High Discrimination Performance Research Articles

Predicting vision-threatening diabetic retinopathy in patients with type 2 diabetes mellitus: Systematic review, meta-analysis, and prospective validation study.

Delayed diagnosis and treatment of vision-threatening diabetic retinopathy (VTDR) is a common cause of visual impairment in individuals with type 2 diabetes mellitus (T2DM). Identification of VTDR predictors is the key to early prevention and intervention, but the predictors from previous studies are inconsistent. This study aims to conduct a systematic review and meta-analysis of the existing evidence for VTDR predictors, then to develop a risk prediction model after quantitatively summarising the predictors across studies, and finally to validate the model with two Chinese cohorts. We systematically retrieved cohort studies that reported predictors of VTDR in T2DM patients from PubMed, Ovid, Embase, Scopus, Cochrane Library, Web of Science, and ProQuest from their inception to December 2023. We extracted predictors reported in two or more studies and combined their corresponding relative risk (RRs) using meta-analysis to obtain pooled RRs. We only selected predictors with statistically significant pooled RRs to develop the prediction model. We also prospectively collected two Chinese cohorts of T2DM patients as the validation set and assessed the discrimination and calibration performance of the prediction model by the time-dependent ROC curve and calibration curve. Twenty-one cohort studies involving 622 490 patients with T2DM and 57 107 patients with VTDR were included in the meta-analysis. Age of diabetes onset, duration of diabetes, glycosylated haemoglobin (HbA1c), estimated glomerular filtration rate (eGFR), hypertension, high albuminuria and diabetic treatment were used to construct the prediction model. We validated the model externally in a prospective multicentre cohort of 555 patients with a median follow-up of 52 months (interquartile range = 39-77). The area under the curve (AUC) of the prediction model was all above 0.8 for 3- to 10-year follow-up periods and different cut-off value of each year provided the optimal balance between sensitivity and specificity. The data points of the calibration curves for each year closely surround the corresponding dashed line. The risk prediction model of VTDR has high discrimination and calibration performance based on validation cohorts. Given its demonstrated effectiveness, there is significant potential to expand the utilisation of this model within clinical settings to enhance the detection and management of individuals at high risk of VTDR.

Heart Failure Risk Prediction in a Population With a High Burden of Diabetes: Evidence From the Strong Heart Study.

Despite the high burden of diabetes and cardiovascular risk factors in American Indian communities in the United States, prospective studies of heart failure (HF) in this population group are scarce, and the generalizability of previous HF risk scales may be limited. We developed a parsimonious HF risk prediction equation that accounts for relevant risk factors affecting American Indian communities, focusing on diabetes and kidney damage. A total of 3059 participants from the SHS (Strong Heart Study) (56±8 years of age, 58% women) were included. Five hundred seven developed HF. Progressively adjusted Cox proportional hazards models were used to identify risk factors for HF and HF subtypes. Predictors of risk at 5 and 10 years included older age (hazard ratio [HR], 1.79 [95% CI, 1.43-2.25]; HR, 1.68 [95% CI, 1.44-1.95]), smoking (HR, 2.26 [95% CI, 1.23-4.13]; HR, 2.08 [95% CI, 1.41-3.06]), macroalbuminuria (HR, 8.38 [95% CI, 4.44-15.83]; HR, 5.20 [95% CI, 3.42-7.9]), microalbuminuria (HR, 2.72 [95% CI, 1.51-4.90]; HR, 1.92 [95% CI, 1.33, 2.78]), and previous myocardial infarction (HR, 6.58 [95% CI, 2.54-17.03]; HR, 3.87 [95% CI, 2.29-6.54]), respectively. These predictors, together with diabetes diagnosis and glycated hemoglobin were significant at 10 and 28 years. High discrimination performance was achieved (C index, 0.81 [95% CI, 0.76-0.84]; C index, 0.78 [95% CI, 0.75-0.81]; and C index, 0.77 [95% CI, 0.74-0.78] at 5, 10, and up to 28 years of follow up, respectively). Some associations varied across HF subtypes, although diabetes, albuminuria, and previous myocardial infarction were associated with all subtypes. This prospective study of HF risk factors in American Indian communities identifies that smoking, body mass index, and indicators of diabetes control and kidney damage (glycated hemoglobin and albuminuria) are major determinants of HF. Our findings can improve HF risk assessment in populations with a high burden of diabetes.

