Development and validation of a machine learning, smartphone-based tonometer.
Ontology highlight
ABSTRACT: Background/aims
To compare intraocular pressure (IOP) measurements using a prototype smartphone tonometer with other tonometers used in clinical practice.Methods
Patients from an academic glaucoma practice were recruited. The smartphone tonometer uses fixed force applanation and in conjunction with a machine-learning computer algorithm is able to calculate the IOP. IOP was also measured using Goldmann applanation tonometry (GAT) in all subjects. A subset of patients were also measured using ICare, pneumotonometry (upright and supine positions) and Tono-Pen (upright and supine positions) and the results were compared.Results
92 eyes of 81 subjects were successfully measured. The mean difference (in mm Hg) for IOP measurements of the smartphone tonometer versus other devices was +0.24 mm Hg for GAT, -1.39 mm Hg for ICare, -3.71 mm Hg for pneumotonometry and -1.30 mm Hg for Tono-Pen. The 95% limits of agreement for the smartphone tonometer versus other devices was -4.35 to 4.83 mm Hg for GAT, -6.48 to 3.70 mm Hg for ICare, -7.66 to -0.15 mm Hg for pneumotonometry and -5.72 to 3.12 mm Hg for Tono-Pen. Overall, the smartphone tonometer results correlated best with GAT (R2=0.67, p<0.001). Of the 92 videos, 90 (97.8%) were within ±5 mm Hg of GAT and 58 (63.0%) were within ±2 mm Hg of GAT.Conclusions
Preliminary IOP measurements using a prototype smartphone-based tonometer was grossly equivalent to the reference standard.
SUBMITTER: Wu Y
PROVIDER: S-EPMC7397723 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundEchocardiography (echo) based machine learning (ML) models may be useful in identifying patients at high-risk of all-cause mortality.MethodsWe developed ML models (ResNet deep learning using echo videos and CatBoost gradient boosting using echo measurements) to predict 1-year, 3-year, and 5-year mortality. Models were trained on the Mackay dataset, Taiwan (6083 echos, 3626 patients) and validated in the Alberta HEART dataset, Canada (997 echos, 595 patients). We examined the performance of the models overall, and in subgroups (healthy controls, at risk of heart failure (HF), HF with reduced ejection fraction (HFrEF) and HF with preserved ejection fraction (HFpEF)). We compared the models' performance to the MAGGIC risk score, and examined the correlation between the models' predicted probability of death and baseline quality of life as measured by the Kansas City Cardiomyopathy Questionnaire (KCCQ).FindingsMortality rates at 1-, 3- and 5-years were 14.9%, 28.6%, and 42.5% in the Mackay cohort, and 3.0%, 10.3%, and 18.7%, in the Alberta HEART cohort. The ResNet and CatBoost models achieved area under the receiver-operating curve (AUROC) between 85% and 92% in internal validation. In external validation, the AUROCs for the ResNet (82%, 82%, and 78%) were significantly better than CatBoost (78%, 73%, and 75%), for 1-, 3- and 5-year mortality prediction respectively, with better or comparable performance to the MAGGIC score. ResNet models predicted higher probability of death in the HFpEF and HFrEF (30%-50%) subgroups than in controls and at risk patients (5%-20%). The predicted probabilities of death correlated with KCCQ scores (all p < 0.05).InterpretationEcho-based ML models to predict mortality had good internal and external validity, were generalizable, correlated with patients' quality of life, and are comparable to an established HF risk score. These models can be leveraged for automated risk stratification at point-of-care.FundingFunding for Alberta HEART was provided by an Alberta Innovates - Health Solutions Interdisciplinary Team Grant no. AHFMRITG 200801018. P.K. holds a Canadian Institutes of Health Research (CIHR) Sex and Gender Science Chair and a Heart & Stroke Foundation Chair in Cardiovascular Research. A.V. and V.S. received funding from the Mitacs Globalink Research Internship.
| S-EPMC10006431 | biostudies-literature
Project description:BackgroundPrevention is highly involved in reducing the incidence of post-thrombotic syndrome (PTS). We aimed to develop accurate models with machine learning (ML) algorithms to predict whether PTS would occur within 24 months.Materials and methodsThe clinical data used for model building were obtained from the Acute Venous Thrombosis: Thrombus Removal with Adjunctive Catheter-Directed Thrombolysis study and the external validation cohort was acquired from the Sun Yat-sen Memorial Hospital in China. The main outcome was defined as the occurrence of PTS events (Villalta score ≥5). Twenty-three clinical variables were included, and four ML algorithms were applied to build the models. For discrimination and calibration, F scores were used to evaluate the prediction ability of the models. The external validation cohort was divided into ten groups based on the risk estimate deciles to identify the hazard threshold.ResultsIn total, 555 patients with deep vein thrombosis (DVT) were included to build models using ML algorithms, and the models were further validated in a Chinese cohort comprising 117 patients. When predicting PTS within 2 years after acute DVT, logistic regression based on gradient descent and L1 regularization got the highest area under the curve (AUC) of 0.83 (95% CI:0.76-0.89) in external validation. When considering model performance in both the derivation and external validation cohorts, the eXtreme gradient boosting and gradient boosting decision tree models had similar results and presented better stability and generalization. The external validation cohort was divided into low, intermediate, and high-risk groups with the prediction probability of 0.3 and 0.4 as critical points.ConclusionMachine learning models built for PTS had accurate prediction ability and stable generalization, which can further facilitate clinical decision-making, with potentially important implications for selecting patients who will benefit from endovascular surgery.
