- Browse by Subject
Browsing by Subject "Prediction"
Now showing 1 - 10 of 21
Results Per Page
Sort Options
Item Assessing Risk of Future Suicidality in Emergency Department Patients(Wiley, 2020-04-02) Brucker, Krista; Duggan, Carter; Niezer, Joseph; Roseberry, Kyle; Le-Niculescu, Helen; Niculescu, Alexander B.; Kline, Jeffrey A.; Emergency Medicine, School of MedicineBackground. Emergency Departments (ED) are the first line of evaluation for patients at risk and in crisis, with or without overt suicidality (ideation, attempts). Currently employed triage and assessments methods miss some of the individuals who subsequently become suicidal. The Convergent Functional Information for Suicidality (CFI-S) 22 item checklist of risk factors, that does not ask directly about suicidal ideation, has demonstrated good predictive ability for suicidality in previous studies in psychiatric outpatients, but has not been tested in the real world-setting of emergency departments (EDs). Methods. We administered CFI-S prospectively to a convenience sample of consecutive ED patients. Median administration time was 3 minutes. Patients were also asked at triage about suicidal thoughts or intentions per standard ED suicide clinical screening (SCS), and the treating ED physician was asked to fill a physician gestalt visual analog scale (VAS) for likelihood of future suicidality spectrum events (SSE) (ideation, preparatory acts, attempts, completed suicide). We performed structured chart review and telephone follow-up at 6 months post index visit. Results. The median time to complete the CFI-S was three minutes (1st to 3rd quartile 3–6 minutes). Of the 338 patients enrolled, 45 (13.3%) were positive on the initial SCS, and 32 (9.5%) experienced a SSE in the 6 months follow-up. Overall, across genders, SCS had a modest diagnostic discrimination for future SSE (ROC AUC 0.63,). The physician VAS was better (AUC 0.76 CI 0.66–0.85), and the CFI-S was slightly higher (AUC 0.81, CI 0.76–0.87). The top CFI-S differentiating items were psychiatric illness, perceived uselessness, and social isolation. The top CFI-S items were family history of suicide, age, and past history of suicidal acts. Conclusions. Using CFI-S, or some of its items, in busy EDs may help improve the detection of patients at high risk for future suicidality.Item Can Early-Assignment Grades Predict Final Grades in IT Courses?: American Society for Engineering Education(2017) Ramanathan, Parameswari; Fernandez, Eugenia; Computer Information and Graphics Technology, School of Engineering and TechnologyItem Classification and prediction of cognitive trajectories of cognitively unimpaired individuals(Frontiers Media, 2023-03-13) Kim, Young Ju; Kim, Si Eun; Hahn, Alice; Jang, Hyemin; Kim, Jun Pyo; Kim, Hee Jin; Na, Duk L.; Chin, Juhee; Seo, Sang Won; Alzheimer’s Disease Neuroimaging Initiative; Radiology and Imaging Sciences, School of MedicineObjectives: Efforts to prevent Alzheimer's disease (AD) would benefit from identifying cognitively unimpaired (CU) individuals who are liable to progress to cognitive impairment. Therefore, we aimed to develop a model to predict cognitive decline among CU individuals in two independent cohorts. Methods: A total of 407 CU individuals from the Alzheimer's Disease Neuroimaging Initiative (ADNI) and 285 CU individuals from the Samsung Medical Center (SMC) were recruited in this study. We assessed cognitive outcomes by using neuropsychological composite scores in the ADNI and SMC cohorts. We performed latent growth mixture modeling and developed the predictive model. Results: Growth mixture modeling identified 13.8 and 13.0% of CU individuals in the ADNI and SMC cohorts, respectively, as the "declining group." In the ADNI cohort, multivariable logistic regression modeling showed that increased amyloid-β (Aβ) uptake (β [SE]: 4.852 [0.862], p < 0.001), low baseline cognitive composite scores (β [SE]: -0.274 [0.070], p < 0.001), and reduced hippocampal volume (β [SE]: -0.952 [0.302], p = 0.002) were predictive of cognitive decline. In the SMC cohort, increased Aβ uptake (β [SE]: 2.007 [0.549], p < 0.001) and low baseline cognitive composite scores (β [SE]: -4.464 [0.758], p < 0.001) predicted cognitive decline. Finally, predictive models of cognitive decline showed good to excellent discrimination and calibration capabilities (C-statistic = 0.85 for the ADNI model and 0.94 for the SMC model). Conclusion: Our study provides novel insights into the cognitive trajectories of CU individuals. Furthermore, the predictive model can facilitate the classification of CU individuals in future primary prevention trials.Item Comparisons