Stacking and ridge regression-based spectral ensemble preprocessing method and its application in near-infrared spectral analysis.

Spectral preprocessing techniques can, to a certain extent, eliminate irrelevant information, such as current noise and stray light from spectral data, thereby enhancing the performance of prediction models. However, current preprocessing techniques mostly attempt to find the best single preprocessing method or their combination, overlooking the complementary information among different preprocessing methods. These preprocessing techniques fail to maximize the utilization of useful information in spectral data and restrict the performance of prediction models. This study proposed a spectral ensemble preprocessing method based on the rapidly developing ensemble learning methods in recent years and the ridge regression (RR) model, named stacking preprocessing ridge regression (SPRR), to address the aforementioned issues. Different from conventional ensemble learning methods, the proposed SPRR method applied multiple different preprocessing techniques to the original spectral data, generating multiple preprocessed datasets. These datasets were then individually inputted into RR base models for training. Ultimately, RR still served as the meta-model, integrating the output results of each RR base model through stacking. This approach not only produced diversity in base models but also achieved higher accuracy and lower computational complexity by using a single type of base model. On the apple spectral dataset collected by our team, correlation analysis showed significant complementary information among the data produced by different preprocessing techniques. This provided robust theoretical support for the proposed SPRR method. By introducing the currently popular averaging ensemble preprocessing method in a comparative experiment, the results of applying the proposed SPRR method to six datasets (apple, meat, wheat, olive oil, tablet, and corn) demonstrated that compared to the single preprocessing method and averaging ensemble preprocessing method, SPRR yielded the best accuracy and reliability for all six datasets. Furthermore, under the same conditions of the training and test datasets, the proposed SPRR method demonstrated better performance than the four commonly used ensemble preprocessing methods.

Primary posterior capsulorhexis with anterior vitrectomy in preventing posterior capsule opacification in pediatric cataract microsurgery.

Our study was performed to investigate the operative effects of pediatric cataract surgery with anterior vitrectomy. The study comprised of 38 pediatric patients aged 2-5 years and involved a total of 60 eyes with congenital cataracts. The study was done between March 2004 and December 2005. Posterior capsulorhexis with anterior vitrectomy was performed on 34 eyes of 20 children, and cataract extraction was performed on 26 eyes of 18 children. The percentages of various complications and rate of neodymium YAG (Nd:YAG) laser capsulotomy were followed up for 12-36 months. There were significant differences in the percentages of posterior capsule opacification (PCO) and rate of neodymium YAG (Nd:YAG) capsulotomy between the anterior vitrectomy group and cataract extraction group (P < 0.01). The anterior vitrectomy group was associated with less posterior capsular opacification (11.8%) than the cataract extraction group (76.9%). The YAG capsulotomy rate was 2.9% for the anterior vitrectomy group, and 57.7% for the cataract extraction group. After operation the fibrous exudates in anterior chamber and the intraocular lens subluxation or capture were 5.9% and 2.9% for the anterior vitrectomy group while for the cataract extraction group they were 23.1% and 15.4%; the difference was statistically significant (P < 0.05). The results suggest that primary posterior capsulorhexis with anterior vitrectomy in pediatric cataract surgery who are between 2 and 5 years old is necessary and effective procedure with low PCO rate.

[Phacoemulsification and the negative power of intraocluar lenses in extremely myopic eyes].

OBJECTIVE: To evaluate the clinical effects of phacoemulsification and the negative power of intraocluar lens implantation in patients with extreme myopia and cataract. METHODS: 89 patients (126 eyes) received phacoemulsification and a negative power intraocluar lens implantation. Preoperative axial length, postoperative visual acuity and refractive error were recorded. Intraoperative and postoperative complications were observed. The follow-up time is from 6 to 25 months. RESULTS: The mean preoperative axial length is 32.45 mm. Best corrected visual acuity achieved 0.2 or better in 106 eyes (84.1%) and 0.5 or better in 69 eyes (54.8%). Of the 126 eyes, 56.3% were within 1.00 diopter (D) of refractive error and 90.5% were within an error of 2.00 D. Only 1 eye has posterior capsule rupture. 28 eyes had binocular disturbances. 15 eyes developed posterior capsule opacification and 6 eyes were performed neodymium: YAG laser posterior capsulotomy. No retinal or choroidal detachment or pressure improvement was seen during the follow-up. CONCLUSION: It is safe and effective for extreme myopia with cataract to implant a negative power intraocular lens after phacoemulsification.

[Observation on therapeutic effect of intraocular lens exchange surgery].

OBJECTIVE: To explore the causes, surgical principle and effect of lens exchange surgery. METHODS: The causes for 30 cases (30 eyes) of lens exchange were retrospectively analyzed, which included 11 cases with eccentric or dislocated intraocular lens (IOL, 36.7%), 8 cases with lens opacification (26.7%), 8 cases with incorrect power (26.7%) and 3 cases with iris capture (10.0%). There were 16 males and 14 females aged 32 to 80 years (average, 62). RESULTS: After extraction of the original implant, the second IOL was inserted in the lens bag in 11 cases (36.7%), in the ciliary sulcus in 13 cases (43.3%), in the anterior chamber in 1 case (3.3%) and with scleral fixation in 5 cases (16.7%). In the follow-up of 1 - 24 months, the best corrected visual acuity over 0.5 was achieved in 23 cases (76.7%), 0.3 - 0.4 in 5 cases (16.7%), under 0.2 in 2 cases (6.6%). The surgical complications included astigmatism in 4 cases, cystoid macular edema 1 case, hyphema 1 case and posterior capsular opacification 1 case. CONCLUSIONS: The eccentric or dislocated IOL, lens opacification and incorrect power are the major causes of lens exchange. Proper IOL selected and meticulous operative technique can avoid the abnormality of IOL, and the lens exchange is an effective way to manage the situation.