Browsing by Subject "Diagnosis, Computer-Assisted"

Now showing 1 - 7 of 7
  • Thumbnail Image
    ItemOpen Access
    Development of a preoperative predictive model for major complications following adult spinal deformity surgery.
    (Journal of neurosurgery. Spine, 2017-06) Scheer, Justin K; Smith, Justin S; Schwab, Frank; Lafage, Virginie; Shaffrey, Christopher I; Bess, Shay; Daniels, Alan H; Hart, Robert A; Protopsaltis, Themistocles S; Mundis, Gregory M; Sciubba, Daniel M; Ailon, Tamir; Burton, Douglas C; Klineberg, Eric; Ames, Christopher P; International Spine Study Group
    OBJECTIVE The operative management of patients with adult spinal deformity (ASD) has a high complication rate and it remains unknown whether baseline patient characteristics and surgical variables can predict early complications (intraoperative and perioperative [within 6 weeks]). The development of an accurate preoperative predictive model can aid in patient counseling, shared decision making, and improved surgical planning. The purpose of this study was to develop a model based on baseline demographic, radiographic, and surgical factors that can predict if patients will sustain an intraoperative or perioperative major complication. METHODS This study was a retrospective analysis of a prospective, multicenter ASD database. The inclusion criteria were age ≥ 18 years and the presence of ASD. In total, 45 variables were used in the initial training of the model including demographic data, comorbidities, modifiable surgical variables, baseline health-related quality of life, and coronal and sagittal radiographic parameters. Patients were grouped as either having at least 1 major intraoperative or perioperative complication (COMP group) or not (NOCOMP group). An ensemble of decision trees was constructed utilizing the C5.0 algorithm with 5 different bootstrapped models. Internal validation was accomplished via a 70/30 data split for training and testing each model, respectively. Overall accuracy, the area under the receiver operating characteristic (AUROC) curve, and predictor importance were calculated. RESULTS Five hundred fifty-seven patients were included: 409 (73.4%) in the NOCOMP group, and 148 (26.6%) in the COMP group. The overall model accuracy was 87.6% correct with an AUROC curve of 0.89 indicating a very good model fit. Twenty variables were determined to be the top predictors (importance ≥ 0.90 as determined by the model) and included (in decreasing importance): age, leg pain, Oswestry Disability Index, number of decompression levels, number of interbody fusion levels, Physical Component Summary of the SF-36, Scoliosis Research Society (SRS)-Schwab coronal curve type, Charlson Comorbidity Index, SRS activity, T-1 pelvic angle, American Society of Anesthesiologists grade, presence of osteoporosis, pelvic tilt, sagittal vertical axis, primary versus revision surgery, SRS pain, SRS total, use of bone morphogenetic protein, use of iliac crest graft, and pelvic incidence-lumbar lordosis mismatch. CONCLUSIONS A successful model (87% accuracy, 0.89 AUROC curve) was built predicting major intraoperative or perioperative complications following ASD surgery. This model can provide the foundation toward improved education and point-of-care decision making for patients undergoing ASD surgery.
  • Thumbnail Image
    ItemOpen Access
    Development of a validated computer-based preoperative predictive model for pseudarthrosis with 91% accuracy in 336 adult spinal deformity patients.
    (Neurosurgical focus, 2018-11) Scheer, Justin K; Oh, Taemin; Smith, Justin S; Shaffrey, Christopher I; Daniels, Alan H; Sciubba, Daniel M; Hamilton, D Kojo; Protopsaltis, Themistocles S; Passias, Peter G; Hart, Robert A; Burton, Douglas C; Bess, Shay; Lafage, Renaud; Lafage, Virginie; Schwab, Frank; Klineberg, Eric O; Ames, Christopher P; International Spine Study Group
    OBJECTIVEPseudarthrosis can occur following adult spinal deformity (ASD) surgery and can lead to instrumentation failure, recurrent pain, and ultimately revision surgery. In addition, it is one of the most expensive complications of ASD surgery. Risk factors contributing to pseudarthrosis in ASD have been described; however, a preoperative model predicting the development of pseudarthrosis does not exist. The goal of this study was to create a preoperative predictive model for pseudarthrosis based on demographic, radiographic, and surgical factors.METHODSA retrospective review of a prospectively maintained, multicenter ASD database was conducted. Study inclusion criteria consisted of adult patients (age ≥ 18 years) with spinal deformity and surgery for the ASD. From among 82 variables assessed, 21 were used for model building after applying collinearity testing, redundancy, and univariable predictor importance ≥ 0.90. Variables included demographic data along with comorbidities, modifiable surgical variables, baseline coronal and sagittal