No abstract

No abstract

Selecting the optimal lens size by predicting the postoperative vault can reduce complications after implantation of an implantable collamer lens with a centralhole (ICL with KS-aquaport). We built a web-based machine learning application that incorporated clinical measurements to predict the postoperative ICL vault and select the optimal ICL size. Methods:We applied the stacking ensemble technique based on eXtreme Gradient Boosting (XGBoost) and a light gradient boosting machine to pre-operative ocular data from two eye centers to predict the postoperative vault. We assigned the Korean patient data to a training (N = 2756 eyes) and internal validation (N = 693 eyes) datasets (prospective validation). Japanese patient data (N = 290 eyes) were used as an independent external dataset from different centers to validate the model. Results:We developed an ensemble model that showed statistically better performance with a lower mean absolute error for ICL vault prediction (106.88 μm and 143.69 μm in the internal and external validation, respectively) than the other machine learning techniques and the classic ICL sizing methods did when applied to both validation datasets. Considering the lens size selection accuracy, our proposed method showed the best performance for both reference datasets (75.9% and 67.4% in the internal and external validation, respectively). Conclusions:Applying the ensemble approach to a large dataset of patients who underwent ICL implantation resulted in a more accurate prediction of vault size and selection of the optimal ICL size.Translational Relevance: We developed a web-based application for ICL sizing to facilitate the use of machine learning calculators for clinicians.

ObjectiveTo investigate the factors affecting rehabilitation outcomes in children with congenital muscular torticollis (CMT).MethodsWe retrospectively reviewed the medical records of 347 patients who were clinically suspected as having CMT and performed neck ultrasonography to measure sternocleidomastoid (SCM) muscle thickness. Fifty-four patients met the inclusion criteria. Included were demographic characteristics as well as measurements of cervical range of motion (ROM), SCM muscle thickness, and the abnormal/normal (A/N) ratio, defined as the ratio of SCM muscle thickness on the affected to the unaffected side.ResultsSubjects were divided into three groups depending on degree of cervical ROM (group 1A: ROM>60, n=12; group 1B: 60≥ROM>30, n=31; group 1C: ROM≤30, n=11), the SCM muscle thickness (Th) (group 2A: Th<1.2 cm, n=23; group 2B: 1.2≤Th<1.4 cm, n=18; group 2C: Th≥1.4 cm, n=13), and the A/N ratio (R) (group 3A: R<2.2, n=19; group 3B: 2.2≤R<2.8, n=20; group 3C: R≥2.8, n=15). We found that more limited cervical ROM corresponded to longer treatment duration. The average treatment duration was 4.55 months in group 1A, 5.87 months in group 1B, and 6.50 months in group 1C. SCM muscle thickness and the A/N ratio were not correlated with treatment duration.ConclusionInfants with CMT who were diagnosed earlier and had an earlier intervention had a shorter duration of rehabilitation. Initial cervical ROM is an important prognostic factor for predicting the rehabilitation outcome of patients with CMT.

[Purpose] The purpose of this meta-analysis was to assess the effects of extracorporeal shock wave therapy (ESWT) on reducing spasticity immediately and 4 weeks after application of ESWT. [Subjects and Methods] We searched PubMed, TCL, Embase, and Scopus from their inception dates through June 2013. The key words “muscle hypertonia OR spasticity” were used for spasticity, and the key words “shock wave OR ESWT” were used for ESWT. Five studies were ultimately included in the meta-analysis. [Results] The Modified Ashworth Scale (MAS) grade was significantly improved immediately after ESWT compared with the baseline values (standardized mean difference [SMD], −0.792; 95% confidence interval [CI], −1.001 to −0.583). The MAS grade at four weeks after ESWT was also significantly improved compared with the baseline values (SMD, −0.735; 95% CI, −0.951 to −0.519). [Conclusion] ESWT has a significant effect on improving spasticity. Further standardization of treatment protocols including treatment intervals and intensities needs to be established and long-term follow up studies are needed.

ObjectiveTo examine the usefulness of the Scale for the Assessment and Rating of Ataxia (SARA) in ataxic stroke patients.MethodThis was a retrospective study of 54 patients following their first ataxic stroke. The data used in the analysis comprised ambulation status on admission and scores on the SARA, the Korean version of the Modified Barthel Index (K-MBI) and the Berg Balance Scale (BBS). The subjects were divided into four groups by gait status and into five groups by level of dependency in activities of daily living (ADLs) based on their K-MBI scores. Data were subjected to a ROC curve analysis to obtain cutoff values on the SARA for individual gait status and levels of activity dependency. The correlations between the SARA, K-MBI and BBS scores were also computed.ResultsThere was significant correlation between the SARA and the K-MBI scores (p<0.001), and this correlation (r=-0.792) was higher than that found between the BBS and the K-MBI scores (r=0.710). The SARA scores of upper extremity ataxia categories were significantly related to the K-MBI scores of upper extremity related function (p<0.001). The SARA scores were also significantly correlated negatively with ambulation status (p<0.001) and positively with ADL dependency (p<0.001). In the ROC analysis, patients with less than 5.5 points on the SARA had minimal dependency in ADL, while those with more than 23 points showed total dependency.ConclusionSARA corresponds well with gait status and ADL dependency in ataxic stroke patients and is considered to be a useful functional measure in that patient group.

Recently, it has become more important to screen candidates that undergo corneal refractive surgery to prevent complications. Until now, there is still no definitive screening method to confront the possibility of a misdiagnosis. We evaluate the possibilities of machine learning as a clinical decision support to determine the suitability to corneal refractive surgery. A machine learning architecture was built with the aim of identifying candidates combining the large multi-instrument data from patients and clinical decisions of highly experienced experts. Five heterogeneous algorithms were used to predict candidates for surgery. Subsequently, an ensemble classifier was developed to improve the performance. Training (10,561 subjects) and internal validation (2640 subjects) were conducted using subjects who had visited between 2016 and 2017. External validation (5279 subjects) was performed using subjects who had visited in 2018. The best model, i.e., the ensemble classifier, had a high prediction performance with the area under the receiver operating characteristic curves of 0.983 (95% CI, 0.977–0.987) and 0.972 (95% CI, 0.967–0.976) when tested in the internal and external validation set, respectively. The machine learning models were statistically superior to classic methods including the percentage of tissue ablated and the Randleman ectatic score. Our model was able to correctly reclassify a patient with postoperative ectasia as an ectasia-risk group. Machine learning algorithms using a wide range of preoperative information achieved a comparable performance to screen candidates for corneal refractive surgery. An automated machine learning analysis of preoperative data can provide a safe and reliable clinical decision for refractive surgery.

Both LASIK and LASEK were safe and effectively treated eyes with high myopia. Laser in situ keratomileusis provided superior results in visual predictability and corneal opacity.