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.