of Metabolic Measures to Predict T1D vs Detect a Preventive Treatment Effect in High-Risk Individuals(Oxford University Press, 2024) Sims, Emily K.; Cuthbertson, David; Jacobsen, Laura; Ismail, Heba M.; Nathan, Brandon M.; Herold, Kevan C.; Redondo, Maria J.; Sosenko, Jay; Pediatrics, School of MedicineContext: Metabolic measures are frequently used to predict type 1 diabetes (T1D) and to understand effects of disease-modifying therapies. Objective: Compare metabolic endpoints for their ability to detect preventive treatment effects and predict T1D. Methods: Six-month changes in metabolic endpoints were assessed for (1) detecting treatment effects by comparing placebo and treatment arms from the randomized controlled teplizumab prevention trial, a multicenter clinical trial investigating 14-day intravenous teplizumab infusion and (2) predicting T1D in the TrialNet Pathway to Prevention natural history study. For each metabolic measure, t-Values from t tests for detecting a treatment effect were compared with chi-square values from proportional hazards regression for predicting T1D. Participants in the teplizumab prevention trial and participants in the Pathway to Prevention study selected with the same inclusion criteria used for the teplizumab trial were studied. Results: Six-month changes in glucose-based endpoints predicted diabetes better than C-peptide-based endpoints, yet the latter were better at detecting a teplizumab effect. Combined measures of glucose and C-peptide were more balanced than measures of glucose alone or C-peptide alone for predicting diabetes and detecting a teplizumab effect. Conclusion: The capacity of a metabolic endpoint to detect a treatment effect does not necessarily correspond to its accuracy for predicting T1D. However, combined glucose and C-peptide endpoints appear to be effective for both predicting diabetes and detecting a response to immunotherapy. These findings suggest that combined glucose and C-peptide endpoints should be incorporated into the design of future T1D prevention trials.Item Delirium Severity Trajectories and Outcomes in ICU Patients. Defining a Dynamic Symptom Phenotype(American Thoracic Society, 2020-09) Lindroth, Heidi; Khan, Babar A.; Carpenter, Janet S.; Gao, Sujuan; Perkins, Anthony J.; Khan, Sikandar H.; Wang, Sophia; Jones, Richard N.; Boustani, Malaz A.; School of NursingRationale: Delirium severity and duration are independently associated with higher mortality and morbidity. No studies to date have described a delirium trajectory by integrating both severity and duration. Objectives: The primary aim was to develop delirium trajectories by integrating symptom severity and duration. The secondary aim was to investigate the association among trajectory membership, clinical characteristics, and 30-day mortality. Methods: A secondary analysis of the PMD (Pharmacologic Management of Delirium) randomized control trial (ClinicalTrials.gov Identifier: NCT00842608; N = 531) was conducted. The presence of delirium and symptom severity were measured at least daily for 7 days using the Confusion Assessment Method for the intensive care unit (CAM-ICU) and CAM-ICU-7 (on a scale of 0-7, with 7 being the most severe). Delirium trajectories were defined using an innovative, data-driven statistical method (group-based trajectory modeling [GBTM]) and SAS v9.4.Results: A total of 531 delirious participants (mean age 60 yr [standard deviation = 16], 55% female, and 46% African American) were analyzed. Five distinct delirium trajectories were described (CAM-ICU-7: mean [standard deviation]); mild-brief (CAM-ICU-7: 0.5 [0.5]), severe-rapid recovers (CAM-ICU-7: 2.1 [1.0]), mild-accelerating (CAM-ICU-7: 2.2 [0.9]), severe-slow recovers (CAM-ICU-7: 3.9 [0.9]), and severe-nonrecovers (CAM-ICU-7: 5.9 [1.0]). Baseline cognition and race were associated with trajectory membership. Trajectory membership independently predicted 30-day mortality while controlling for age, sex, race, cognition, illness severity, and comorbidities. Conclusions: This secondary analysis described five distinct delirium trajectories based on delirium symptom severity and duration using group-based trajectory modeling. Trajectory membership predicted 30-day mortality.Item Differential Learning for Outliers: A Case Study of Water Demand Prediction(MDPI, 2018-11) Shah, Setu; Ben Miled, Zina; Schaefer, Rebecca; Berube, Steve; Electrical and Computer Engineering, School of Engineering and TechnologyPredicting water demands is becoming increasingly critical because of the scarcity of this natural resource. In fact, the subject was the focus of numerous studies by a large number