Machine learning-based delirium prediction in surgical in-patients: a prospective validation study.

Delirium is a syndrome that leads to severe complications in hospitalized patients, but is considered preventable in many cases. One of the biggest challenges is to identify patients at risk in a hectic clinical routine, as most screening tools cause additional workload. The aim of this study was to validate a machine learning (ML)-based delirium prediction tool on surgical in-patients undergoing a systematic assessment of delirium. 738 in-patients of a vascular surgery, a trauma surgery and an orthopedic surgery department were screened for delirium using the DOS scale twice a day over their hospital stay. Concurrently, delirium risk was predicted by the ML algorithm in real-time for all patients at admission and evening of admission. The prediction was performed automatically based on existing EHR data and without any additional documentation needed. 103 patients (14.0%) were screened positive for delirium using the DOS scale. Out of them, 85 (82.5%) were correctly identified by the ML algorithm. Specificity was slightly lower, detecting 463 (72.9%) out of 635 patients without delirium. The AUROC of the algorithm was 0.883 (95% CI, 0.8523-0.9147). In this prospective validation study, the implemented machine-learning algorithm was able to detect patients with delirium in surgical departments with high discriminative performance. In future, this tool or similar decision support systems may help to replace time-intensive screening tools and enable efficient prevention of delirium.

Development and validation of an automated machine learning model for the multi-class classification of diabetic retinopathy, central retinal vein occlusion and branch retinal vein occlusion based on color fundus photographs

IntroductionAutomated machine learning (AutoML) is a novel artificial intelligence (AI) strategy that enables clinicians without coding experience to develop their own AI models. This study assessed the discriminative performance of AutoML in differentiating diabetic retinopathy (DR), central retinal vein occlusion (CRVO) and branch retinal vein occlusion (BRVO) from normal fundi using color fundus photographs (CFPs). MethodsWe carried out AutoML model design using CFPs retrieved from a publicly available CFP data set (3200 labelled images). The retrieved CFPs were reviewed for quality and then uploaded to the Google Cloud Vertex AI platform for AutoML training and testing. We trained a multi-class classification model to differentiate DR, CRVO, BRVO from normal fundi using 875 CFPs and externally validated the model using 210 CFPs obtained from another dataset. Performance metrics, including area under receiver operator curve (AUROC) and sensitivity were reported. We then compared the AutoML model to state-of-the-art deep learning (DL)-based DR and RVO multi-class models identified through a literature search. ResultsOur AutoML model showed high discriminative performance in the multi-class classification of DR, CRVO and BRVO based on CFPs, with an AUROC, precision and recall reaching 0.995, 95.4% and 95.4% respectively at the 0.5 confidence threshold. The per-label sensitivity and specificity, respectively, were normal fundi (97.5%, 100%), DR (100%, 93.88%), CRVO (66.67%, 100%) and BRVO (71.43%, 98.73%). Our AutoML model generally showed similar performance to the state-of-the-art DL classifiers. ConclusionOur AutoML model can detect DR, CRVO, and BRVO in CFPs with good diagnostic accuracy and is a potentially useful screening tool.

Associations between serum ferritin baselines and trajectories and the incidence of metabolic dysfunction-associated steatotic liver disease: a prospective cohort study.

