Prediction of dynamic tendon forces from electromyographic signals: an artificial neural network approach

Artificial neural networks (ANN) with a backpropagation algorithm were used to predict dynamic tendon forces from electromyographic (EMG) signals. To achieve this goal, tendon forces and EMG-signals were recorded simultaneously in the gastrocnemius muscle of three cats while walking and trotting at different speeds on a motor-driven treadmill. The quality of the tendon force predictions were evaluated for three levels of generalization. First, at the intrasession level, tendon force predictions were made for step cycles from the same experimental session as the step cycles which were used to train the ANN. At this level of generalization very good results were obtained. Second, at the intrasubject level, tendon force predictions were made for one cat walking at a given speed while the ANN was trained with data from the same animal walking at different speeds. For the intrasubject predictions, the quality of the results depended on the walking speed for which the predictions were made: for the speeds at the low and high extremes, the predictions were worse than for the intermediate speeds. The cross-correlation coefficients between predicted and actual force time histories ranged from 0.78 to 0.91. Third, at the intersubject level, tendon forces were predicted for one animal walking at a given speed while the ANN was trained with data from the remaining two animals walking at the corresponding speed. The cross-correlation coefficients between predicted and actual force time histories ranged from 0.72 to 0.98. It was concluded that the ANN-approach is a powerful technique to predict dynamic tendon forces from EMG-signals.     

Pharyngeal wall vibration detection using an artificial neural network

OBJECTIVES: To assess the likelihood of health care legislation in the forthcoming 105th Congress in 5 areas: health care coverage, tax and Employee Retirement Income Security Act (ERISA) policy, Medicaid, Medicare, and managed care. DESIGN: Informal, semistructured conversations that took place in the months prior to the 1996 elections. POPULATION: Congressional health staff and administration officials. OUTCOME MEASURES: Unofficial, off-the-record personal opinions. RESULTS: Health care coverage initiatives to benefit children and unemployed persons are likely to be proposed, but have little chance of enactment; children are seen as well provided for under current Medicaid law, the strong economy and high employment levels lower concern for unemployed issues, and the effort required to pass the Kassebaum-Kennedy legislation needs time to settle. Tax proposals, such as medical savings accounts (MSAs), and ERISA amendments have no constituency; also, the MSA demonstration in Kassebaum-Kennedy will forestall further action. Medicaid is far less an issue than in the previous Congress, because spending has fallen unexpectedly, the bitter fight over block grants makes them unlikely to be revisited, and the administration is likely to enhance state flexibility through waivers. Medicare will be the subject of substantial action to defer impending insolvency temporarily, but there is virtually no chance that definitive long-term solutions will be enacted even though the underlying fiscal problems are thoroughly understood and recognized. Managed care will be the venue for numerous proposals designed to address specific consumer and quality issues. CONCLUSIONS: Four bitter years of fighting over health care issues has raised awareness of the problems, but has produced a political chemistry that is too rancorous to permit passage of significant legislation in the near future.     

Are subjective clinical findings and objective clinical tests related to the motion characteristics of low back pain subjects?

OBJECTIVE: Examine the association between county occupational structure, public expenditures, services availability, prevalence of risk factors, and coronary mortality rates, for 1980-1994, in Washington state. DESIGN: Washington's 39 counties were classified into three occupational structure categories: counties with the lowest percentages of the labor force in managerial, professional, and technical occupations were classified in category I; counties with the highest percentages were in category III. Directly age-adjusted coronary heart disease (CHD) mortality rates, aged 35-64 years, (from vital statistics and Census data), per capita expenditures (Washington Department of Revenue data), per capita services (U.S. Statistical Abstracts data), and the prevalence of CHD risk factors (BRFSS data) were calculated for each occupational structure category. RESULTS: CHD mortality rates and the prevalence of risk factors were inversely associated with occupational structure. Per capita expenditures for health, social, and employment services were 2.2 times, and for schools and recreation were 1.4 times higher in category III vs. I counties. Per capita numbers of child care, job training, employment services, exercise facilities, schools, and medical services were 1.5-6.4 times greater in category III vs. I counties. CONCLUSIONS: Strategies to improve community living conditions and decrease economic disparities between counties may be important to decrease geographic differences in premature CHD mortality.     

