Purpose: To evaluate the effect of axial length (AL) and the average preoperative keratometry (K) on the A constant in the SRK/T formula. Methods: The retrospective, comparative case series includes 635 eyes from 407 ...Purpose: To evaluate the effect of axial length (AL) and the average preoperative keratometry (K) on the A constant in the SRK/T formula. Methods: The retrospective, comparative case series includes 635 eyes from 407 cataract patients from Columbia University Medical Center from January 2006 to August 2010, operated by a single surgeon using a temporal incision and the Acrysof SN60WF IOL (Alcon Laboratories, TX). Using the postoperative manifest refraction and biometry data, we calculated the precise A constant (Ap) necessary to yield the postoperative spherical equivalent for each eye. To optimize the A constant, we developed three regression models (linear, quadratic, and categorical in 7 AL groups) to relate these precise A constants to AL and K. We verified our method with another series of 45 eyes for which we calculated mean errors (defined as the difference between the spherical equivalent of the postoperative refraction and the predicted postoperative refraction) using the optimized and manufacturer’s suggested A constants. Results: There is a statistically significant relationship between AL (P < 0.001), K (P < 0.001) and the A constant. Ap increased as AL increased and as K decreased. In the validation data set, optimizing the A constant reduced mean errors from 0.50 D to 0.25 D and also reduced hyperopic refractive outcomes. Conclusions: The A constant for longer eyes with flatter corneas is larger than the A constant for shorter eyes with steeper corneas. Optimizing A constants using both AL and K improved the predictability of refractive outcomes without modification to the SRK/T formula.展开更多
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 ...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.展开更多
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 ...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.展开更多
文摘Purpose: To evaluate the effect of axial length (AL) and the average preoperative keratometry (K) on the A constant in the SRK/T formula. Methods: The retrospective, comparative case series includes 635 eyes from 407 cataract patients from Columbia University Medical Center from January 2006 to August 2010, operated by a single surgeon using a temporal incision and the Acrysof SN60WF IOL (Alcon Laboratories, TX). Using the postoperative manifest refraction and biometry data, we calculated the precise A constant (Ap) necessary to yield the postoperative spherical equivalent for each eye. To optimize the A constant, we developed three regression models (linear, quadratic, and categorical in 7 AL groups) to relate these precise A constants to AL and K. We verified our method with another series of 45 eyes for which we calculated mean errors (defined as the difference between the spherical equivalent of the postoperative refraction and the predicted postoperative refraction) using the optimized and manufacturer’s suggested A constants. Results: There is a statistically significant relationship between AL (P < 0.001), K (P < 0.001) and the A constant. Ap increased as AL increased and as K decreased. In the validation data set, optimizing the A constant reduced mean errors from 0.50 D to 0.25 D and also reduced hyperopic refractive outcomes. Conclusions: The A constant for longer eyes with flatter corneas is larger than the A constant for shorter eyes with steeper corneas. Optimizing A constants using both AL and K improved the predictability of refractive outcomes without modification to the SRK/T formula.
文摘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.
文摘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.