Evidence from prospective cohort studies on the relationship between metabolic dysfunction-associated steatotic liver disease (MASLD) and longitudinal changes in serum ferritin (SF) still limited. This study aimed to investigate the associations of SF baselines and trajectories with new-onset MASLD and to present a MASLD discriminant model. A total of 1895 participants who attended health examinations at least three times in a hospital in Dalian City between 2015 and 2022 were included. The main outcome was the incidence of MASLD. The associations between SF baselines and trajectories with the risk of MASLD were analyzed by Cox proportional hazards regression, restricted cubic spline (RCS) analysis and time-dependent receiver operating characteristic (ROC) curve analysis. In addition, a MASLD discrimination model was established using logistic regression analyses. Among the 1895 participants, 492 developed MASLD during follow-up. Kaplan-Meier analysis indicated that participants in the low-stable trajectory group had a longer MASLD-free time compared with participants in other groups. Compared with those in the low-stable trajectory group, the adjusted hazard ratios (HRs) with 95% confidence intervals (CIs) for the risk of new-onset MASLD in the medium-high, high-stable and high-high trajectory groups were 1.54(1.18-2.00), 1.77(1.35-2.32) and 1.55(1.07-2.26), respectively (Ptrend < 0.001). The results were robust in subgroup and sensitivity analyses. Multivariate Cox proportional regression showed that SF was an independent risk factor of MASLD (HR = 1.002, 95%CI: 1.000-1.003, P = 0.003). The restricted cubic spline demonstrated a nonlinear relationship between SF and the risk of MASLD. The 8-variable model had high discriminative performance, good accuracy and clinical effectiveness. The ROC curve results showed that AUC was greater than that of the FLI, HSI and ZJU models (all P < 0.01). Not only a higher baseline SF but also SF changing trajectory are significantly associated with risk of new-onset MASLD. SF could be a predictor of the occurrence of MASLD.

A novel discriminant algorithm for differential diagnosis of mild to moderate thalassemia and iron deficiency anemia.

Mild to moderate thalassemia trait (TT) and iron deficiency anemia (IDA) are the most common conditions of microcytic hypochromic anemia (MHA) and they exhibit highly similar clinical and laboratory features. It is sometimes difficult to make a differential diagnosis between TT and IDA in clinical practice. Therefore, a simple, effective, and reliable index is needed to discriminate between TT and IDA. Data of 598 patients (320 for TT and 278 for IDA) were enrolled and randomly assigned to training set (278 of 598, 70%) and validation set (320 of 598, 30%). Stepwise discriminant analysis was used to define the best diagnostic formula for the discrimination between TT and IDA in training set. The accuracy and diagnostic performance of formula was tested and verified by receiver operating characteristic (ROC) analysis in validation set and its diagnostic performance was compared with other published indices. A novel formula, Thalassemia and IDA Discrimination Index (TIDI) = -13.932 + 0.434 × RBC + 0.033 × Hb + 0.025 ×MCHC + 53.593 × RET%, was developed to discriminate TT from IDA. TIDI showed a high discrimination performance in ROC analysis, with the Area Under the Curve (AUC) = 0.936, Youden' s index = 78.7%, sensitivity = 89.5%, specificity = 89.2%, respectively. Furthermore, the formula index also obtained a good classification performance in distinguishing 5 common genotypes of TT from IDA (AUC from 0.854-0.987). The new, simple algorithm can be used as an effective and robust tool for the differential diagnosis of mild to moderate TT and IDA in Guangxi region, China.

Incidence and risk prediction of post-Covid-19 cardiovascular disease in the general population: a multivariable prediction model development and validation study