Prediction of electrical resistivity of steel using artificial neural network

Electrical resistivity of commercially produced plain carbon manganese steel has been experimentally measured at room temperature (28–30°C) using four-probe method. Resulting data were used to generate both regression based and artificial neural network-based models for prediction of electrical resistivity from the chemical composition of steel. It was found that both models were capable of predicting the resistivity within ±5% error band. Analysis of data also indicated carbon to be the most influential element to increase resistivity followed by manganese and silicon. A comprehensive literature review indicates no such advanced resistivity prediction model is available in the public literature for commercially produced steel with wide variation in carbon content (0.03?0.85?wt-%), manganese content (0.35–1.50?wt-%) and silicon content (0.015–0.90?wt-%).     

Clinical evaluation of low back pain

To properly diagnose and treat low back pain, a thorough history and physical examination are the cornerstones. The most important diagnoses for the physician to be aware of are cauda equina syndrome, back strain, herniated disc, stenosis, and spondylolisthesis.     

Conservative management of low back pain

The importance of using appropriate conservative care in the management of low back pain has been increasingly stressed in recent years, initially as a backlash to the many failures following surgical intervention (particularly repeated surgeries), and, more recently, as a means of controlling health care costs and instituting patient-centered systems of care. It is difficult to define and determine just what "appropriate conservative care" is and should be. Perhaps even more important in this current era of health care reform is the question of who makes this determination.     

Epidemiology of occupational low back pain

Lack of awareness of mental disorder in schizophrenia has been increasingly identified by researchers during recent years due to a resurgence of interest in the subject. In addition, better measurement methods have led to more valid and detailed investigations on insight in schizophrenia. Poor insight has been reported as a common phenomenon which may have both nosological and prognostic value. Specifically, due to recent studies indicating that lack of insight in schizophrenia may lead to poor treatment outcome, research focused on this phenomenon could lead to increasingly effective and efficient treatment strategies. However, many past and present studies reporting a correlation between insight and outcome in schizophrenia demonstrate significant theoretical or methodological limitations which may limit the implications and generalization of findings. This article lists and critically analyzes historical and contemporary research focusing on insight, illness, and outcome in schizophrenia. The role of insight is outlined, as are current methods for assessing awareness of mental disorder in schizophrenia. Cumulative research in this area is then reviewed, in terms of hypotheses, methods, conclusions, and limitations. Finally, suggestions for future research in this area are delineated.     

Sacral insufficiency fractures: an unsuspected cause of low back pain

We describe 10 cases of sacral fractures diagnosed within the rheumatology department at Southend Hospital over the last 5 yr. All presented with sudden-onset low back pain. The majority were elderly, frail, with chronic inflammatory disease (six with rheumatoid arthritis, one with polymyalgia rheumatica, one with vasculitis) and had received steroids. Diagnosis was delayed by the inability of plain radiographs to show these fractures and was ultimately demonstrated by technetium scintigraphy/computed tomography scan. We feel that this diagnosis should be considered in elderly patients with rheumatoid arthritis or other risk factors for osteoporosis who present with low back pain and sacral tenderness. Further clues may be parasymphyseal tenderness (suggesting associated pubic ramus fracture), elevated alkaline phosphatase and plain radiograph showing pubic ramus fractures or parasymphyseal sclerosis. Patients with this complication generally have a poor prognosis and two of our patients have died. Seven required in-patient stay (mean 20 days; range 14-41). The mortality, morbidity and costs incurred in management may be comparable to those of femoral neck fractures.     

Empirically derived MMPI profile clusters and characteristics of low back pain patients.

