Parents of Children with Cleft Lip Exhibit Heightened Visual Attention to the Perioral Area.

Following high-quality surgical repair, children born with a cleft lip anomaly may still display lasting visual differences. We exposed control adults and parents of affected children to images of children with cleft deformity and compared their visual tracking patterns. The protocol investigated whether parental exposure to secondary cleft deformity heightens or diminishes visual attraction to this type of structural facial variation. Method: Twenty participants (10 control adults, 10 parents of affected children) assessed 40 colored images of children's faces while their eye movements were tracked. Twenty-four control images and 16 repaired cleft lip images were displayed to observers. Nine bilateral facial aesthetic zones were considered as regions of interest. Percentage of time visually fixating within each region, and statistical differences in fixation duration percentage between the two participant groups and across the bilateral regions of interest were analyzed. Results: While both groups of observers directed more visual attention to the nasal and oral regions of the cleft images than control images, parents of children with cleft lip spent significantly more time fixating on these areas (25% and 24% of the time, respectively) than did unaffected adults (14.6% and 19.3%; P < 0.001). Conclusions: These results demonstrate that parents of cleft lip children exhibit heightened attention to this type of facial difference relative to the naive observer. These findings highlight that observer profile can meaningfully influence the perception of a facial deformity. Awareness of this information may enhance communication between surgeon and parents of an affected child by providing added insight into parental perspective.

An Artificial Intelligence-Based Diagnostic System for Acute Lymphoblastic Leukemia Detection.

This study suggests a novel Acute Lymphoblastic Leukemia (ALL) diagnostic model, built solely on complete blood count (CBC) records. Using a dataset comprised of CBC records of 86 ALL and 86 control patients respectively, we identified the most ALL-specific parameters using a feature selection approach. Next, Grid Search-based hyperparameter tuning with a five-fold cross-validation scheme was adopted to build classifiers using Random Forest, XGBoost, and Decision Tree algorithms. A comparison between the performances of the three models demonstrates that Decision Tree classifier outperformed XGBoost and Random Forest algorithms in ALL detection using CBC-based records.

Machine Learning for Diagnosis and Screening of Chronic Lymphocytic Leukemia Using Routine Complete Blood Count (CBC) Results.

The comprehensive epidemiology and global disease burdens reported recently suggest that chronic lymphocytic leukemia (CLL) constitutes 25-30% of leukemias thus being the most common leukemia subtype. However, there is an insufficient presence of artificial intelligence (AI)-based techniques for CLL diagnosis. The novelty of this study is in the investigation of data-driven techniques to leverage the intricate CLL-related immune dysfunctions reflected in routine complete blood count (CBC) alone. We used statistical inferences, four feature selection methods, and multistage hyperparameter tuning to build robust classifiers. With respective accuracies of 97.05%, 97.63%, and 98.62% for Quadratic Discriminant Analysis (QDA), Logistic Regression (LR), and XGboost (XGb)-based models, CBC-driven AI methods promise timely medical care and improved patient outcome with lesser resource usage and related cost.

Predicting long-term type 2 diabetes with support vector machine using oral glucose tolerance test.

Diabetes is a large healthcare burden worldwide. There is substantial evidence that lifestyle modifications and drug intervention can prevent diabetes, therefore, an early identification of high risk individuals is important to design targeted prevention strategies. In this paper, we present an automatic tool that uses machine learning techniques to predict the development of type 2 diabetes mellitus (T2DM). Data generated from an oral glucose tolerance test (OGTT) was used to develop a predictive model based on the support vector machine (SVM). We trained and validated the models using the OGTT and demographic data of 1,492 healthy individuals collected during the San Antonio Heart Study. This study collected plasma glucose and insulin concentrations before glucose intake and at three time-points thereafter (30, 60 and 120 min). Furthermore, personal information such as age, ethnicity and body-mass index was also a part of the data-set. Using 11 OGTT measurements, we have deduced 61 features, which are then assigned a rank and the top ten features are shortlisted using minimum redundancy maximum relevance feature selection algorithm. All possible combinations of the 10 best ranked features were used to generate SVM based prediction models. This research shows that an individual's plasma glucose levels, and the information derived therefrom have the strongest predictive performance for the future development of T2DM. Significantly, insulin and demographic features do not provide additional performance improvement for diabetes prediction. The results of this work identify the parsimonious clinical data needed to be collected for an efficient prediction of T2DM. Our approach shows an average accuracy of 96.80% and a sensitivity of 80.09% obtained on a holdout set.