Abstract Background Previous studies showed that relative risks of various cardiovascular events are increased after Covid-19, even in non-hospitalized individuals. The global burden of post-Covid-19 cardiovascular disease is large and not (yet) hospitalized Covid-19 infected adults may represent a potential target for prevention strategies to mitigate this burden. However, good estimates of individual absolute risks in the general population and risk stratification models are lacking, yet pivotal to assess its impact and direct health care policy. Purpose This study aimed to assess the absolute risk of post-Covid-19 cardiovascular events in the general population, and subsequently explore individual risk prediction in this domain. Methods Covid-19 diagnosed adults were identified from the United Kingdom’s Clinical Practice Research Datalink Aurum, a primary care electronic healthcare database. We assessed 180-day incidence rates of atherosclerotic events (acute coronary syndrome, stroke and transient ischaemic accident), venous thrombo-embolic events (pulmonary embolism and deep venous thrombosis), and newly diagnosed atrial fibrillation and heart failure. Multivariable logistic regression models using elastic net penalization were developed on a cohort of 220,751 adults with Covid-19 before 1 December 2020 (before the start of national vaccination campaigns). Candidate predictors included age, sex, body mass index, smoking, medical history and medication. Three models were fit for each endpoint, with increasing numbers of predictors. All models were validated in (1) 138,034 vaccinated and (2) 503,404 non-vaccinated adults with a first Covid-19 diagnosis after 1 December 2020. We evaluated discriminative and calibration performance upon internal cross-validation and in both validation cohorts. Results Post-Covid-19 cardiovascular event incidences ranged from 13 (venous thromboembolic events) down to 4 (heart failure de novo) per 1000 person-years. Incidences were relatively increased up to 50 days after Covid-19 infection. However, on an absolute scale, individual risks were very low: only less than one in twenty adults with Covid-19 had a predicted 180-day risk larger than 1% and these mainly included individuals aged 60 years or older. Even though the best models had high discriminative performance (AUC &amp;gt; 0.90), rare outcomes complicated predictive performance and calibration. Conclusions Risks of atherosclerotic events, venous thromboembolic events, and newly diagnosed atrial fibrillation and heart failure are increased after Covid-19 infection in the general population, notably within the first 50 days after infection and in individuals aged 60 years or older. However, individual risks are too low to be predictive or helpful to guide individual risk management. Risk mitigation strategies should therefore be aimed at population-based prevention (such as increasing vaccination uptake) and at individual management of Covid-19 hospitalized patients.Graphical abstractPredicted 180-day risk after Covid-19

Establishment and Validation of a Machine Learning-Based Prediction Model for Termination of Pregnancy via Cesarean Section.

This study aimed to investigate the risk factors of cesarean section and establish a prediction model for cesarean section based on the characteristics of pregnant women. The clinical characteristics of 2552 singleton pregnant women who delivered a live baby between January 2020 and December 2021 were retrospectively reviewed. They were divided into vaginal delivery group (n = 1850) and cesarean section group (n = 702). These subjects were divided into training set (2020.1-2021.6) and validation set (2021.7-2021.12). In the training set, univariate analysis, Lasso regression, and Boruta were used to screen independent risk factors for cesarean section. Four models, including Logistic Regression (LR), K-Nearest Neighbor (KNN), Classification and Regression Tree (CART), and Random forest (RF), were established in the training set using K-fold cross validation, hyperparameter optimization, and random oversampling techniques. The best model was screened, and Sort graph of feature variables, univariate partial dependency profile, and Break Down profile were delineated. In the validation set, the confusion matrix parameters were calculated, and receiver operating characteristic curve (ROC), precision recall curve (PRC), calibration curve, and clinical decision curve analysis (DCA) were delineated. The risk factors of cesarean section included age and height of women, weight at delivery, weight gain, para, assisted reproduction, abnormal blood glucose during pregnancy, pregnancy hypertension, scarred uterus, premature rupture of membrane (PROM), placenta previa, fetal malposition, thrombocytopenia, floating fetal head, and labor analgesia. RF had the best performance among the four models, and the accuracy of confusion matrix parameters was 0.8956357. The Matthews correlation coefficient (MCC) was 0.753012. The area under ROC (AUC-ROC) was 0.9790787, and the area under PRC (AUC-PRC) was 0.957888. RF prediction model for caesarean section has high discrimination performance, accuracy and consistency, and outstanding generalization ability.

Multiplex Quantification of Exosomes via Multiple Types of Nanobeads Labeling Combined with Laser Scanning Detection.

