Feasibility of New Method for the Prediction of Clinical Trial Results Using Compressive Sensing of Artificial Intelligence
DOI:
https://doi.org/10.14738/bjhmr.101.14061Keywords:
Clinical Trial, Artificial Intelligence, Compressive Sensing, Computer Science, Study DesignAbstract
To develop a new method for interim analysis to obtain the p-values distribution profile of the log-rank test and the statistical power at various information fraction by iteratively predicting the lacking time data of censored and uncensored cases respectively for each arm at the time when the determined sample size will be achieved. A compressive sensing algorithm derived from artificial intelligence was developed for comparing two groups of clinical trial data from real-world databases of deidentified individual participant-level data. The judgement of the interim analysis was compared to the conventional method, with our method demonstrating that it was at least comparable to the conventional method. The power by our method was higher than the conditional power of the conventional method. When α-error by log-rank test was focused, our method seemed to have made the right decision earlier than the conventional method. It may be possible to expand the options of applicable methods for interim analysis. It would be helpful in establishing efficacy and futility judgement in clinical trials.
References
Simon, R. (1989) Optimal two-stage designs for phase II clinical trials. Control Clin Trials, 10, 1-10.
Jung, S. H., Lee, T., Kim, K. and George, S. L. (2004). Admissible two-stage designs for phase II cancer clinical trials. Statist in Med., 23, 561-569.
Aspril, J. (2018) Clinical trials to obtain FDA approval typically account for small proportion of total drug research and development costs, study suggests. Johns Hopkins Bloomberg School of Public Health, https://publichealth.jhu.edu/2018/cost-of-clinical-trials-for-new-drug-FDA-approval-are-fraction-oftotal-tab
DiMasi, J. A., Grabowski, H. G. and Hansen, R. W. (2016). Innovation in the pharmaceutical industry: new estimates of R&D costs. J Health Economics, 47, 20-33., https://doi.org/10.1016/j.jhealeco.2016.01.012.
Gordon Lan, K. K. and DeMets, D. L. (1983). Discrete sequential boundaries for clinical trials. Biometrika, 70, 659-663.
Pocock, S.J. (1977) Group sequential method in the design and analysis of clinical trials. Biometrika, 64,
O’Brien, P.C. & Fleming, T.R. (1979) A multiple testing procedure for clinical trials. Biometrics, 35, 549-612.
Uemura, K., Matsuyama, Y. & Ohashi, Y. (2008) A Modification of the 50%-Conditional Power Approach for Increasing the Sample Size Based on an Interim Estimate of Treatment Difference. Jpn J Biometrices, 29,
Jitlal, M., Khan, I., Lee, S. M. and Hackshaw, A. (2012). Stopping clinical trials early for futility: retrospective analysis of several randomised clinical studies. Br J Cancer, 107, 910-917. https://doi.org/10.1038/bjc.2012.344
Chen, Y.H., DeMets, D.L. and Gordon Lan, K.K. (2004) Increasing sample size when the unblinded interim result is promising. Statist in Medicine, 23, 1023–1038.
Candés, E.J., Romberg, J. and Toa, T. (2006) Robust uncertainty principles: Exact signal reconstruction from highly incomplete frequency information. IEEE Trans Inf Theory, 52, 489-509.
Donoho, D.L. (2006) Compressed sensing. IEEE Trans. Inf. Theory, 52, 1289–1306.
Candès, E.J. and Tao, T. (2006) Near-optimal signal recovery from random projections: Universal encoding strategies? IEEE Trans. Inf. Theory, 52, 5406–5425.
Rani, M., Dhok, S.B. & Deshmukh, R.B. (2018) A systematic review of compressive sensing: Concepts, implementations and applications. IEEE Access, 6, 4875-4894.
Miyagi, Y., Fujiwara, K., Oda, T., Miyake, T. and Coleman, R. L. (2018). Development of new method for the prediction of clinical trial results using compressive sensing of artificial intelligence. J Biostat Biometric., 3, 202.
