Methods for calculating credible intervals for ratios of beta distributions with application to relative risks of death during the second plague pandemic

Dunbar, Maria Bekker‐Nielsen; Finnie, Thomas; Sloane, Barney; Hall, Ian

doi:10.1371/journal.pone.0211633

Cited by 3 publications

(2 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Differences between rates of findings were interrogated by means of the chi-square test, with p < 0.05 being considered statistically significant. The uncertainty in each state transition was propagated through the model using beta distributions based on the observed numerator and denominator information with 95% credible confidence intervals calculated using the beta distribution as previously described [ 22 ]. This was implemented in R using R Studio [ 23 ].…”

Section: Methodsmentioning

confidence: 99%

Comparing the clinical performance and cost efficacy of [68Ga]Ga-PSMA-11 and [18F]PSMA-1007 in the diagnosis of recurrent prostate cancer: a Markov chain decision analysis

Alberts

Mingels

Lanz

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

Purpose Amongst others, [68Ga]Ga-PSMA-11 and [18F]PSMA-1007 are available for the detection of recurrent prostate cancer (rPC). There are currently limited data comparing the performance of these two radioligands with respect to clinical outcomes or their cost efficacy, which this study aims to address. Methods Two hundred and forty-four patients undergoing PSMA PET/CT for rPC were retrospectively analysed for this study (one hundred and twenty two with each radiopharmaceutical) to generate rates of PET positivity, negativity and unclear findings. Patients underwent follow-up to determine the rate of additional examinations and to confirm PET findings. A Markov chain decision analysis was implemented to model clinical decision-making processes and to analyse clinical performance of the two tracers. We determine their clinical cost efficacies using cost data from several countries where both radiotracers are in routine use. Results The PET positivity rate was non-significantly higher for [18F]PSMA-1007 compared to [68Ga]Ga-PSMA-11 (91.8% vs. 86.9%, p = 0.68), whereas the rate of uncertain findings was significantly greater (17.2% vs. 8.25%, p = 0.02). The probability of a true positive finding was higher for [68Ga]Ga-PSMA-11 (0.90, 95% CI 0.70-0.98) vs. [18F]PSMA-1007 (0.81, 95% CI 0.66–0.91). A significantly (p < 0.0001) higher PPV for [68Ga]Ga-PSMA-11 (0.99, 95% CI 0.99–1.0 vs. 0.86) was found compared to [18F]PSMA-1007 (0.86, 95% CI 0.82–1.00). Intervention efficacy analysis favoured [68Ga]Ga-PSMA-11, where the number needed to image (to achieve a true positive finding) was 10.58 and the number needed to image to harm (to achieve a false positive finding) was − 8.08. A cost efficacy analysis favours [68Ga]Ga-PSMA-11 in three of the four jurisdictions analysed where health economic data was available (Switzerland, Israel, Australia) and [18F]PSMA-1007 in one jurisdiction (Denmark). Conclusion The analysis reveals a non-significantly higher PET positivity rate for [18F]PSMA-1007, but finds significantly greater rates of uncertain findings and false positive findings when compared to [68Ga]Ga-PSMA-11. We find differences in the two tracers in terms of clinical performance and cost efficacy. The method presented herein is generalisable and can be used with clinical or cost data for other countries or tracers.

show abstract

Section: Methodsmentioning

confidence: 99%

Comparing the clinical performance and cost efficacy of [68Ga]Ga-PSMA-11 and [18F]PSMA-1007 in the diagnosis of recurrent prostate cancer: a Markov chain decision analysis

Alberts

Mingels

Lanz

et al. 2021

Eur J Nucl Med Mol Imaging

View full text Add to dashboard Cite

show abstract

“…We compare our bayesint Python solution with the two following calculation options for calculating the uncertainty of a ratio of beta distributions. Matsen IV et al [13] uses the same Pham-Gia [17] density that we consider, but does not explicitly calculate the distribution on the basis of this density and Sverdlov et al [19] consider Nurminen and Mutanen [15] which is subsumed in Bekker-Nielsen Dunbar et al [1]. As such, we expect them to contain at least an implementation of the equaltailed credible interval, as it is the easier of the two to program.…”

Section: Comparisonsmentioning

confidence: 99%

bayesint: A Python Package for Calculating Bayesian Credible Intervals of Ratios of Beta Distributions

Dunbar

Finnie

2021

JORS

Self Cite

View full text Add to dashboard Cite

Some comments on the spread of the Black Death in Russia and Eurasia

Khaydarov¹

2022

De medio aevo

View full text Add to dashboard Cite

The article analyzes the process of the «Black Death» in the spaces of Eurasia and Russia. In the light of the latest advances in Yersinia pestis paleogenetics, epidemiology, climatology, and the study of historical sources, a host of scientific questions were resolved. This first affected a number of well-established historical facts since the bombing by troops of the Golden Horde Khan of Janibik in 1346 of the besieged Italian colony in the Crimea of Kafa. Many of them, despite all the scientific advances that have been made to date, have received little critical consideration. At the same time, the biggest shortcomings of the study of the Black Death until recently were the lack of a unified theoretical point of view. The article therefore focused on the convergence of the existing concepts of the emergence and spread of the second plague pandemic in Eurasia in the middle Ages. The study identified in pandemic processes the role of different types of plague hotspots, climate change, anthropogenic factors, urban development in densely populated areas and the road network of the Eurasian space. The poly variate start and implementation of the pandemic waves «Black Death» was recognized. The data thus obtained have allowed the motorist to rethink some of the issues related to the chronological interpretation of the events of the second plague pandemic.

show abstract

Methods for calculating credible intervals for ratios of beta distributions with application to relative risks of death during the second plague pandemic

Cited by 3 publications

References 16 publications

Comparing the clinical performance and cost efficacy of [68Ga]Ga-PSMA-11 and [18F]PSMA-1007 in the diagnosis of recurrent prostate cancer: a Markov chain decision analysis

Comparing the clinical performance and cost efficacy of [68Ga]Ga-PSMA-11 and [18F]PSMA-1007 in the diagnosis of recurrent prostate cancer: a Markov chain decision analysis

bayesint: A Python Package for Calculating Bayesian Credible Intervals of Ratios of Beta Distributions

Some comments on the spread of the Black Death in Russia and Eurasia

Contact Info

Product

Resources

About