In recent years, exosomes have attracted attention in many aspects from basic research to clinical application, including therapeutic reagents or biomarkers for liquid biopsy. The increasing understanding of exosome's heterogeneous properties is expected to lead to more advanced exosome research, and there is therefore a need for a multiplex system that can easily classify and analyze exosomes in complex biological samples according to their properties. In this study, we developed a simple and sensitive multiplexed exosome quantification system based on ExoCounter, an exosome quantification system utilizing optical disk technology, by introducing nanobeads made of different materials as exosome labeling substances. The refractive indices suitable for nanobead materials were analyzed by computer simulation of optical diffraction generated by nanobeads. The results showed that polymer (FG), Au, and Ag nanobeads exhibited superior discrimination capability in terms of the amplitude and polarity of detection pulses generated by each nanobead. The specificity and detection sensitivity of three types of nanobeads were confirmed by detecting HER2-positive exosomes with anti-HER2 antibody-conjugated nanobeads. Furthermore, CD147-positive, HER2-positive, and CD81-positive exosomes in 12.5 μL of serum were simultaneously quantified with high discrimination performance using the anti-CD147 antibody, anti-HER2 antibody, or anti-CD81 antibody conjugated for FG beads, Au nanobeads, or Ag nanobeads, respectively. A limit of detection was also evaluated as low as 210 exosomes/μL. This system is a promising tool for advanced exosome research because it enables multiplexed detection of heterogeneous exosomes in serum with high specificity, accuracy, and sensitivity without purification.

Prediction of Maxillary Bone Invasion in Hard Palate/Upper Alveolus Cancer: A Multi-Center Retrospective Study.

maxillary bone invasion (MBI) is not uncommon in hard palate or upper alveolus (HP/UA) cancer; however, there have been relatively few reports about the MBI of HP/UA cancer. this was a multi-center retrospective study, enrolling 144 cases of HP/UA cancer. MBI was defined by surgical pathology or radiology follow-up. The multiple prediction models for MBI were developed in total cases and in cases having primary bone resection, using clinical and radiological variables. computerized tomography (CT) alone predicted MBI, with an area under receiver operating curve (AUC) of 0.779 (95% confidence interval (CI) = 0.712-0.847). The AUC was increased in a model that combined tumor dimensions and clinical factors (male sex and nodal metastasis) (0.854 (95%CI = 0.790-0.918)). In patients who underwent 18fluorodeoxyglucose positron emission tomography/CT (PET/CT), the discrimination performance of a model including the maximal standardized uptake value (SUVmax) had an AUC of 0.911 (95%CI = 0.847-0.975). The scoring system using CT finding, tumor dimension, and clinical factors, with/without PET/CT SUVmax clearly distinguished low-, intermediate-, and high-risk groups for MBI. using information from CT, tumor dimension, clinical factors, and the SUVmax value, the MBI of HP/UA cancer can be predicted with a relatively high discrimination performance.

Demonstration of Convolutional Neural Networks to Determine Patch Test Reactivity.

Background: Convolutional neural networks (CNNs) have the potential to assist allergists and dermatologists in the analysis of patch tests. Such models can help reduce interprovider variability and improve consistency of patch test interpretations. Objective: Our aim is to evaluate the performance of a CNN model as a proof of concept in discriminating between patch tests with reactions and patch tests without reactions. Methods: We performed a retrospective analysis of patch test images from March 2020 to March 2021. The CNN model was trained as a binary classifier to discriminate between reaction and nonreaction patches. Performance of the model was determined using summary statistics and receiver operator characteristics (ROC) curves. Results: In total, 13,622 images from 125 patients were recorded for analysis. The majority of patients in the cohort were female (81.6%) with Fitzpatrick skin types I-II (88.0%). The area under curve was 0.940, indicating a high discriminative performance of the model for this data set. This resulted in a total accuracy of 90.1%, sensitivity of 86.0%, and specificity of 90.2%. Conclusions: CNNs have the capacity to determine the presence of delayed-type reactions in patch tests. Future prospective studies are required to assess the generalizability of such models.

Differences in non-linearities determine retinal cell types.

Classifying neurons in different types is still an open challenge. In the retina, recent works have taken advantage of the ability to record a large number of cells to classify ganglion cells into different types based on functional information. While the first attempts in this direction used the receptive field properties of each cell to classify them, more recent approaches have proposed to cluster ganglion cells directly based on their response to standard stimuli. These two approaches have not been compared directly. Here we recorded the responses of a large number of ganglion cells and compared two methods for classifying them into types, one based on the receptive field properties, and the other one using their responses to standard stimuli. We show that the stimulus-based approach allows separating more types than the receptive field-based method, leading to a better classification. This better granularity is due to the fact that the stimulus-based method takes into account not only the linear part of ganglion cell function, but also non-linearities. A careful characterization of non-linear processing is thus key to allow functional classification of sensory neurons.