| S-EPMC9523080 | biostudies-literature
Project description:BackgroundCognitive impairment in schizophrenia remains a chief source of functional disability and impairment, despite the potential for effective interventions. This is in part related to a lack of practical and easy to administer screening strategies that can identify and help triage cognitive impairment. This study explores how smartphone-based assessments may help address this need.MethodsIn this study, data was analyzed from 25 subjects with schizophrenia and 30 controls who engaged with a gamified mobile phone version of the Trails-B cognitive assessment in their everyday life over 90 days and complete a clinical neurocognitive testing battery at the beginning and end of the study. Machine learning was applied to the resulting dataset to predict disease status and neurocognitive function and understand which features were most important for accurate prediction.ResultsThe generated models predicted disease status with high accuracy using static features alone (AUC = 0.94), with the total number of items collected and the total duration of interaction with the application most predictive. The addition of temporal data statistically significantly improved performance (AUC = 0.95), with the amount of idle time a significant new predictor. Correlates of sleep dysfunction were also predicted (AUC = 0.80), with similar feature importance.DiscussionMachine learning enabled the highly accurate identification of subjects with schizophrenia versus healthy controls, and the accurate prediction of neurocognitive function. The addition of temporal data significantly improved the performance of these models, underscoring the value of smartphone-based assessments of cognition as a practical tool for assessing cognition.
| S-EPMC8655108 | biostudies-literature
Project description:PurposeContrast sensitivity (CS) testing is an important measure of visual function reflecting variations in everyday visual experience in different conditions and helps to identify more subtle vision loss. However, it is only infrequently used. To make this more accessible, we have developed and validated a smartphone-based CS test.MethodsA new tumbling-E smartphone-based CS test was developed, Peek Contrast Sensitivity (PeekCS). This was field tested and refined through several iterations. Reference standard was a tumbling-E Pelli-Robson CS test (PRCS). The validation study was conducted in community clinics in Ethiopia. Test-retest variability was measured for both PRCS and PeekCS. PRCS and PeekCS were then compared. Correlation coefficients and 95% confidence intervals (CIs) were calculated; 95% limits of agreement were calculated and displayed on Bland-Altman plots.ResultsPeekCS showed strong repeatability (correlation coefficient: 0.93; 95% CI: 0.91-0.95), which was comparable with PRCS (correlation coefficient: 0.96; 95% CI: 0.95-0.97). The 95% limit of agreement for test-retest variability of PRCS and PeekCS were -0.20 to 0.21 and -0.31 to 0.29, respectively. PRCS and PeekCS were highly correlated: 0.94 (95% CI: 0.93-0.95); 95% limits of agreement -0.27 to 0.29; and mean difference 0.010 (95% CI: -0.001 to 0.022). PeekCS had a faster testing time (44.6 seconds) than PRCS (48.6 seconds): mean difference -3.98 (95% CI: -5.38 to -2.58); P < 0.001.ConclusionsThe smartphone-based PeekCS is a repeatable and rapid test, providing results that are highly comparable with the commonly used PRCS test.Translational relevancePeekCS provides an accessible and easy to perform alternative for CS testing, particularly in the community setting.
| S-EPMC6743644 | biostudies-literature
Project description:BackgroundThe main obstacle to a patient's recovery following a tonsillectomy is complications, and bleeding is the most frequent culprit. Predicting post-tonsillectomy hemorrhage (PTH) allows for accurate identification of high-risk populations and the implementation of protective measures. Our study aimed to investigate how well machine learning models predict the risk of PTH.MethodsData were obtained from 520 patients who underwent a tonsillectomy at The 940th Hospital of Joint Logistics Support Force of Chinese People's Liberation Army. The age range of the patients was 2-57 years, and 364 (70%) were male. The prediction models were developed using five machine learning models: decision tree, support vector machine (SVM), extreme gradient boosting (XGBoost), random forest, and logistic regression. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC). Shapley additive explanation (SHAP) was used to interpret the results of the best-performing model.ResultsThe frequency of PTH was 11.54% among the 520 patients, with 10.71% in the training group and 13.46% in the validation set. Age, BMI, season, smoking, blood type, INR, combined secretory otitis media, combined adenoidectomy, surgical wound, and use of glucocorticoids were selected by mutual information (MI) method. The XGBoost model had best AUC (0.812) and Brier score (0.152). Decision curve analysis (DCA) showed that the model had a high clinical utility. The SHAP method revealed the top 10 variables of MI according to the importance ranking, and the average of the age was recognized as the most important predictor variable.ConclusionThis study built a PTH risk prediction model using machine learning. The XGBoost model is a tool with potential to facilitate population management strategies for PTH.