of researchers around the world. Several models have been proposed that are able to predict water demands using both statistical and machine learning techniques. These models have successfully identified features that can impact water demand trends for rural and metropolitan areas. However, while the above models, including recurrent network models proposed by the authors are able to predict normal water demands, most have difficulty estimating potential deviations from the norms. Outliers in water demand can be due to various reasons including high temperatures and voluntary or mandatory consumption restrictions by the water utility companies. Estimating these deviations is necessary, especially for water utility companies with a small service footprint, in order to efficiently plan water distribution. This paper proposes a differential learning model that can help model both over-consumption and under-consumption. The proposed differential model builds on a previously proposed recurrent neural network model that was successfully used to predict water demand in central Indiana.Item External validation of the modified sepsis renal angina index for prediction of severe acute kidney injury in children with septic shock(Springer Nature, 2023-11-28) Stanski, Natalja L.; Basu, Rajit K.; Cvijanovich, Natalie Z.; Fitzgerald, Julie C.; Bigham, Michael T.; Jain, Parag N.; Schwarz, Adam J.; Lutfi, Riad; Thomas, Neal J.; Baines, Torrey; Haileselassie, Bereketeab; Weiss, Scott L.; Atreya, Mihir R.; Lautz, Andrew J.; Zingarelli, Basilia; Standage, Stephen W.; Kaplan, Jennifer; Chawla, Lakhmir S.; Goldstein, Stuart L.; Pediatrics, School of MedicineBackground: Acute kidney injury (AKI) occurs commonly in pediatric septic shock and increases morbidity and mortality. Early identification of high-risk patients can facilitate targeted intervention to improve outcomes. We previously modified the renal angina index (RAI), a validated AKI prediction tool, to improve specificity in this population (sRAI). Here, we prospectively assess sRAI performance in a separate cohort. Methods: A secondary analysis of a prospective, multicenter, observational study of children with septic shock admitted to the pediatric intensive care unit from 1/2019 to 12/2022. The primary outcome was severe AKI (≥ KDIGO Stage 2) on Day 3 (D3 severe AKI), and we compared predictive performance of the sRAI (calculated on Day 1) to the original RAI and serum creatinine elevation above baseline (D1 SCr > Baseline +). Original renal angina fulfillment (RAI +) was defined as RAI ≥ 8; sepsis renal angina fulfillment (sRAI +) was defined as RAI ≥ 20 or RAI 8 to < 20 with platelets < 150 × 103/µL. Results: Among 363 patients, 79 (22%) developed D3 severe AKI. One hundred forty (39%) were sRAI + , 195 (54%) RAI + , and 253 (70%) D1 SCr > Baseline + . Compared to sRAI-, sRAI + had higher risk of D3 severe AKI (RR 8.9, 95%CI 5-16, p < 0.001), kidney replacement therapy (KRT) (RR 18, 95%CI 6.6-49, p < 0.001), and mortality (RR 2.5, 95%CI 1.2-5.5, p = 0.013). sRAI predicted D3 severe AKI with an AUROC of 0.86 (95%CI 0.82-0.90), with greater specificity (74%) than D1 SCr > Baseline (36%) and RAI + (58%). On multivariable regression, sRAI + retained associations with D3 severe AKI (aOR 4.5, 95%CI 2.0-10.2, p < 0.001) and need for KRT (aOR 5.6, 95%CI 1.5-21.5, p = 0.01). Conclusions: Prediction of severe AKI in pediatric septic shock is important to improve outcomes, allocate resources, and inform enrollment in clinical trials examining potential disease-modifying therapies. The sRAI affords more accurate and specific prediction than context-free SCr elevation or the original RAI in this population.Item Index60 as an additional diagnostic criterion for type 1 diabetes(Springer, 2021) Redondo, Maria J.; Nathan, Brandon M.; Jacobsen, Laura M.; Sims, Emily; Bocchino, Laura E.; Pugliese, Alberto; Schatz, Desmond A.; Atkinson, Mark A.; Skyler, Jay; Palmer, Jerry; Geyer, Susan; Sosenko, Jay M.; Type 1 diabetes TrialNet Study Group; Pediatrics, School of MedicineAims/hypothesis: We aimed to compare characteristics of individuals identified in the peri-diagnostic range by Index60 (composite glucose and C-peptide measure) ≥2.00, 2 h OGTT glucose ≥11.1 mmol/l, or both. Methods: We studied autoantibody-positive participants in the Type 1 Diabetes TrialNet Pathway to Prevention study who, at their baseline OGTT, had 2 h blood glucose ≥11.1 mmol/l and/or Index60 ≥2.00 (n = 354, median age = 11.2 years, age range = 1.7-46.6; 49% male, 83% non-Hispanic White). Type 1 diabetes-relevant characteristics (e.g., age, C-peptide, autoantibodies, BMI) were compared among