radiographic parameters, and baseline scores for health-related quality of life measures. Patients groups were determined according to their Lenke radiographic fusion type at the 2-year follow-up: bilateral or unilateral fusion (union) or pseudarthrosis (nonunion). A decision tree was constructed, and internal validation was accomplished via bootstrapped training and testing data sets. Accuracy and the area under the receiver operating characteristic curve (AUC) were calculated to evaluate the model.RESULTSA total of 336 patients were included in the study (nonunion: 105, union: 231). The model was 91.3% accurate with an AUC of 0.94. From 82 initial variables, the top 21 covered a wide range of areas including preoperative alignment, comorbidities, patient demographics, and surgical use of graft material.CONCLUSIONSA model for predicting the development of pseudarthrosis at the 2-year follow-up was successfully created. This model is the first of its kind for complex predictive analytics in the development of pseudarthrosis for patients with ASD undergoing surgical correction and can aid in clinical decision-making for potential preventative strategies.
  • Thumbnail Image
    ItemOpen Access
    Noninvasive monitoring of tissue hemoglobin using UV-VIS diffuse reflectance spectroscopy: a pilot study.
    (Opt Express, 2009-12-21) Bender, Janelle E; Shang, Allan B; Moretti, Eugene W; Yu, Bing; Richards, Lisa M; Ramanujam, Nirmala
    We conducted a pilot study on 10 patients undergoing general surgery to test the feasibility of diffuse reflectance spectroscopy in the visible wavelength range as a noninvasive monitoring tool for blood loss during surgery. Ratios of raw diffuse reflectance at wavelength pairs were tested as a first-pass for estimating hemoglobin concentration. Ratios can be calculated easily and rapidly with limited post-processing, and so this can be considered a near real-time monitoring device. We found the best hemoglobin correlations were when ratios at isosbestic points of oxy- and deoxyhemoglobin were used, specifically 529/500 nm. Baseline subtraction improved correlations, specifically at 520/509 nm. These results demonstrate proof-of-concept for the ability of this noninvasive device to monitor hemoglobin concentration changes due to surgical blood loss. The 529/500 nm ratio also appears to account for variations in probe pressure, as determined from measurements on two volunteers.
  • Thumbnail Image
    ItemOpen Access
    Optimized approach to decision fusion of heterogeneous data for breast cancer diagnosis.
    (Med Phys, 2006-08) Jesneck, Jonathan Lee
    As more diagnostic testing options become available to physicians, it becomes more difficult to combine various types of medical information together in order to optimize the overall diagnosis. To improve diagnostic performance, here we introduce an approach to optimize a decision-fusion technique to combine heterogeneous information, such as from different modalities, feature categories, or institutions. For classifier comparison we used two performance metrics: The receiving operator characteristic (ROC) area under the curve [area under the ROC curve (AUC)] and the normalized partial area under the curve (pAUC). This study used four classifiers: Linear discriminant analysis (LDA), artificial neural network (ANN), and two variants of our decision-fusion technique, AUC-optimized (DF-A) and pAUC-optimized (DF-P) decision fusion. We applied each of these classifiers with 100-fold cross-validation to two heterogeneous breast cancer data sets: One of mass lesion features and a much more challenging one of microcalcification lesion features. For the calcification data set, DF-A outperformed the other classifiers in terms of AUC (p < 0.02) and achieved AUC=0.85 +/- 0.01. The DF-P surpassed the other classifiers in terms of pAUC (p < 0.01) and reached pAUC=0.38 +/- 0.02. For the mass data set, DF-A outperformed both the ANN and the LDA (p < 0.04) and achieved AUC=0.94 +/- 0.01. Although for this data set there were no statistically significant differences among the classifiers' pAUC values (pAUC=0.57 +/- 0.07 to 0.67 +/- 0.05, p > 0.10), the DF-P did significantly improve specificity versus the LDA at both 98% and 100% sensitivity (p < 0.04). In conclusion, decision fusion directly optimized clinically significant performance measures, such as AUC and pAUC, and sometimes outperformed two well-known machine-learning techniques when applied to two different breast cancer data sets.
  • Thumbnail Image
    ItemOpen Access
    Prediction of Acute-Phase Treatment Outcomes by Adding a Single-Item Measure of Activity Impairment to Symptom Measurement: Development and Validation of an Interactive Calculator from the STAR*D and CO-MED Trials.
    (The international journal of neuropsychopharmacology, 2019-05) Jha, Manish K; South, Charles; Trivedi, Jay; Minhajuddin, Abu; Rush, A John; Trivedi, Madhukar H

