Eficacia de los resultados no estadísticamente significativos de los ensayos clínicos en anestesiología: un estudio transversal
| dc.contributor.advisor | Tellez, Cristian | |
| dc.contributor.author | Lasso Andrade, Fabricio Andres | |
| dc.contributor.orcid | 0000-0002-0641-0479 | |
| dc.date.accessioned | 2025-07-15T14:08:15Z | |
| dc.date.available | 2025-07-15T14:08:15Z | |
| dc.date.issued | 2025-06 | |
| dc.description.abstract | Introducción: Los ensayos clínicos aleatorizados (ECA) son el estándar para evaluar intervenciones en salud. Sin embargo, la interpretación tradicional basada en el valor p < 0.05 ha sido cuestionada, especialmente cuando los resultados no alcanzan significancia estadística. Estos casos pueden ocultar efectos clínicamente relevantes. La razón de verosimilitud (LR) podría ser una estadística alternativa al valor p, muestra que tanto favorecen los datos a la hipótesis nula o alterna. Objetivo: Evaluar si el uso de la razón de verosimilitud (LR) aporta evidencia adicional al valor p, para interpretar resultados primarios no significativos en ensayos clínicos de anestesiología. Métodos: Se realizó un estudio transversal sobre ECA publicados retrospectivamente desde diciembre de 2024 en revistas Q1 y Q2 de anestesiología. Se incluyeron ensayos con resultados primarios no significativos (p > 0.05) y con datos suficientes para calcular la LR. Se evaluó su distribución, asociación con el valor p y su impacto en la probabilidad post-prueba en distintos escenarios pretest. Resultados: Se identificaron inicialmente 642 ECA de los que 117 cumplieron los criterios de inclusión. El 26.5% tuvo una LR < 1 (evidencia a favor de la hipótesis alternativa), y el 35.1% tuvo LR ≥ 100 (fuerte evidencia a favor de la hipótesis nula). En escenarios con probabilidad pretest del 10%, 25% o 50% una LR ≥ 100 elevó la probabilidad post-prueba de la hipótesis nula a una probabilidad mayor al 96%. La correlación entre LR y valor p fue baja (ρ = 0.076), sugiriendo que ambas medidas aportan información distinta. Conclusión: La razón de verosimilitud permite una interpretación matizada de los resultados no significativos en los ECA en anestesiología. La LR da una información adicional al valor p y puede mejorar la toma de decisiones en investigación clínica. | |
| dc.description.abstractenglish | Introduction: Randomized controlled trials (RCTs) are the gold standard for evaluating health interventions. However, the traditional interpretation based on a p-value < 0.05 has been questioned, particularly when results do not reach statistical significance. These cases may obscure clinically relevant effects. The likelihood ratio (LR) could serve as an alternative to the p-value, indicating how much the data support either the null or the alternative hypothesis. Objective: To assess whether the use of the likelihood ratio (LR) provides additional evidence beyond the p-value for interpreting non-significant primary outcomes in anesthesiology clinical trials. Methods: A cross-sectional study was conducted on RCTs published retrospectively since December 2024 in Q1 and Q2 anesthesiology journals. Trials with non-significant primary outcomes (p > 0.05) and sufficient data to calculate the LR were included. The distribution of LR was evaluated, along with its association with the p-value and its impact on post-test probability across different pretest scenarios. Results: A total of 642 RCTs were initially identified, of which 117 met the inclusion criteria. Of these, 26.5% had an LR < 1 (evidence favoring the alternative hypothesis), and 35.1% had an LR ≥ 100 (strong evidence favoring the null hypothesis). In scenarios with pretest probabilities of 10%, 25%, or 50%, an LR ≥ 100 increased the post-test probability of the null hypothesis to over 96%. The correlation between LR and p-value was low (ρ = 0.076), suggesting that both measures provide distinct information. Conclusion: The likelihood ratio allows for a more nuanced interpretation of non-significant results in anesthesiology RCTs. LR provides additional information beyond the p-value and may improve decision-making in clinical research. | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12495/14955 | |
| dc.language.iso | es | |
| dc.relation.references | Aronson JK. What is a clinical trial? British Journal of Clinical Pharmacology. 2004;58(1):1-3. | |
