differs from that derived using conventional metrics.</p><p><strong>Discussion: </strong>Conventional evaluation metrics do not consider alert timing relative to clinical events and are often applied to different evaluation datasets (sample and admission level), introducing bias and confusion. In contrast, the EEU methodology (i) generates admission level evaluations at different alert thresholds; (ii) measures alert timing relative to clinical events; and (iii) provides a visual display that enables identification of the alert threshold that optimally balances EEU factors.</p><p><strong>Conclusion: </strong>Evaluations of prediction models for adverse events in hospitalised patients should incorporate the EEU approach in assessing model suitability and selecting alert thresholds.</p>"
 keywords: ["adult", "sepsis/mortality", "electronic health records/statistics and numerical data", "machine learning", "decision support systems", "clinical", "emergency service", "hospital/statistics and numerical data", "hospitalization/statistics and numerical data", "ROC curve", "retrospective studies"]