    Background

    Day-to-day functioning is impaired in major depressive disorder. Yet there are no guidelines to systematically assess these functional changes. This report evaluates prognostic utility of changes in activity impairment to inform clinical decision-making at an individual level.

    Methods

    Mixed model analyses tested changes in activity impairment (sixth item of Work and Activity Impairment scale, rated 0-10) at mid-point (week 6) and end of step 1 (weeks 12-14) in the Sequenced Treatment Alternatives to Relieve Depression (STAR*D) trial (n = 2697) after controlling for depression severity [Quick Inventory of Depressive Symptomatology Self-Report (QIDS-SR)]. Interactive calculators for end of step 1 remission (QIDS-SR ≤5) and no meaningful benefit (<30% QIDS-SR reduction from baseline) were developed for participants with complete data (n = 1476) and independently replicated in the Combining Medications to Enhance Depression Outcomes trial (n = 399).

    Results

    Activity impairment improved independently with acute-phase treatment in STAR*D (F = 7.27; df = 2,2625; P < .001). Baseline to mid-point activity impairment change significantly predicted remission (P < .001, model area under the curve = 0.823) and no meaningful benefit (P < .001, area under the curve = 0.821) in the STAR*D trial. Adding activity impairment variables to depression severity measures correctly reclassified 28.4% and 15.8% remitters and nonremitters (net reclassification improvement analysis, P < .001), and 11.4% and 16.8% of those with no meaningful benefit and meaningful benefit (net reclassification improvement analysis, P < .001). The STAR*D trial model estimates accurately predicted remission (area under the curve = 0.80) and no meaningful benefit (area under the curve = 0.82) in the Combining Medications to Enhance Depression Outcomes trial and was used to develop an interactive calculator.

    Conclusion

    A single-item self-report measure of activity impairment changes independently with antidepressant treatment. Baseline to week 6 changes in activity impairment and depression severity can be combined to predict acute-phase remission and no meaningful benefit at an individual level.
  • Thumbnail Image
    ItemOpen Access
    Racial/ethnic variations in substance-related disorders among adolescents in the United States.
    (Archives of general psychiatry, 2011-11) Wu, Li-Tzy; Woody, George E; Yang, Chongming; Pan, Jeng-Jong; Blazer, Dan G
    While young racial/ethnic groups are the fastest growing population in the United States, data about substance-related disorders among adolescents of various racial/ethnic backgrounds are lacking.To examine the magnitude of past-year DSM-IV substance-related disorders (alcohol, marijuana, cocaine, inhalants, hallucinogens, heroin, analgesic opioids, stimulants, sedatives, and tranquilizers) among adolescents of white, Hispanic, African American, Native American, Asian or Pacific Islander, and multiple race/ethnicity.The 2005 to 2008 National Survey on Drug Use and Health.Academic research.Noninstitutionalized household adolescents aged 12 to 17 years.Substance-related disorders were assessed by standardized survey questions administered using the audio computer-assisted self-interviewing method.Of 72 561 adolescents aged 12 to 17 years, 37.0% used alcohol or drugs in the past year; 7.9% met criteria for a substance-related disorder, with Native Americans having the highest prevalence of use (47.5%) and disorder (15.0%). Analgesic opioids were the second most commonly used illegal drugs, following marijuana, in all racial/ethnic groups; analgesic opioid use was comparatively prevalent among adolescents of Native American (9.7%) and multiple race/ethnicity (8.8%). Among 27 705 past-year alcohol or drug users, Native Americans (31.5%), adolescents of multiple race/ethnicity (25.2%), adolescents of white race/ethnicity (22.9%), and Hispanics (21.0%) had the highest rates of substance-related disorders. Adolescents used marijuana more frequently than alcohol or other drugs, and 25.9% of marijuana users met criteria for marijuana abuse or dependence. After controlling for adolescents' age, socioeconomic variables, population density of residence, self-rated health, and survey year, adjusted analyses of adolescent substance users indicated elevated odds of substance-related disorders among Native Americans, adolescents of multiple race/ethnicity, adolescents of white race/ethnicity, and Hispanics compared with African Americans; African Americans did not differ from Asians or Pacific Islanders.Substance use is widespread among adolescents of Native American, white, Hispanic, and multiple race/ethnicity. These groups also are disproportionately affected by substance-related disorders.
  • Thumbnail Image
    ItemOpen Access
    Robust deep learning classification of adamantinomatous craniopharyngioma from limited preoperative radiographic images.
    (Scientific reports, 2020-10) Prince, Eric W; Whelan, Ros; Mirsky, David M; Stence, Nicholas; Staulcup, Susan; Klimo, Paul; Anderson, Richard CE; Niazi, Toba N; Grant, Gerald; Souweidane, Mark; Johnston, James M; Jackson, Eric M; Limbrick, David D; Smith, Amy; Drapeau, Annie; Chern, Joshua J; Kilburn, Lindsay; Ginn, Kevin; Naftel, Robert; Dudley, Roy; Tyler-Kabara, Elizabeth; Jallo, George; Handler, Michael H; Jones, Kenneth; Donson, Andrew M; Foreman, Nicholas K; Hankinson, Todd C
    Deep learning (DL) is a widely applied mathematical modeling technique. Classically, DL models utilize large volumes of training data, which are not available in many healthcare contexts. For patients with brain tumors, non-invasive diagnosis would represent a substantial clinical advance, potentially sparing patients from the risks associated with surgical intervention on the brain. Such an approach will depend upon highly accurate models built using the limited datasets that are available. Herein, we present a novel genetic algorithm (GA) that identifies optimal architecture parameters using feature embeddings from state-of-the-art image classification networks to identify the pediatric brain tumor, adamantinomatous craniopharyngioma (ACP). We optimized classification models for preoperative Computed Tomography (CT), Magnetic Resonance Imaging (MRI), and combined CT and MRI datasets with demonstrated test accuracies of 85.3%, 83.3%, and 87.8%, respectively. Notably, our GA improved baseline model performance by up to 38%. This work advances DL and its applications within healthcare by identifying optimized networks in small-scale data contexts. The proposed system is easily implementable and scalable for non-invasive computer-aided diagnosis, even for uncommon diseases.