| dc.relation.references | Bothwell LE, Greene JA, Podolsky SH, Jones DS. Assessing the Gold Standard — Lessons from the History of RCTs. New England Journal of Medicine. 2 de junio de 2016;374(22):2175-81. | |
| dc.relation.references | Fisher R. Statistical Methods for Research Workers. In: Kotz, S., Johnson, N.L. (eds) Breakthroughs in Statistics. [Internet]. New York, NY: Springer; 1992 [citado 3 de mayo de 2025]. Disponible en: https://doi.org/10.1007/978-1-4612-4380-9_6 | |
| dc.relation.references | Hurlbert SH, Levine ,Richard A., and Utts J. Coup de Grâce for a Tough Old Bull: “Statistically Significant” Expires. The American Statistician [Internet]. 29 de marzo de 2019 [citado 3 de mayo de 2025];73(sup1):352-7. Disponible en: https://doi.org/10.1080/00031305.2018.1543616 | |
| dc.relation.references | Amrhein V, Greenland S, McShane B. Scientists rise up against statistical significance. Nature [Internet]. marzo de 2019 [citado 3 de mayo de 2025];567(7748):305-7. Disponible en: https://www.nature.com/articles/d41586-019-00857-9 | |
| dc.relation.references | Lash TL. The Harm Done to Reproducibility by the Culture of Null Hypothesis Significance Testing. American Journal of Epidemiology [Internet]. 15 de septiembre de 2017 [citado 3 de mayo de 2025];186(6):627-35. Disponible en: https://doi.org/10.1093/aje/kwx261 | |
| dc.relation.references | Concato J, Hartigan JA. P Values: From Suggestion to Superstition. Journal of Investigative Medicine [Internet]. 1 de octubre de 2016 [citado 3 de mayo de 2025];64(7):1166-71. Disponible en: https://doi.org/10.1136/jim-2016-000206 | |
| dc.relation.references | Altman DG, Bland JM. Absence of evidence is not evidence of absence. BMJ. 19 de agosto de 1995;311(7003):485. | |
| dc.relation.references | Ioannidis JPA. Why Most Published Research Findings Are False. PLOS Medicine [Internet]. 30 de agosto de 2005 [citado 3 de mayo de 2025];2(8):e124. Disponible en: https://journals.plos.org/plosmedicine/article?id=10.1371/journal.pmed.0020124 | |
| dc.relation.references | Greenland S, Senn SJ, Rothman KJ, Carlin JB, Poole C, Goodman SN, et al. Statistical tests, P values, confidence intervals, and power: a guide to misinterpretations. Eur J Epidemiol. abril de 2016;31(4):337-50. | |
| dc.relation.references | Gardner MJ, Altman DG. Confidence intervals rather than P values: estimation rather than hypothesis testing. Br Med J (Clin Res Ed) [Internet]. 15 de marzo de 1986 [citado 3 de mayo de 2025];292(6522):746-50. Disponible en: https://www.bmj.com/content/292/6522/746 | |
| dc.relation.references | Walter SD. Choice of effect measure for epidemiological data. J Clin Epidemiol. septiembre de 2000;53(9):931-9. | |
| dc.relation.references | Cumming G. The New Statistics: Why and How. Psychol Sci [Internet]. 1 de enero de 2014 [citado 3 de mayo de 2025];25(1):7-29. Disponible en: https://doi.org/10.1177/0956797613504966 | |
| dc.relation.references | Goodman SN. Toward evidence-based medical statistics. 1: The P value fallacy. Ann Intern Med. 15 de junio de 1999;130(12):995-1004. | |
| dc.relation.references | Perneger TV. How to use likelihood ratios to interpret evidence from randomized trials. J Clin Epidemiol. agosto de 2021;136:235-42. | |
| dc.relation.references | Falagas ME, Kouranos VD, Arencibia-Jorge R, Karageorgopoulos DE. Comparison of SCImago journal rank indicator with journal impact factor. FASEB J. agosto de 2008;22(8):2623-8. | |
| dc.relation.references | Doi SA, Furuya-Kanamori L, Xu C, Lin L, Chivese T, Thalib L. Controversy and Debate: Questionable utility of the relative risk in clinical research: Paper 1: A call for change to practice. J Clin Epidemiol. febrero de 2022;142:271-9. | |
| dc.relation.references | Hoekstra R, Monden R, van Ravenzwaaij D, Wagenmakers EJ. Bayesian reanalysis of null results reported in medicine: Strong yet variable evidence for the absence of treatment effects. PLoS One. 2018;13(4):e0195474. | |
| dc.relation.references | Chen Y, Moustaki I, Zhang H. A Note on Likelihood Ratio Tests for Models with Latent Variables. Psychometrika [Internet]. 1 de diciembre de 2020 [citado 19 de mayo de 2025];85(4):996-1012. Disponible en: https://doi.org/10.1007/s11336-020-09735-0 | |
| dc.relation.references | Bayes T, Price null. LII. An essay towards solving a problem in the doctrine of chances. By the late Rev. Mr. Bayes, F. R. S. communicated by Mr. Price, in a letter to John Canton, A. M. F. R. S. Philosophical Transactions of the Royal Society of London [Internet]. enero de 1997 [citado 19 de mayo de 2025];53:370-418. Disponible en: https://royalsocietypublishing.org/doi/10.1098/rstl.1763.0053 | |
