Acute subdural hematoma: Outcome and outcome prediction

Patients with traumatic acute subdural hematoma were studied to determine the factors influencing outcome.Between January 1986 and August 1995, we collected 113 patients who underwent craniotomy for traumatic acute subdural hematoma. The relationship between initial clinical signs and the outcome 3 months after admission was studied retrospectively.Functional recovery was achieved in 38% of patients and the mortality was 60%. 91% of patients with a high Glasgow Coma Scale (GCS) score (9–15) and 23% of patients with a low GCS score (3–8) achieved functional recovery. All of 14 patients with a GCS score of 3 died. The mortality of patients with GCS scores of 4 and 5 was 95% to 75%, respectively. Patients over 61 years old had a mortality of 73% compared to 64% mortality for those aged 21–40 years. 97% of patients with bilateral unreactive pupil and 81% of patients with unilateral unreactive pupil died. The mortality rates of associated intracranial lesions were 91% in intracerebral hematoma, 87% in subarachnoid hemorrhage, 75% in contusion.Time from injury to surgical evacuation and type of surgical intervention did not affect mortality. Age and associated intracranial lesions were related to outcome. Severity of injury and pupillary response were the most important factors for predicting outcome.     

Comparison of artificial neural network and logistic regression models for prediction of outcomes in trauma patients: A systematic review and meta-analysis

Background

Currently, two models of artificial neural network (ANN) and logistic regression (LR) are known as models that extensively used in medical sciences. The aim of this study was to compare the ANN and LR models in prediction of Health-related outcomes in traumatic patients using a systematic review.

Initial biopsy outcome prediction--head-to-head comparison of a logistic regression-based nomogram versus artificial neural network

OBJECTIVES: Nomograms and artificial neural networks (ANNs) represent alternative methodologic approaches to predict the probability of prostate cancer on initial biopsy. We hypothesized that, in a head-to-head comparison, one of the approaches might demonstrate better accuracy and performance characteristics than the other. METHODS: A previously published nomogram, which relies on age, digital rectal examination, serum prostate-specific antigen (PSA), and percent-free PSA, and an ANN, which relies on the same predictors plus prostate volume, were applied to a cohort of 3980 men, who were subjected to multicore systematic prostate biopsy. The accuracy and the performance characteristics were compared between these two approaches. RESULTS: The accuracy of the nomogram was 71% versus 67% for the ANN (p=0.0001). Graphical exploration of the performance characteristics demonstrated virtually perfect predictions for the nomogram. Conversely, the ANN underestimated the observed rate of prostate cancer. CONCLUSIONS: A 4% increase in predictive accuracy implies that the use of the nomogram instead of the ANN will result in 40 additional patients who will be correctly classified between benign and cancer.     

Chronic subdural hematoma in children

Chronic subdural hematoma (CSH) is generally a disease affecting the elderly and infants. In infants, the process is particularly confusing and frequently misunderstood. In the pediatric population, CSH is just one of a group of sometimes related conditions known as extracerebral fluid collections. In the past, extracerebral fluid collections, in general, and CSHs, in particular, have been inaccurately or incompletely described. Modern neuroimaging techniques, however, have greatly advanced our understanding of these conditions. Surprisingly little literature exists on the subject, and publications before the advent of modern computed tomography and magnetic resonance imaging should be interpreted with caution.     

Independent predictors of recurrence of chronic subdural hematoma: results of multivariate analysis performed using a logistic regression model

OBJECT: The authors attempted to determine independent predictors that contribute to the recurrence of chronic subdural hematoma (CSDH). METHODS: A total of 105 consecutive patients who underwent surgery for CSDH were included in this study. Eleven patients underwent a repeated operation because the CSDH recurred. Univariate and multivariate analyses were performed to assess the relationships among various variables and CSDH recurrence. Finally, four variables were found to be independently associated with the recurrence of CSDH: 1) absence of a multiplicity of hematoma cavities on CT scans; 2) presence of a history of seizure; 3) width of the hematoma; and 4) absence of a history of diabetes mellitus (DM). CONCLUSIONS: As previously reported, the width of the hematoma is related to the incidence of CSDH recurrence. In this study, the lack of a multiplicity of hematoma cavities was the favorite predictor of CSDH recurrence. In addition, histories of seizure and no past DM are closely related to the incidence of CSDH recurrence.     