Miyagi, Y., Fujiwara, K., Oda, T., Miyake, T. and Coleman, R.L. (2020) Studies on Development of New Method for the Prediction of Clinical Trial Results Using Compressive Sensing of Artificial Intelligence. In: Theory and Practice of Mathematics and Computer Science (ed M.A.M. Ferreira), pp101-108. Hooghly, West Bengal, India: Book Publisher International. Print ISBN: 978-93-90206-63-6, eBook ISBN: 978-93-90206-64-3 DOI: 10.9734/bpi/tpmcs/v2 https://bp.bookpi.org/index.php/bpi/catalog/book/271
Taichman DB, Sahni P, Pinborg A, Peiperl L, Laine C, James A., et al. (2017) Data sharing statements for clinical trials: a requirement of the International Committee of Medical Journal Editors. Annals of Internal medicine. 167, 63-5.
Stewart, L. A., Clarke, M., Rovers, M., Riley, R. D., Simmonds, M., Stewart, G. and Tierney, J. F. (2015). Preferred reporting items for a systematic review and meta-analysis of individual participant data: the PRISMA-IPD statement. Jama., 313, 1657-1665. DOI: 10.1001/jama.2015.3656.
Hussain, J. A., White, I. R., Johnson, M. J., Bland, M. and Currow, D. C. (2021). Performance status and trial site-level factors are associated with missing data in palliative care trials: An individual participant-level data analysis of 10 phase 3 trials. Palliative medicine, 35, 1998-2007. doi: 10.1177/02692163211040970. Epub 2021 Sep 16.
Van Cutsem, E., Yoshino, T., Lenz, H.J., Lonardi, S., Falcone, A., Limón, M.L., et al. (2018) Nintedanib for the treatment of patients with refractory metastatic colorectal cancer (LUME-Colon 1): a phase III, international, randomized, placebo-controlled study. Ann Oncol., 29, 1955-1963. https://doi.org/10.1093/annonc/mdy241.
Tabernero, J., Yoshino, T., Cohn, A. L., Obermannova, R., Bodoky, G., Garcia-Carbonero, R., et al. (2015). Ramucirumab versus placebo in combination with second-line FOLFIRI in patients with metastatic colorectal carcinoma that progressed during or after first-line therapy with bevacizumab, oxaliplatin, and a fluoropyrimidine (RAISE): a randomised, double-blind, multicentre, phase 3 study. Lancet Oncol., 16,
Aghajanian, C., Goff, B., Nycum, L.R., Wang, Y.V., Husain, A. and Blank, S.V. (2015) Final overall survival and safety analysis of OCEANS, a phase 3 trial of chemotherapy with or without bevacizumab in patients with platinum-sensitive recurrent ovarian cancer. Gynecol. Oncol. 139, 10-16. doi: 10.1016/j.ygyno.2015.08.004.
Pujade-Lauraine, E., Hilpert, F., Weber, B., Reuss, A., Poveda, A., Kristensen, G., et al. (2014). Bevacizumab combined with chemotherapy for platinum-resistant recurrent ovarian cancer: the AURELIA open-label randomized phase III trial. Obstet Gynecol Survey, 69, 402-404.
Bamias, A., Gibbs, E., Khoon Lee, C., Davies, L., Dimopoulos, M., Zagouri, F., et al. (2017) Bevacizumab with or after chemotherapy for platinum-resistant recurrent ovarian cancer: exploratory analyses of the AURELIA trial. Ann. Oncol., 28, 1842-1848. doi: 10.1093/annonc/mdx228.
Bennouna, J., Sastre, J., Arnold, D., Österlund, P., Greil, R., Van Cutsem, E., et al. (2013) ML18147 Study Investigators. Continuation of bevacizumab after first progression in metastatic colorectal cancer (ML18147): a randomised phase 3 trial. Lancet Oncol. 14, 29-37. doi: 10.1016/S1470-2045(12)70477-1.
Miyagi, Y., Tada, K., Yasuhi, I., Maekawa, Y., Okura, N., Kawakami, K., et al. (2020) New method for determining fibrinogen and FDP threshold criteria by artificial intelligence in cases of massive hemorrhage during delivery. J Obstet Gynaecol Res., 46, 256–265. https://doi.org/10.1111/jog.14166
Forbes, C., Evans, M., Hastings, N. & Peacock, B. (2011). Statistical distributions (Vol. 4). New York: Wiley.
Chen, M.Z., Chen, H., Ma, Y.C., Wang, B. and Tang, Y. (2011). Recovery rate Models Based on General Beta Regression for Non-performing Loan. J Applied Stat Management, 30, 810–823.