| dc.relation.references | Wasserstein RL, and Lazar NA. The ASA Statement on p-Values: Context, Process, and Purpose. The American Statistician [Internet]. 2 de abril de 2016 [citado 19 de mayo de 2025];70(2):129-33. Disponible en: https://doi.org/10.1080/00031305.2016.1154108 | |
| dc.relation.references | Neyman J, Pearson ES, Pearson K. IX. On the problem of the most efficient tests of statistical hypotheses. Philosophical Transactions of the Royal Society of London Series A, Containing Papers of a Mathematical or Physical Character [Internet]. enero de 1997 [citado 19 de mayo de 2025];231(694-706):289-337. Disponible en: https://royalsocietypublishing.org/doi/10.1098/rsta.1933.0009 | |
| dc.relation.references | Kass RE, and Raftery AE. Bayes Factors. Journal of the American Statistical Association [Internet]. 1 de junio de 1995 [citado 19 de mayo de 2025];90(430):773-95. Disponible en: https://www.tandfonline.com/doi/abs/10.1080/01621459.1995.10476572 | |
| dc.relation.references | Gignac GE, Szodorai ET. Effect size guidelines for individual differences researchers. Personality and Individual Differences [Internet]. 1 de noviembre de 2016 [citado 19 de mayo de 2025];102:74-8. Disponible en: https://www.sciencedirect.com/science/article/pii/S0191886916308194 | |
| dc.relation.references | Fornacon-Wood I, Mistry H, Johnson-Hart C, Faivre-Finn C, O’Connor JPB, Price GJ. Understanding the Differences Between Bayesian and Frequentist Statistics. International Journal of Radiation Oncology, Biology, Physics [Internet]. 1 de abril de 2022 [citado 19 de mayo de 2025];112(5):1076-82. Disponible en: https://www.redjournal.org/article/S0360-3016%2821%2903256-9/fulltext?utm_source=chatgpt.com | |
| dc.relation.references | Ioannidis JPA, Greenland S, Hlatky MA, Khoury MJ, Macleod MR, Moher D, et al. Increasing value and reducing waste in research design, conduct, and analysis. Lancet. 11 de enero de 2014;383(9912):166-75. | |
| dc.relation.references | Burt T, Button KS, Thom H, Noveck RJ, Munafò MR. The Burden of the «False-Negatives» in Clinical Development: Analyses of Current and Alternative Scenarios and Corrective Measures. Clin Transl Sci. noviembre de 2017;10(6):470-9. | |
| dc.relation.references | Perneger TV. How to use likelihood ratios to interpret evidence from randomized trials. J Clin Epidemiol. agosto de 2021;136:235-42. | |
| dc.relation.references | Matthews RAJ. Beyond ‘significance’: principles and practice of the Analysis of Credibility. Royal Society Open Science [Internet]. 17 de enero de 2018 [citado 19 de mayo de 2025];5(1):171047. Disponible en: https://royalsocietypublishing.org/doi/10.1098/rsos.171047 | |
| dc.relation.references | Button KS, Ioannidis JPA, Mokrysz C, Nosek BA, Flint J, Robinson ESJ, et al. Power failure: why small sample size undermines the reliability of neuroscience. Nat Rev Neurosci. mayo de 2013;14(5):365-76. | |
| dc.relation.references | De Oliveira GS, Chang R, Kendall MC, Fitzgerald PC, McCarthy RJ. Publication bias in the anesthesiology literature. Anesth Analg. mayo de 2012;114(5):1042-8. | |
| dc.rights | Attribution-NonCommercial-ShareAlike 4.0 International | en |
| dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/4.0/ | |
| dc.subject | Likelihood Functions | |
| dc.subject | Clinical Trials as Topic | |
| dc.subject | Bayes Theorem | |
| dc.subject.keywords | Likelihood Functions | |
| dc.subject.keywords | Clinical Trials as Topic | |
| dc.subject.keywords | Bayes Theorem | |
| dc.title | Eficacia de los resultados no estadísticamente significativos de los ensayos clínicos en anestesiología: un estudio transversal | |
| dc.title.translated | Efficacy of Non-Statistically Significant Results in Anesthesiology Clinical Trials: A Cross-Sectional Study |
Archivos
Bloque original
1 - 1 de 1
Cargando...
- Nombre:
- Trabajo de grado.pdf
- Tamaño:
- 563.51 KB
- Formato:
- Adobe Portable Document Format
Bloque de licencias
1 - 3 de 3
Cargando...
- Nombre:
- license.txt
- Tamaño:
- 1.95 KB
- Formato:
- Item-specific license agreed upon to submission
- Descripción:
Cargando...
- Nombre:
- Carta de autorizacion.pdf
- Tamaño:
- 101.77 KB
- Formato:
- Adobe Portable Document Format
- Descripción:
Cargando...
- Nombre:
- Anexo 1 acta de aprobacion.pdf
- Tamaño:
- 381.8 KB
- Formato:
- Adobe Portable Document Format
- Descripción:
