RESUMO
BACKGROUND: To examine the effectiveness of the use of machine learning for adapting an intraocular lens (IOL) power calculation for a patient group. METHODS: In this retrospective study, the clinical records of 1,611 eyes of 1,169 Japanese patients who received a single model of monofocal IOL (SN60WF, Alcon) at Miyata Eye Hospital were reviewed and analyzed. Using biometric metrics and postoperative refractions of 1211 eyes of 769 patients, constants of the SRK/T and Haigis formulas were optimized. The SRK/T formula was adapted using a support vector regressor. Prediction errors in the use of adapted formulas as well as the SRK/T, Haigis, Hill-RBF and Barrett Universal II formulas were evaluated with data from 395 eyes of 395 distinct patients. Mean prediction errors, median absolute errors, and percentages of eyes within ± 0.25 D, ± 0.50 D, and ± 1.00 D, and over + 0.50 D of errors were compared among formulas. RESULTS: The mean prediction errors in the use of the SRT/K and adapted formulas were smaller than the use of other formulas (P < 0.001). In the absolute errors, the Hill-RBF and adapted methods were better than others. The performance of the Barrett Universal II was not better than the others for the patient group. There were the least eyes with hyperopic refractive errors (16.5%) in the use of the adapted formula. CONCLUSIONS: Adapting IOL power calculations using machine learning technology with data from a particular patient group was effective and promising.
RESUMO
Ethnicity may be considered a factor when considering what size endotracheal tube to insert. In particular it has been suggested that Chinese patients have a smaller tracheal diameter, justifying the selection of smaller endotracheal tubes. We systematically evaluated transverse tracheal diameters in Chinese and Caucasian patients, utilising archived computer tomography images. A convenience sample of 100 Caucasian patients from Australia was compared with 100 Chinese patients from Hong Kong. Patients over 18 years of age who had undergone a computerised tomography scan of the neck and thorax, and also had accurate body height and weight recorded, were studied. The mean transverse diameter of the trachea measured at three levels was similar between the Chinese and Caucasian patients. At the narrowest measurement point, the immediate subcricoid transverse diameter, the unadjusted mean difference between male Chinese and Caucasian patients was small (1 mm, standard deviation 0.83 mm, P=0.01), and similarly small between female Chinese and Caucasian patients (1.5 mm, standard deviation 0.8 mm, P <0.01). Multivariate analysis demonstrated only a small influence related to ethnicity (12% relative contribution to the overall variance [R2] of the model), but substantial influence of height (40%) and sex (41%). Our findings do not support the practice of routinely selecting a smaller endotracheal tube size for Chinese patients on the basis that there is a difference related to the Chinese ethnic phenotype. Considerations regarding choice of endotracheal tube size should rather focus on patient sex and height.