Zhai, Z., Jia, G. & Wang, K. (2018) A Novel Teaching-Learning-Based Optimization with Error Correction and Cauchy Distribution for Path Planning of Unmanned Air Vehicle. Comput Intell Neurosci., 2018, Article ID 5671709. https://doi.org/10.1155/2018/5671709
Anderson, D. (1981) Maximum Likelihood Estimation in the Non-Central Chi Distribution with Unknown Scale Parameter. Sankhyā: The Ind. J. Stat. Series B., 43, 58-67.
Satterthwaite, F. E. (1946). An approximate distribution of estimates of variance components. Biometrics bulletin, 2, 110-114.
Epstein B. and Sobel M. (1954) Some Theorems Relevant to Life Testing from an Exponential Distribution. Ann Math Statist., 25, 373-381. doi:10.1214/aoms/1177728793.
Hosking, J. R. M., Wallis, J. R. and Wood, E. F. (1985). Estimation of the generalized extreme-value distribution by the method of probability-weighted moments. Technometrics, 27, 251-261.
Nadarajah, S. & Kotz, S. (2003) The exponentiated Fréchet distribution. Interstat Electronic J.,14, 1-7.
Stacy, E.W. (1962) A Generalization of the Gamma Distribution. Ann Math Statist., 33, 1187–1192. doi:10.1214/aoms/1177704481. https://projecteuclid.org/euclid.aoms/1177704481
Nadarajah, S. & Kotz, S. (2004) The beta Gumbel distribution. Math Problems in engineering, 4, 323-332.
Cooray, K. and Ananda, M. (2008) A generalization of the half-normal distribution with applications to lifetime data. Communications in Statistics—Theory and Methods, 37, 1323-1337.
Chhikara, R.S. and Folks, J.L. (1977) The inverse Gaussian distribution as a lifetime model. Technometrics, 19, 461-468.
Barndorff-Nielsen, O.E. (1997) Normal inverse Gaussian distributions and stochastic volatility models, Scand. J. Statist., 24, 1–13. URL: http://dx.doi.org/10.14738/jbemi.101.14061 265
Reed, W.J. (2006) The Normal-Laplace Distribution and Its Relatives. In: Advances in Distribution Theory, Order Statistics, and Inference. Statistics (eds N. Balakrishnan, J.M. Sarabia and E. Castillo), pp. 61-74. Boston: Birkhäuser.
Coronel-Brizio, H.F. & Hernandez-Montoya, A.R. (2005) On fitting the Pareto–Levy distribution to stock market index data: Selecting a suitable cutoff value. Physica A: Stat Mech Appl, 354, 437-449.
Gupta, S. S. and Gnanadesikan, M. (1966). Estimation of the parameters of the logistic distribution. Biometrika, 53, 565-570.
Mudholkar, G. S. and George, E. O. (1978). A remark on the shape of the logistic distribution. Biometrika, 65, 667-668.
Limpert, E., Stahel, W. A. and Abbt, M. (2001). Log-normal distributions across the sciences: keys and clues: on the charms of statistics, and how mechanical models resembling gambling machines offer a link to a handy way to characterize log-normal distributions, which can provide deeper insight into variability and probability—normal or log-normal: that is the question. BioScience, 51, 341-352.
Koch AL. (1966). The logarithm in biology. I. Mechanisms generating the log-normal distribution exactly. J Theoret Biol 23, 276–290.
Reed, W.J. & Jorgensen, M. (2004) The double Pareto-lognormal distribution: A new parametric model for size distributions. Communications in Statistics—Theory and Methods, 33, 1733–1753.
Roy, D. (2004) Discrete rayleigh distribution. IEEE Transactions on Reliability. 53, 255-260.
Ord, J.K. (1968) The Discrete Student's t Distribution. The Annals of Mathematical Statistics, 39, 1513-1516.
Avigad, J. (2013) Uniform distribution and algorithmic randomness. The J. Symbolic. Logic., 78, 334-344.
Miyagi, Y. and Miyake, T. (2020) Potential of artificial intelligence for estimating Japanese fetal weights. Acta Medica Okayama, 74, 483-493.
Miyagi, Y., Habara, T., Hirata, R. and Hayashi, N. (2019) Feasibility of deep learning for predicting live birth from a blastocyst image in patients classified by age. Reprod Med Biol., 18, 190-203.
