Cruciate paralysis, hypothesis for injury and recovery.

STUDY DESIGN: Case report and review of the literature. OBJECTIVES: Discuss a case of cruciate paralysis, a review of the literature and the hypotheses regarding the pathogenesis and recovery in spinal cord injuries that cause disproportionate weakness of the upper extremities. SETTING: Thomas Jefferson University Hospital, Philadelphia, PA, USA. METHODS: Case report. RESULTS: A case of cruciate paralysis is presented involving a 59-year-old female who experienced a gunshot wound to the face. Initial motor exams revealed mild lower limb weakness and absent upper limb function with an upper limb modified American Spinal Injury Association motor score of 0/50 (a modified impairment scale using half point muscle grades). Spinal imaging revealed fractures of the C1 anterior ring and the odontoid process, both associated with multiple bullet fragments. No spinal surgery was performed and she was placed in halo fixation. By 3 weeks she had regained enough upper limb function to manipulate large objects with her left hand and move her right hand. At that time, her upper limb ASIA score was 16/50. By 5 weeks, her upper limb modified ASIA motor score had improved to 31.5/50 and she began manipulating feeding utensils, writing legibly, and brushing her teeth with her left hand. CONCLUSIONS: In this case report we present a patient's motor and functional recovery. We also discuss the hypothesis that the acute central cord syndrome and cruciate paralysis are a likely result of similar pathologic mechanisms and that good functional outcome resulted from an initially disabling trauma.

Improved statistical classification methods in computerized psychiatric diagnosis.

BACKGROUND: Mainstream psychiatric diagnosis involves mainly sequential, expert-system-derived, logical decision rules. Among the few statistical classification methods that have been sporadically evaluated are Bayes, k-nearest neighbor, and discriminant analysis classifiers. METHODS: A statistical classification method based on artificial neural networks (ANN) with task-specific constrained architectures was applied to a sample of 796 clinical interviews, where the symptom evaluation and the diagnostic judgments were made using the Psychiatric State Examination (PSE) system. The proposed constrained ANN (CANN) method was compared with other statistical classification methods. RESULTS: CANN was found to be superior to all other considered methods, having an overall "correct" classification rate of 80% when applied to test data. Similarly, the concordance coefficients of agreement with the PSE diagnostic categories were all very high. Among the other used methods, discriminant analysis had slightly inferior performance but better generalization capability. CONCLUSIONS: The proposed CANN method has a definite utility in psychiatric diagnosis and requires further evaluation, perhaps alongside other standard classification systems and/or with larger samples.