A flexible symbolic regression method for constructing interpretable clinical prediction models

Machine learning (ML) models trained for triggering clinical decision support (CDS) are typically either accurate or interpretable but not both. Scaling CDS to the panoply of clinical use cases while mitigating risks to patients will require many ML models be intuitively interpretable for clinicians. To this end, we adapted a symbolic regression method, coined the feature engineering automation tool (FEAT), to train concise and accurate models from high-dimensional electronic health record (EHR) data. We first present an in-depth application of FEAT to classify hypertension, hypertension with unexplained hypokalemia, and apparent treatment-resistant hypertension (aTRH) using EHR data for 1200 subjects receiving longitudinal care in a large healthcare system. FEAT models trained to predict phenotypes adjudicated by chart review had equivalent or higher discriminative performance (p < 0.001) and were at least three times smaller (p < 1 × 10−6) than other potentially interpretable models. For aTRH, FEAT generated a six-feature, highly discriminative (positive predictive value = 0.70, sensitivity = 0.62), and clinically intuitive model. To assess the generalizability of the approach, we tested FEAT on 25 benchmark clinical phenotyping tasks using the MIMIC-III critical care database. Under comparable dimensionality constraints, FEAT’s models exhibited higher area under the receiver-operating curve scores than penalized linear models across tasks (p < 6 × 10−6). In summary, FEAT can train EHR prediction models that are both intuitively interpretable and accurate, which should facilitate safe and effective scaling of ML-triggered CDS to the panoply of potential clinical use cases and healthcare practices.

Development of Machine-Learning Models for Tinnitus-Related Distress Classification Using Wavelet-Transformed Auditory Evoked Potential Signals and Clinical Data.

Tinnitus is a highly prevalent condition, affecting more than 1 in 7 adults in the EU and causing negative effects on sufferers' quality of life. In this study, we utilised data collected within the "UNITI" project, the largest EU tinnitus-related research programme. Initially, we extracted characteristics from both auditory brainstem response (ABR) and auditory middle latency response (AMLR) signals, which were derived from tinnitus patients. We then combined these features with the patients' clinical data, and integrated them to build machine learning models for the classification of individuals and their ears according to their level of tinnitus-related distress. Several models were developed and tested on different datasets to determine the most relevant features and achieve high performances. Specifically, seven widely used classifiers were utilised on all generated datasets: random forest (RF), linear, radial, and polynomial support vector machines (SVM), naive bayes (NB), neural networks (NN), and linear discriminant analysis (LDA). Results showed that features extracted from the wavelet-scattering transformed AMLR signals were the most informative data. In combination with the 15 LASSO-selected clinical features, the SVM classifier achieved optimal performance with an AUC value, sensitivity, and specificity of 92.53%, 84.84%, and 83.04%, respectively, indicating high discrimination performance between the two groups.

Ecological Niche Models using MaxEnt in Google Earth Engine: Evaluation, guidelines and recommendations