Miyagi, Y., Habara, T., Hirata, R. and Hayashi, N. (2019). Feasibility of artificial intelligence for predicting live birth without aneuploidy from a blastocyst image. Reprod Med Biol., 18, 204-211.
Miyagi, Y., Habara, T., Hirata, R. and Hayashi, N. (2019). Feasibility of predicting live birth by combining conventional embryo evaluation with artificial intelligence applied to a blastocyst image in patients classified by age. Reprod Med Biol., 18, 344–35.
Miyagi, Y., Habara, T., Hirata, R. and Hayashi, N. (2020). Predicting a live birth by artificial intelligence incorporating both the blastocyst image and conventional embryo evaluation parameters. Artif Intell Med Imaging, 1, 94-107.
Miyagi, Y., Habara, T., Hirata, R. and Hayashi, N. (2022) New methods for comparing embryo selection methods by applying artificial intelligence: Comparing embryo selection AI for live births. Br J Healthcare Med Res., 9, 36–44.
Miyagi, Y., Habara, T., Hirata, R. and Hayashi, N. (2022). Deep Learning to Predicting Live Births and Aneuploid Miscarriages from Images of Blastocysts Combined with Maternal Age. Int J Bioinform Intellig Comput., 1, 10-21.
Miyagi, Y., Hata, T., Bouno, S., Koyanagi, A. and Miyake, T. (2021). Recognition of facial expression of fetuses by artificial intelligence (AI). J Perinat Med, 49, 596-603.
Miyagi, Y., Hata, T., Bouno, S., Koyanagi, A. and Miyake, T. (2021). Recognition of fetal facial expressions using artificial intelligence deep learning. Donald School J Ultrasound Obstet Gynecol 15, 223-228.
Miyagi, Y., Takehara, K. and Miyake, T. (2019) Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images. Mol Clin Oncol., 11, 583-589.
Miyagi, Y., Takehara, K., Nagayasu, Y. and Miyake, T. (2020). Application of deep learning to the classification of uterine cervical squamous epithelial lesion from colposcopy images combined with HPV types. Oncol Lett., 19, 1602-1610.
Miyagi, Y., Hata, T, Bouno., S, Koyanagi. and Miyake, T. (2022) Artificial intelligence to understand fluctuation of fetal brain activity by recognizing facial expressions. Int J Gynecol Obstet. doi: 10.1002/ijgo.14569
Müller, H.H. and Schäfer, H. (2001) Adaptive group sequential designs for clinical trials: combining the advantages of adaptive and of classical group sequential approaches. Biometrics, 57, 886-891. doi: 10.1111/j.0006-341x.2001.00886.x.
Lehmacher, W. and Wassmer, G. (1999). Adaptive sample size calculations in group sequential trials. Biometrics, 55, 1286-1290. doi: 10.1111/j.0006-341x.1999.01286. x. PMID: 11315085.
Wassmer, G. (2006) Planning and analyzing adaptive group sequential survival trials. Biom J., 48, 714-29. doi: 10.1002/bimj.200510190. PMID: 16972724.
Bauer, P. and Kohne, K. (1994) Evaluation of Experiments with Adaptive Interim Analyses. Biometrics, 50, 1029–1041. https://doi.org/10.2307/2533441
Chang, M. (2007) Adaptive design method based on sum of p-values. Statist in Med., 26, 2772-2784.
Chow, S.C. and Chang, M. (2008) Adaptive design methods in clinical trials – a review. Orphanet J Rare Dis., 3, 11. https://doi.org/10.1186/1750-1172-3-11
Shun, Z., Lan, K.G. and Soo, Y. (2008) Interim treatment selection using the normal approximation approach in clinical trials. Statist in Med., 27, 597-618.
Jenkins, M., Stone, A. and Jennison, C. (2011). An adaptive seamless phase II/III design for oncology trials with subpopulation selection using correlated survival endpoints. Pharmaceutical statistics, 10, 347-356.
Bauer, P. and Kieser, M. (1999) Combining different phases in the development of medical treatments within a single trial. Statist. in Med., 18, 1833-1848.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2023 Yasunari Miyagi, Keiichi Fujiwara, Hisanaga Nomura, Koji Yamamoto, Robert L Coleman
This work is licensed under a Creative Commons Attribution 4.0 International License.