three mutually exclusive groups: 2 h glucose ≥11.1 mmol/l and Index60 <2.00 [Glu(+), n = 76], 2 h glucose <11.1 mmol/l and Index60 ≥2.00 [Ind(+), n = 113], or both 2 h glucose ≥11.1 mmol/l and Index60 ≥2.00 [Glu(+)/Ind(+), n = 165]. Results: Participants in Glu(+), vs those in Ind(+) or Glu(+)/Ind(+), were older (mean ages = 22.9, 11.8 and 14.7 years, respectively), had higher early (30-0 min) C-peptide response (1.0, 0.50 and 0.43 nmol/l), higher AUC C-peptide (2.33, 1.13 and 1.10 nmol/l), higher percentage of overweight/obesity (58%, 16% and 30%) (all comparisons, p < 0.0001), and a lower percentage of multiple autoantibody positivity (72%, 92% and 93%) (p < 0.001). OGTT-stimulated C-peptide and glucose patterns of Glu(+) differed appreciably from Ind(+) and Glu(+)/Ind(+). Progression to diabetes occurred in 61% (46/76) of Glu(+) and 63% (71/113) of Ind(+). Even though Index60 ≥2.00 was not a Pathway to Prevention diagnostic criterion, Ind(+) had a 4 year cumulative diabetes incidence of 95% (95% CI 86%, 98%). Conclusions/interpretation: Participants in the Ind(+) group had more typical characteristics of type 1 diabetes than participants in the Glu(+) did and were as likely to be diagnosed. However, unlike Glu(+) participants, Ind(+) participants were not identified at the baseline OGTT.Item Motor onset and diagnosis in Huntington disease using the diagnostic confidence level(Springer, 2015-12) Liu, Dawei; Long, Jeffrey D.; Zhang, Ying; Raymond, Lynn A.; Marder, Karen; Rosser, Anne; McCusker, Elizabeth A.; Mills, James A.; Paulsen, Jane S.; Department of Biostatistics, Richard M. Fairbanks School of Public HealthHuntington disease (HD) is a neurodegenerative disorder characterized by motor dysfunction, cognitive deterioration, and psychiatric symptoms, with progressive motor impairments being a prominent feature. The primary objectives of this study are to delineate the disease course of motor function in HD, to provide estimates of the onset of motor impairments and motor diagnosis, and to examine the effects of genetic and demographic variables on the progression of motor impairments. Data from an international multisite, longitudinal observational study of 905 prodromal HD participants with cytosine-adenine-guanine (CAG) repeats of at least 36 and with at least two visits during the followup period from 2001 to 2012 was examined for changes in the diagnostic confidence level from the Unified Huntington's Disease Rating Scale. HD progression from unimpaired to impaired motor function, as well as the progression from motor impairment to diagnosis, was associated with the linear effect of age and CAG repeat length. Specifically, for every 1-year increase in age, the risk of transition in diagnostic confidence level increased by 11% (95% CI 7-15%) and for one repeat length increase in CAG, the risk of transition in diagnostic confidence level increased by 47% (95% CI 27-69%). Findings show that CAG repeat length and age increased the likelihood of the first onset of motor impairment as well as the age at diagnosis. Results suggest that more accurate estimates of HD onset age can be obtained by incorporating the current status of diagnostic confidence level into predictive models.Item Patient-GAT: Sarcopenia Prediction using Multi-modal Data Fusion and Weighted Graph Attention Networks(Association for Computing Machinery, 2023) Xiao, Cary; Imel, Erik A.; Pham, Nam; Luo, Xiao; Medicine, School of MedicineGraph Attention Networks (GAT) have been extensively used to perform node-level classification on data that can be represented as a graph. However, few papers have investigated the effectiveness of using GAT on graph representations of patient similarity networks. This paper proposes Patient-GAT, a novel method to predict chronic health conditions by first integrating multi-modal data fusion to generate patient vector representations using imputed lab variables with other structured data. This data representation is then used to construct a patient network by measuring patient similarity, finally applying GAT to the patient network for disease prediction. We demonstrated our framework by predicting sarcopenia using real-world EHRs obtained from the Indiana Network for Patient Care. We evaluated the performance of our system by comparing it to other baseline models, showing that our model outperforms other methods. In addition, we studied the contribution of the temporal representation of the lab data and discussed the interpretability of this model by analyzing the attention coefficients of the trained Patient-GAT model. Our code can be found on Github.
- «
- 1 (current)
- 2
- 3
- »