Google Earth Engine (GEE) has revolutionized geospatial analyses by fast-processing formerly demanding analyses from multiple research areas. Recently, maximum entropy (MaxEnt), the most commonly used method in ecological niche models (ENMs), was integrated into GEE. This integration can significantly enhance modeling efficiency and encourage multidisciplinary approaches of ENMs, but an evaluation assessment of MaxEnt in GEE is lacking. Herein, we present the first MaxEnt models in GEE, as well as its first statistical and spatial evaluation. We also identify the limitations of the approach, providing guidelines and recommendations for its easier applicability in GEE.We tested MaxEnt in GEE using 11 case studies. For each case, we used species of different taxa (insects, amphibians, reptiles, birds and mammals) distributed across global and regional extents. Each species occupied habitats with distinct environmental characteristics (nine terrestrial and two marine species) and within divergent ecoregions across five continents. The models were performed in GEE and Maxent software, and both approaches were contrasted for their model discrimination performance (assessed by eight evaluation metrics) and spatial consistency (correlation analyses and two measures of niche overlap/equivalency).MaxEnt in GEE allows setting several parameters, but important analyses and outputs are unavailable, such as automatic selection of background data, model replicates, and analyses of variable importance (concretely, jackknife analyses and response curves). GEE provided MaxEnt models with high discrimination performance (area under the curve mean between all species models of 0.90) and with spatial equivalency in relation to Maxent software outputs (Hellinger's I mean between all species models >0.90).Our work demonstrates the first application and assessment of MaxEnt in GEE at global and regional scales. We conclude that the GEE modeling method provides ENMs with high performance and reliable spatial predictions, comparable to the widely used Maxent software. We also acknowledge important limitations that should be integrated into GEE in the future, particularly those related to the assessment of variable importance. We expect that our guidelines, recommendations and potential solutions to surpass the identified limitations could help researchers easily apply MaxEnt in GEE across different research fields.

Discrimination in the clinical diagnosis between patients with schizophrenia and healthy controls using eye movement and cognitive functions.

Eye movements and cognitive functions are significantly impaired in patients with schizophrenia. The authors aimed to develop promising clinical diagnostic markers that fit practical digital health applications in psychiatry using eye movement and cognitive function data from 1254 healthy individuals and 336 patients with schizophrenia. Multivariate analyses using logistic regression were performed to confirm net performance of eye movements and cognitive functions scored using the Wechsler Adult Intelligence Scale, Third Edition, and Wechsler Memory Scale-Revised. The authors then examined the discrimination performance of pairs containing an eye movement and a cognitive function measure to search the pairs that would be effective in practical application for the discrimination according to the diagnostic criterion between the groups. Multivariate analyses confirmed that eye movements and cognitive functions were effective modalities for discriminating between patients with schizophrenia and healthy controls. The discriminant analyses of the pairs demonstrated that seven eye movement measures and seven scores from cognitive function tests showed high discrimination performance when paired with one measure from the other modality. Moreover, seven pairs of digit-symbol coding or symbol-search and eye movement measures had high and robust discrimination performance. Seven pairs of an eye movement and a cognitive function measure were effective, robust, and less time-consuming in assisting with clinical diagnosis by categorizing healthy individuals or patients with schizophrenia. These findings may help develop an objective auxiliary diagnosis method working even on portable devices, which facilitates the consistency of diagnosis, earlier intervention, and shared decision-making.

A Charge-Transfer-Induced Strategy for Enantioselective Discrimination by Potential-Regulated Surface-Enhanced Raman Scattering Spectroscopy.

A simple and efficient enantioselective discrimination method, especially the chirality-label-free discrimination method, for the recognition of chiral small molecules with high resolution and wide applicability has been urgently desired. Herein, achiral Au/p-aminothiophenol (PATP) substrates were prepared to link the enantiomers via coupling reactions for constructing the enantioselective discrimination system. The resultant Au/PATP/enantiomer systems displayed charge-transfer (CT)-induced surface-enhanced Raman scattering (SERS) spectra that offered distinguishable information for the systems with different chirality. The differentiated spectral signal can be amplified by regulating the applied electrode potential, leading to great enantioselective discrimination performance. Moreover, the relationship between the discrimination performance and the potential-regulated CT process was revealed by SERS, which enabled an accurate and effective enantiomeric determination for various chiral molecules, including aromatic and aliphatic small molecules. The aliphatic molecule with the shorter chain was discriminated with a higher resolution, since the longer-chain molecule in the discrimination system may cause a change in the molecular electronic structure of the PATP. In addition, the aromatic chiral molecule can be distinguished easier than the aliphatic molecules, which means that the generation of the conjugation of electrons in the aromatic molecule-involved enantiomeric systems facilitates CT-induced SERS discrimination. Our work provides guidance for the design and development of an effective enantioselective discrimination strategy with high discrimination performance in diverse application fields.