| S-EPMC9941337 | biostudies-literature
Project description:Background and aimsBiliary atresia is a rare and devastating bile duct disease that occurs during the neonatal period. Timely identification and prompt surgical intervention is critical for improving the outcome. The aim of the study was to develop a new machine learning-based prediction model for the detection of biliary atresia.MethodsNeonates aged <100 days with cholestasis at least once were retrospectively screened in 2 tertiary referral hospitals between 2015 and 2020. Simple demographic data, routine laboratory indices, and imaging findings of ultrasonography and hepatobiliary scintigraphy were used as features in the multivariate analysis. The extreme gradient boosting (XGBoost) framework was used to develop prediction models according to the diagnostic steps.ResultsAmong 1605 enrolled neonates with all-cause cholestasis, 145 (9%) were included as having biliary atresia. Direct bilirubin, gamma-glutamyl transpeptidase, abdominal sonography, and hepatobiliary scan were the most impactful features in prediction models. The Step II XGBoost model, consisting of nonimaging inputs, showed excellent discriminatory performance (area under the curve = 0.97). The Step III and IV XGBoost models showed near-perfect performances (area under the curve = 0.998 and 0.999, respectively). In external validation (n = 912 with 118 [12.9%] biliary atresia), XGBoost-based prediction models consistently showed acceptable performances. Utilizing shapley additive explanation values also provided visualized insight and explanation of the contribution of features in detecting biliary atresia. The models were integrated into a web-based diagnostic tool for case-level application.ConclusionWe introduced a new machine learning-based prediction model for detecting biliary atresia in the largest cohorts of neonatal cholestasis.
| S-EPMC11307559 | biostudies-literature
Project description:Introduction: The duration and frequency of crying of an infant can be indicative of its health. Manual tracking and labeling of crying is laborious, subjective, and sometimes inaccurate. The aim of this study was to develop and technically validate a smartphone-based algorithm able to automatically detect crying. Methods: For the development of the algorithm a training dataset containing 897 5-s clips of crying infants and 1,263 clips of non-crying infants and common domestic sounds was assembled from various online sources. OpenSMILE software was used to extract 1,591 audio features per audio clip. A random forest classifying algorithm was fitted to identify crying from non-crying in each audio clip. For the validation of the algorithm, an independent dataset consisting of real-life recordings of 15 infants was used. A 29-min audio clip was analyzed repeatedly and under differing circumstances to determine the intra- and inter- device repeatability and robustness of the algorithm. Results: The algorithm obtained an accuracy of 94% in the training dataset and 99% in the validation dataset. The sensitivity in the validation dataset was 83%, with a specificity of 99% and a positive- and negative predictive value of 75 and 100%, respectively. Reliability of the algorithm appeared to be robust within- and across devices, and the performance was robust to distance from the sound source and barriers between the sound source and the microphone. Conclusion: The algorithm was accurate in detecting cry duration and was robust to various changes in ambient settings.
| S-EPMC8076575 | biostudies-literature
Project description:BackgroundAs the manual creation and maintenance of biomedical ontologies are labor-intensive, automatic aids are desirable in the lifecycle of ontology development.ObjectiveProvided with a set of concept names in the Foundational Model of Anatomy (FMA), we propose an innovative method for automatically generating the taxonomy and the partonomy structures among them, respectively.MethodsOur approach comprises 2 main tasks: The first task is predicting the direct relation between 2 given concept names by utilizing word embedding methods and training 2 machine learning models, Convolutional Neural Networks (CNN) and Bidirectional Long Short-term Memory Networks (Bi-LSTM). The second task is the introduction of an original granularity-based method to identify the semantic structures among a group of given concept names by leveraging these trained models.ResultsResults show that both CNN and Bi-LSTM perform well on the first task, with F1 measures above 0.91. For the second task, our approach achieves an average F1 measure of 0.79 on 100 case studies in the FMA using Bi-LSTM, which outperforms the primitive pairwise-based method.ConclusionsWe have investigated an automatic way of predicting a hierarchical relationship between 2 concept names; based on this, we have further invented a methodology to structure a group of concept names automatically. This study is an initial investigation that will shed light on further work on the automatic creation and enrichment of biomedical ontologies.
