Search

BackgroundMachine learning (ML) algorithms have been widely introduced to diabetes research including those for the identification of hypoglycemia. ObjectiveThe objective of this meta-analysis is to assess the current ability of ML algorithms to detect hypoglycemia (ie, alert to hypoglycemia coinciding with its symptoms) or predict hypoglycemia (ie, alert to hypoglycemia before its symptoms have occurred). MethodsElectronic literature searches (from January 1, 1950, to September 14, 2020) were conducted using the Dialog platform that covers 96 databases of peer-reviewed literature. Included studies had to train the ML algorithm in order to build a model to detect or predict hypoglycemia and test its performance. The set of 2 × 2 data (ie, number of true positives, false positives, true negatives, and false negatives) was pooled with a hierarchical summary receiver operating characteristic model. ResultsA total of 33 studies (14 studies for detecting hypoglycemia and 19 studies for predicting hypoglycemia) were eligible. For detection of hypoglycemia, pooled estimates (95% CI) of sensitivity, specificity, positive likelihood ratio (PLR), and negative likelihood ratio (NLR) were 0.79 (0.75-0.83), 0.80 (0.64-0.91), 8.05 (4.79-13.51), and 0.18 (0.12-0.27), respectively. For prediction of hypoglycemia, pooled estimates (95% CI) were 0.80 (0.72-0.86) for sensitivity, 0.92 (0.87-0.96) for specificity, 10.42 (5.82-18.65) for PLR, and 0.22 (0.15-0.31) for NLR. ConclusionsCurrent ML algorithms have insufficient ability to detect ongoing hypoglycemia and considerate ability to predict impeding hypoglycemia in patients with diabetes mellitus using hypoglycemic drugs with regard to diagnostic tests in accordance with the Users’ Guide to Medical Literature (PLR should be ≥5 and NLR should be ≤0.2 for moderate reliability). However, it should be emphasized that the clinical applicability of these ML algorithms should be evaluated according to patients’ risk profiles such as for hypoglycemia and its associated complications (eg, arrhythmia, neuroglycopenia) as well as the average ability of the ML algorithms. Continued research is required to develop more accurate ML algorithms than those that currently exist and to enhance the feasibility of applying ML in clinical settings. Trial RegistrationPROSPERO International Prospective Register of Systematic Reviews CRD42020163682; http://www.crd.york.ac.uk/PROSPERO/display_record.php?ID=CRD42020163682

BackgroundApplications of machine learning for the early detection of diseases for which a clear-cut diagnostic gold standard exists have been evaluated. However, little is known about the usefulness of machine learning approaches in the decision-making process for decisions such as insulin initiation by diabetes specialists for which no absolute standards exist in clinical settings. ObjectiveThe objectives of this study were to examine the ability of machine learning models to predict insulin initiation by specialists and whether the machine learning approach could support decision making by general physicians for insulin initiation in patients with type 2 diabetes. MethodsData from patients prescribed hypoglycemic agents from December 2009 to March 2015 were extracted from diabetes specialists’ registries, resulting in a sample size of 4860 patients who had received initial monotherapy with either insulin (n=293) or noninsulin (n=4567). Neural network output was insulin initiation ranging from 0 to 1 with a cutoff of >0.5 for the dichotomous classification. Accuracy, recall, and area under the receiver operating characteristic curve (AUC) were calculated to compare the ability of machine learning models to make decisions regarding insulin initiation to the decision-making ability of logistic regression and general physicians. By comparing the decision-making ability of machine learning and logistic regression to that of general physicians, 7 cases were chosen based on patient information as the gold standard based on the agreement of 8 of the 9 specialists. ResultsThe AUCs, accuracy, and recall of logistic regression were higher than those of machine learning (AUCs of 0.89-0.90 for logistic regression versus 0.67-0.74 for machine learning). When the examination was limited to cases receiving insulin, discrimination by machine learning was similar to that of logistic regression analysis (recall of 0.05-0.68 for logistic regression versus 0.11-0.52 for machine learning). Accuracies of logistic regression, a machine learning model (downsampling ratio of 1:8), and general physicians were 0.80, 0.70, and 0.66, respectively, for 43 randomly selected cases. For the 7 gold standard cases, the accuracies of logistic regression and the machine learning model were 1.00 and 0.86, respectively, with a downsampling ratio of 1:8, which were higher than the accuracy of general physicians (ie, 0.43). ConclusionsAlthough we found no superior performance of machine learning over logistic regression, machine learning had higher accuracy in prediction of insulin initiation than general physicians, defined by diabetes specialists’ choice of the gold standard. Further study is needed before the use of machine learning–based decision support systems for insulin initiation can be incorporated into clinical practice.

Purpose: The purpose of the current study was to examine normative nasalance values in Vietnamese adult speakers with Southern dialect and to investigate the effects of vowels and tones on . Previous studies examining nasalance have been mainly conducted with Indo-European languages. Limited information on nasalance is available in tone languages other than Chinese. Furthermore, tone and vowel effects on nasalance scores in tone languages have not been fully examined. Method: Nasalance scores of various speech stimuli including passages, syllables, and prolonged vowels were obtained from Vietnamese-speaking adults with Southern dialect (M[subscript age] = 23 years) using a nasometer (KayPENTAX 6450). Results: The average nasalance scores of Southern Vietnamese adult speakers were 24.16%, 38.17%, and 70.03% for the oral, oral-nasal, and nasal passages, respectively. Southern Vietnamese speakers produced the highest nasalance scores on the vowel /a/, followed by /i/ and /u/. Nasalance scores of stimuli produced with the falling and restricted tone were significantly lower than those produced with the other tones. Conclusions: The normative nasalance values of the current study will contribute as a reference index for the Vietnamese language. The effects of vowels and tones can also provide insight into the development of nasalance testing stimuli and for characterizing nasalance values across languages.

We encountered two acute stroke cases with apraxia of speech (AOS) due to left internal border‐zone infarction. Neither case had a lower precentral gyrus lesion in the left frontal lobe. The findings obtained confirmed the relationship between AOS with improvement and damage to the left frontal aslant tract (FAT) in stroke. FAT integrity has potential as a prognostic imaging biomarker of AOS. It is important to visualize the fiber connections of white matter using diffusion tensor tractography, which will predict the outcome of AOS. [ABSTRACT FROM AUTHOR]

Background and objectives To clarify whether the presence or absence of fast walking and habitual physical activity are independently associated with the incidence of functional disability. Methods This historical cohort study was comprised of 9,652 (4,412 men, mean age 65 years) individuals aged 39–98 years without functional disability at baseline. Functional disability was determined based on the Japanese long-term care insurance system, which specified requirements for assistance in the activities of daily living. The impact of fast walking and habitual physical activity on the incidence of functional disability was analysed by Cox proportional hazards models. Results The follow-up period was a median of 3.7 years during which 165 patients were newly certified as having functional disability. In the multivariate analysis, baseline age in 5-year increments (hazard ratio 2.42 [95% confidence interval 2.18–2.69]), no habitual physical activity (1.56 [1.07–2.27]), and not fast walking (1.89 [1.32–2.69]) significantly increased the risk of functional disability after adjustment for covariates. The stratified analysis showed that compared with physical activity (+), the impact of physical activity (−) on the incidence of functional disability was observed in those aged ≥75 years regardless of fast walking (+). Fast walking (−) significantly increased the risk of disability compared with fast walking (+) in those aged <75 years regardless of a physical activity habit. Conclusion In Japanese, slow walking speed and lack of a physical activity habit were shown to be independent risk factors for incident functional disability, with their impact differing according to age. [ABSTRACT FROM AUTHOR]