Evaluating the importance of clinical data completeness in a real case of breast diagnosis

• Márcio Juchneski UFF
• Eudoxia Lottie Silva Moura UFF / IFRO
• Roger Resmini UFR
• Aura Conci UFF

DOI: https://doi.org/10.5753/sbcas.2024.2178

Abstract

This work focuses on verifying the importance of completeness of breast metadata for diagnosis aid systems. The aim is to investigate the possibility of using already known approaches to treat missing data and how they affect diagnoses. For a real case example, the Dataset for Mastologic Research (DMR), developed and made available at IC/UFF is used. This includes, in addition to clinical data, thermal breast images, mammograms, and diagnoses. After a bibliographical review of possible techniques, the Hot Deck was considered the most appropriate to be compared with the simple exclusion of attributes of missing data to classify known cases. Its use in classification of normal or abnormal patients resulted in 94% of correction in the Area Under the Receiver Operating Characteristic Curve (AUC) versus 92% if the six attributes with the largest amount of missing data were simply disregarded.

References

Instituto Nacional de Câncer INCA (2023) “Estatísticas de câncer”, Disponível em [link].

Arnold M., Morgan E., Rumgay H., Mafra A., Singh D., Laversanne M., Vignat J., Gralow J.R., Cardoso F., Siesling S., Soerjomataram I., (2022). "Current and future burden of breast cancer: Global statistics for 2020 and 2040", The Breast. DOI: 10.1016/j.breast.2022.08.010.

Donoho, D. "50 Years of Data Science." Journal of Computational and Graphical Statistics, vol. 26, no. 4, 2017, pp. 745-766. DOI: 10.1080/10618600.2017.1384734.

Pérez, A., Dennis, R.J., Gil, J.F.A., Rondón, M.A., and López, A. "Use of the mean, hot deck and multiple imputation techniques to predict outcome in intensive care unit patients in Colombia." Statist. Med., vol. 21, 2002, pp. 3885-389 DOI: 10.1002/sim.1391.

Barzi, F., Woodward, M. "Imputations of Missing Values in Practice: Results from Imputations of Serum Cholesterol in 28 Cohort Studies." American Journal of Epidemiology, vol. 160, no. 1, 2004, pp. 34-45. DOI: 10.1093/aje/kwh175.

Tang, L., Song, J., Belin, T.R., and Unützer, J. "A comparison of imputation methods in a longitudinal randomized clinical trial." Statist. Med., vol. 24, 2005, pp. 2111-2128. DOI: 10.1002/sim.2099.

Periyasamy, S., Prakasarao, A., Menaka, M., Venkatraman, B., Jayashree, M. (2021). Thermal Grading Scale for Classification of Breast Thermograms. IEEE Sensors Journal, 21(13), 13996–14002. DOI: 10.1109/JSEN.2020.3045455.

Pérez-Martín, J. e Sánchez-Cauce, R., “Quality analysis of a breast thermal images database”, Health Informatics Journal, 2023, DOI: 10.1177/14604582231153779 [link].

Silva, L. F., et al. "A new database for breast research with infrared images." Journal of Medical Imaging and Health Informatics 4.1 (2014): 92-100.

Lee, C. H., Dershaw, D. D., Kopans, D., Evans, P., Monsees, B., Monticciolo, D., Burhenne, L. W. (2010). Breast cancer screening with imaging: recommendations from the Society of Breast Imaging and the ACR on the use of mammography, breast MRI, breast ultrasound, and other technologies for the detection of clinically occult breast cancer. Journal of the American College of Radiology, 7(1), 1827.

Neal, C. H., Flynt, K. A., Jeffries, D. O., Helvie, M. A. (2018). Breast Imaging Outcomes following Abnormal Thermography. Academic Radiology, 25(3), 273–278. DOI: 10.1016/j.acra.2017.10.015.

Heena, H., Durrani, S., Riaz, M., Al Fayyad, I., Tabasim, R., Parvez, G., & AbuShaheen, A. (2019). Knowledge, attitudes, and practices related to breast cancer screening among female health care professionals: a cross sectional study. BMC women's health, 19, 1-112019.

Ragavendra, U., Gudigar, A., Rao, T. N., Ciaccio, E. J., Ng, E. Y. K., & Rajendra Acharya, U. (2019). Computer-aided diagnosis for the identification of breast cancer using thermogram images: A comprehensive review. Infrared Physics & Technology, 102, 103041. DOI: 10.1016/j.infrared.2019.103041.

Andridge, R. R, Little R. J. "A Review of Hot Deck Imputation for Survey Nonresponse." Int Stat Rev, vol. 78, no. 1, 2010, pp. 40-64. DOI: 10.1111/j.17515823.2010.00103.x.

Resmini, R. et al. Combining genetic algorithms and SVM for breast cancer diagnosis using infrared thermography. Sensors, v. 21, n. 14, p. 4802, 2021.