| S-EPMC7725650 | biostudies-literature
Project description:ImportanceThere is an absence of mortality risk assessment tools in first-episode psychosis (FEP) that could enable personalized interventions.ObjectiveTo examine the feasibility of machine learning (ML) in discerning mortality risk in FEP and to assess whether such risk predictions can inform pharmacotherapy choices.Design, setting, and participantsIn this prognostic study, Swedish nationwide cohort data (from July 1, 2006, to December 31, 2021) were harnessed for model development and validation. Finnish cohort data (from January 1, 1998, to December 31, 2017) were used for external validation. Data analyses were completed between December 2022 and December 2023.Main outcomes and measuresFifty-one nationwide register variables, encompassing demographics and clinical and work-related histories, were subjected to ML to predict future mortality risk. The ML model's performance was evaluated by calculating the area under the receiver operating characteristic curve (AUROC). The comparative effectiveness of pharmacotherapies in patients was assessed and was stratified by the ML model to those with predicted high mortality risk (vs low risk), using the between-individual hazard ratio (HR). The 5 most important variables were then identified and a model was retrained using these variables in the discovery sample.ResultsThis study included 24 052 Swedish participants (20 000 in the discovery sample and 4052 in the validation sample) and 1490 Finnish participants (in the validation sample). Swedish participants had a mean (SD) age of 29.1 (8.1) years, 62.1% were men, and 418 died with 2 years. Finnish participants had a mean (SD) age of 29.7 (8.0) years, 61.7% were men, and 31 died within 2 years. The discovery sample achieved an AUROC of 0.71 (95% CI, 0.68-0.74) for 2-year mortality prediction. Using the 5 most important variables (ie, the top 10% [substance use comorbidities, first hospitalization duration due to FEP, male sex, prior somatic hospitalizations, and age]), the final model resulted in an AUROC of 0.70 (95% CI, 0.63-0.76) in the Swedish sample and 0.67 (95% CI, 0.56-0.78) in the Finnish sample. Individuals with predicted high mortality risk had an elevated 15-year risk in the Swedish sample (HR, 3.77 [95% CI, 2.92-4.88]) and an elevated 20-year risk in the Finnish sample (HR, 3.72 [95% CI, 2.67-5.18]). For those with predicted high mortality risk, long-acting injectable antipsychotics (HR, 0.45 [95% CI, 0.23-0.88]) and mood stabilizers (HR, 0.64 [95% CI, 0.46-0.90]) were associated with decreased mortality risk. Conversely, for those predicted to survive, only oral aripiprazole (HR, 0.38 [95% CI, 0.20-0.69]) and risperidone (HR, 0.38 [95% CI, 0.18-0.82]) were associated with decreased mortality risk.Conclusions and relevanceIn this prognostic study, an ML-based model was developed and validated to predict mortality risk in FEP. These findings may help to develop personalized interventions to mitigate mortality risk in FEP.
| S-EPMC10949098 | biostudies-literature
Project description:The major challenge in the diagnosis of disseminated intravascular coagulation (DIC) comes from the lack of specific biomarkers, leading to developing composite scoring systems. DIC scores are simple and rapidly applicable. However, optimal fibrin-related markers and their cut-off values remain to be defined, requiring optimization for use. The aim of this study is to optimize the use of DIC-related parameters through machine learning (ML)-approach. Further, we evaluated whether this approach could provide a diagnostic value in DIC diagnosis. For this, 46 DIC-related parameters were investigated for both clinical findings and laboratory results. We retrospectively reviewed 656 DIC-suspected cases at an initial order for full DIC profile and labeled their evaluation results (Set 1; DIC, n = 228; non-DIC, n = 428). Several ML algorithms were tested, and an artificial neural network (ANN) model was established via independent training and testing using 32 selected parameters. This model was externally validated from a different hospital with 217 DIC-suspected cases (Set 2; DIC, n = 80; non-DIC, n = 137). The ANN model represented higher AUC values than the three scoring systems in both set 1 (ANN 0.981; ISTH 0.945; JMHW 0.943; and JAAM 0.928) and set 2 (AUC ANN 0.968; ISTH 0.946). Additionally, the relative importance of the 32 parameters was evaluated. Most parameters had contextual importance, however, their importance in ML-approach was different from the traditional scoring system. Our study demonstrates that ML could optimize the use of clinical parameters with robustness for DIC diagnosis. We believe that this approach could play a supportive role in physicians' medical decision by integrated into electrical health record system. Further prospective validation is required to assess the clinical consequence of ML-approach and their clinical benefit.
| S-EPMC5931474 | biostudies-literature