去势抵抗性前列腺癌人工神经网络预后预测模型的建立及其准确性分析

目的试图建立去势抵抗性前列腺癌（CRPC）患者预后预测模型,并评估其准确性。方法回顾分析2007年1月至2012年1月在中山大学附属第三医院就诊的去势抵抗性前列腺癌病例,收集入组时年龄、基线PSA值、PSA倍增时间、血红蛋白、碱性磷酸酶、白蛋白、是否采用多西他赛三周化疗方案治疗等因素,运用Cox单因素分析筛选潜在预后预测变量后,分别以Cox多因素回归分析与部分指数回归人工神经网络建立预后预测模型,以ROC曲线下面积评估模型准确性。结果Cox多因素回归模型的ROC曲线下面积为0．69,部分指数回归人工神经网络模型ROC曲线下面积为0．84。结论通过部分指数人工神经网络建立的预后预测模型可以纳入不符合比例风险假定的临床数据,改善预测准确度,较好的预测去势抵抗性前列腺癌患者的预后情况。     

Comparison of artificial neural network and logistic regression models for predicting mortality in elderly patients with hip fracture

Purpose

Older patients with hip fracture have a mortality rate one year after surgery of 20-30%. The purpose of this study is to establish a predictive model to assess the outcome of surgical treatment in older patients with hip fracture.

Methods

A database of information from 286 consecutive cases of surgery for hip fracture from the Department of Orthopedics, National Taiwan University Hospital Yun-Lin Branch, was utilised for model building and testing. Both logistic regression and artificial neural network (ANN) models were developed. Cases were randomly assigned to training and testing datasets. A testing dataset was utilised to test the accuracy of both models (n = 89).

Results

The areas under the receiver operator characteristic curves of both models were utilised to compare predictability and accuracy. The logistic regression training and testing datasets had an area of 0.938 (95% CI: 0.904, 0.972) and 0.784 (95% CI: 0.669, 0.899), respectively, below the 0.998 (95% CI: 0.995, 1.000) and 0.949 (95% CI: 0.857, 1.000) of the final ANN model.

Conclusion

Overall, ANNs have higher predictive ability than logistic regression, perhaps because they are not affected by interactions between factors. They may assist in complex decision making in the clinical setting.     

Internal validation of an artificial neural network for prostate biopsy outcome

Objectives:   To carry out an internal validation of the retrospectively trained artificial neural network (ANN) 'ProstataClass'.
Methods:   A prospectively collected database of 393 patients undergoing 8–12 core prostate biopsy was analyzed. Data of these patients were applied to the online available ANN 'ProstataClass' using the Elecsys total prostate-specific antigen (tPSA) and free PSA (fPSA) assays. Beside the internal validation of the ANN 'ProstataClass' an additional ANN (named as ANN internal validation: ANNiv) only using the 393 prospective patient data was evaluated. The new ANN model was constructed with the MATLAB Neural Network Toolbox. Diagnostic accuracy was evaluated by receiver operator characteristic (ROC) curves comparing the areas under the ROC curves (AUC) and specificities at 90% and 95% sensitivity.
Results:   Within a tPSA range of 1.0–22.8 ng/mL, 229 men (58.3%) had prostate cancer (PCa). tPSA, %fPSA and the number of positive digital rectal examinations (DRE) differed significantly from the cohort of patients of the ANN 'ProstataClass', whereas age and prostate volume were comparable. AUCs for tPSA, %fPSA and the ANN 'ProstataClass' were 0.527, 0.726 and 0.747 ( P  = 0.085 between %fPSA and ANN). The AUC of the ANNiv (0.754) was significantly better compared with %fPSA ( P  = 0.021), whereas the AUC of two ANN models built on external cohorts (0.726 and 0.729) showed no differences to %fPSA and the other ANN models.
Conclusions:   Significant differences of DRE status and %fPSA medians decrease the power of the 'ProstataClass' ANN in the internal validation cohort. The effect of retrospective data evaluation the 'ProstataClass' cohort and prospective fPSA measurement may be responsible for %fPSA differences. All ANN models built with different PSA and fPSA assays performed equally if applied to the two cohorts.     

Chronic subdural hematoma secondary to coagulopathy

Eleven cases of chronic subdural hematoma (CSH) secondary to coagulopathy were experienced in our department in the last 5 years. They were classified into 4 groups, I: secondary to diffuse metastatic carcinomatosis of the bone marrow (4 cases), II: malignant hematological disease (acute lymphocytic leukemia and myelodysplastic syndrome 1 case each), III: postreplacement of cardiac valves or vein graft having been treated with anticoagulants (warfarin) (3 cases) and IV: chronic renal failure after having been hemodialyzed (2 cases). The outcomes were all good in group III, and there was one good outcome in group IV. However, death was the outcome in all the other cases. Conservative treatment (mannitol and steroid for 2 weeks) was carried out in 4 cases, all of which improved clinically with diminished hematoma. In 9 cases, surgical treatment was attempted by means of burr hole irrigation of the hematoma. Two of them developed intracerebral hematoma, and one developed acute brain swelling. In conclusion, treatment of CSH secondary to coagulopathy should be selected as follows. 1. Conservative treatment is to be the first choice, if conditions allow it. 2. Surgery can be performed by burr hole irrigation when indicated. Precautions should be taken not to injure the inner membrane of the hematoma or the brain proper, and the need for slow decompression should be kept in mind.     