An efficient landmark model for prediction of suicide attempts in multiple clinical settings

Growing evidence has shown that applying machine learning models to large clinical data sources may exceed clinician performance in suicide risk stratification. However, many existing prediction models either suffer from “temporal bias” (a bias that stems from using case-control sampling) or require training on all available patient visit data. Here, we adopt a “landmark model” framework that aligns with clinical practice for prediction of suicide-related behaviors (SRBs) using a large electronic health record database. Using the landmark approach, we developed models for SRB prediction (regularized Cox regression and random survival forest) that establish a time-point (e.g., clinical visit) from which predictions are made over user-specified prediction windows using historical information up to that point. We applied this approach to cohorts from three clinical settings: general outpatient, psychiatric emergency department, and psychiatric inpatients, for varying prediction windows and lengths of historical data. Models achieved high discriminative performance (area under the Receiver Operating Characteristic curve 0.74–0.93 for the Cox model) across different prediction windows and settings, even with relatively short periods of historical data. In short, we developed accurate, dynamic SRB risk prediction models with the landmark approach that reduce bias and enhance the reliability and portability of suicide risk prediction models.

Sensory test A-Not A rating signal detection: Panel’s sensory learning and stability of decision criteria

Signal detection theory (SDT) sensory discrimination analysis using A-Not A with a two-step rating is an efficient approach to in-house sensory quality management in the food industry. For such sensory analysis using an internal panel, the panels’ ability to use stable decision criteria and provide a consistent response distribution responding to “A” vs “Not A” is critical for guaranteeing the data quality. This study examined the effects of the familiarization procedure (FP) and reference presentation probability (RPP) in the SDT A-Not A rating protocol on the panels’ sensory learning of samples and stability of decision criteria using SDT parameters, recognition d' (d'Rec),criteria location (c), and discrimination d' indices. Three different protocols were compared using ice-tea samples with small differences: Control, 0.25 RPP with repeated reference tasting (FPR); Modified-1, 0.25 RPP with reference categorization (FPC); Modified-2, 0.5 RPP with reference categorization (FPC). An independent sample design with three groups having equal sensitivity was used to identify the differences among the protocols. For each protocol, two sub-groups with similar decision criteria (response bias) were formed according to the results obtained from the pre-test and used for the main-test analysis. SDT analysis results indicated that the Modified-2 protocol with a higher RPP (0.5) induced the most efficient sensory learning of the reference. The protocol improved the subjects’ recognition of the reference and test samples, better differentiating from the reference and stabilizing the decision criterion, resulting in higher discrimination performance (larger d'). The results showed that d'Rec analysis, together with d' analysis using a sensory panel, is a useful tool for monitoring the panel performance and checking for the sensory data quality of the sensory difference tests. In the present paper, a detailed illustration of the A-Not A sensory test procedure and examples of how to apply the SDT indices for different business decision-making is also introduced using the design and results of the present experiment.

Effective haptic feedback type for robot-mediated material discrimination depending on target properties

Haptic feedback enables material perception via remote robotics. Both force and vibration information are essential for haptic feedback, and it is important to understand their applicability in different situations. In this study, the relationship between the effective type of haptic feedback and target properties in robot-mediated material discrimination was investigated. A remote-control system including a force presentation device and a wearable vibrotactile display was constructed. In the first experiment, the discrimination performance of material hardness was compared between two types of feedback, force and hybrid (vibrotactile and force) conditions. The results show that both feedback systems allow statistically-significant discrimination of the stimuli, and a significant difference in correct-answer rates between the two feedback conditions was not observed. This indicates that the force system was effective for hardness discrimination, and that there was no superimposed effect of the hybrid system. In the second experiment, the discrimination performance of material roughness was compared between three types of feedback (force, vibrotactile, and hybrid). The results indicate that the rate of correct responses for hybrid feedback condition are significantly higher than those for the force condition. This suggests that hybrid feedback is effective for roughness discrimination. Therefore, the effective type of feedback depends on the properties of target materials, and the superimposed effect of hybrid feedback was only observed in roughness discrimination. These findings play an important role in selecting the best feedback method for a given situation or constructing multiple feedback methods that achieve high discrimination performance.