Prognostic accuracy of an artificial neural network in patients undergoing radical cystectomy for bladder cancer: a comparison with logistic regression analysis

OBJECTIVE: To compare the prognostic performance of an artificial neural network (ANN) with that of standard logistic regression (LR), in patients undergoing radical cystectomy for bladder cancer. PATIENTS AND METHODS: From February 1982 to February 1994, 369 evaluable patients with non-metastatic bladder cancer had pelvic lymph node dissection and radical cystectomy for either stage Ta-T1 (any grade) tumour not responding to intravesical therapy, with or with no carcinoma in situ, or stage T2-T4 tumour. LR analysis based on 12 variables was used to identify predictors of overall 5-year survival, and the ANN model was developed to predict the same outcome. The LR analysis, based on statistically significant predictors, and the ANN model were the compared for their accuracy in predicting survival. RESULTS: The median age of the patients was 63 years, and overall 201 of them died. The tumour stage and nodal involvement (both P<0.001) were the only statistically independent predictors of overall 5-year survival on LR analysis. Based on these variables, LR had a sensitivity and specificity for predicting survival of 68.4% and 82.8%, respectively; corresponding values for the ANN were 62.7% and 86.1%. For LR and ANN, the positive predictive values were 78.6% and 76.2%, and the negative predictive values were 73.9% and 76.5%, respectively. The index of diagnostic accuracy was 75.9% for LR and 76.4% for ANN. CONCLUSIONS: The ANN accurately predicted the survival of patients undergoing radical cystectomy for bladder cancer and had a prognostic performance comparable with that of LR. As ANNs are based on easy-to-use software that can identify nonlinear interactions between variables, they might become the preferred tool for predicting outcome.     

Identification of severe acute pancreatitis using an artificial neural network

BACKGROUND: The aim of this study was to construct and validate an artificial neural network (ANN) model to identify severe acute pancreatitis (AP) and predict fatal outcome. METHODS: All patients who presented with AP from January 2000 to September 2004 were reviewed. Presentation data on admission and at 48 hours were collected. Acute Physiology and Chronic Health Evaluation (APACHE) II and Glasgow severity (GS) score were calculated. A feed-forward ANN was created and trained to predict development of severe AP and mortality from AP; 25% of the data set was withheld from training and was used to evaluate the accuracy of the ANN. Accuracy of the ANN in predicting severity of AP was compared with APACHE II and GS scores. RESULTS: A total of 664 patients with AP were identified of whom 181 (27.3%) fulfilled the clinical and radiologic criteria for severe pancreatitis and 42 patients died (6.3%). Median APACHE II score at 48 hours was 4 (range, 0 to 23). ANN was more accurate than APACHE II or GS scoring systems at predicting progression to a severe course (P < .05 and P < .01, respectively), predicting development of multiorgan dysfunction syndrome (P < .05 and P < .01) and at predicting death from AP (P < .05). CONCLUSIONS: An ANN was able to predict progression to severe disease, development of organ failure and mortality from acute pancreatitis with considerable accuracy and outperformed other clinical risk scoring systems. Further studies are required to assess its utility in aiding management decisions in patients with AP.     

Chronic subdural hematoma in adult and elderly patients

Chronic subdural hematomas display a wide diversity of features in adults, often simulating other neurologic and psychiatric disease processes. This is particularly problematic in elderly patients, for whom more nonspecific clinical presentations are common. Recognition of these features is the key to early diagnosis in elderly patients, who exhibit a markedly increased incidence of this disease. Prompt diagnosis prevents delays that may lead to increased morbidity in these patients.     

Chronic subdural hematoma mimicking transient ischemic attacks

A case is reported in which a chronic subdural hematoma caused recurrent episodes of neurologic dysfunction that simulated transient ischemic attacks. Possible pathophysiological mechanisms are: a subdural hematoma could cause local ischemia or focal epileptic discharges; a cerebral mass could cause cortical depression by mechanical stimulation; regional cerebral edema could cause vascular displacement and ischemia; or small repeated hemorrhages could cause transient neurologic deficits. Computer assisted tomography of the head is recommended in the differentiation of the two conditions.