Analysis of the MMPI scores of 401 low-back-pain patients (average age 45 yrs) by a multivariate clustering procedure produced 5 homogeneous subgroups. Three groups with elevated MMPI profiles and 2 unelevated groups showed differences in age, employment, marital status, pretreatment pain intensity, and activity limitations. Follow-up comparisons at 6-mo and 1-yr intervals revealed that the elevated subgroups had a poorer response to treatment. (8 ref) (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

The surgical treatment of low back pain

If nonoperative management fails to relieve a clearly identifiable and surgically treatable cause of lumbar pain, then surgery may be beneficial. Certain "red flags" indicate the need for urgent or emergent surgical intervention. Low back pain is associated with several degenerative conditions in the lumbar spine, including degenerative disc disease, spinal stenosis, spondylolisthesis, degenerative scoliosis, facet joint syndrome, and disc herniation.     

Role of chaos in trial-and-error problem solving by an artificial neural network

The effect of heparin as a reversing agent of multidrug resistance (MDR) was tested on normal mononuclear cells from 24 healthy volunteers and leukaemic cells from 12 acute myeloid leukaemia, five chronic myeloid leukaemia, five acute lymphoid leukaemia and three chronic lymphoid leukaemia patients. Two cell lines were used as controls, the human erythroleukaemia K562 and its vincristine-resistant derivative K562-Lucena 1. Heparin was not cytotoxic by itself as determined using a MTT assay and cell counts. MDR modulation was assessed by Rhodamine 123 extrusion using flow-cytometry. Modulation of the resistant cell line was produced by the classical reversing agent verapamil and also by heparin, the same being observed in normal and leukaemic cells and being independent of the type of leukaemia. Our work suggests that heparin may be considered a potential MDR modulator.     

Chronic low back pain: Toward an integrated psychosocial assessment model.

Reports on the integration of 6 dimensions of chronic low back pain to provide a multidimensional profile of the patient. These dimensions were pain intensity, functional disability, attitudes toward pain, pain coping strategies, depression, and illness behavior. Cluster analysis of the data obtained from 100 patients with chronic low back pain revealed the presence of 3 distinct patient groups: patients who were in control, patients who were depressed and disabled, and patients who were active copers with high denial. The validity of these clusters was supported by significance testing on several external variables. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Quantitation of grey matter, white matter, and cerebrospinal fluid from spin-echo magnetic resonance images using an artificial neural network technique

An operator independent technique has been developed to quantitate the volume of white matter (WM), grey matter (GM), and cerebrospinal fluid (CSF) using spin-echo magnetic resonance images. Using skull stripped spin-echo images, CSF was removed using an automated thresholding technique. The bimodal histogram of the remaining images was used to train a perceptron and a single hidden layer neural network to output the percentage of GM and WM in the image. The output values were compared with those of a semiautomated technique employing a least square fitting technique [graduated nonconvexity algorithm (GNC)] applied to the bimodal histogram. This semiautomated technique allowed for intervention by the radiologist. Fourteen normal volunteers with eight contiguous slices each were analyzed. The individual percentages of WM, GM, and CSF of 40 slices from five subjects not used in the training set as well as the total percentages of GM, WM, and CSF in each individual were predicted using the two artificial network architectures. GM, WM, and CSF percentages were predicted within 7% for individual slices while total percentages of WM, GM, and CSF were computed accurately with an absolute error of less than 5% when compared to the semiautomated technique involving a trained neuroradiologist.     

Identification and management of pregnancy-related low back pain

A nonconcurrent prospective study was done on the relationship between a number of variables and the progression to AIDS among persons diagnosed with the human immunodeficiency virus (HIV). The variables included sociodemographic ones, behavioral ones, and, most importantly, those persons' difficulties in obtaining public health services for HIV/AIDS. The course of the infection was monitored from the first to the last visit to the health services by means of an individual, diagnostic-based classification, using categories established in 1993 by the Centers for Disease Control and Prevention of the United States of America. Participating in the study were 758 patients seen between 1989 and 1992 in the public AIDS referral services of the city of Belo Horizonte (Minas Gerais). All the persons had been diagnosed with HIV and classified in a pre-AIDS stage. Both the patients who developed AIDS during the study as well as those who did not were assessed according to the selected study characteristics. During the study period, 39.5% of the patients developed AIDS. For the group as a whole, the median time without AIDS was 32.4 months. Multivariate analysis showed that the patients who had less risk of developing AIDS were those who had had fewer than 8.8 medical consultations per year (relative risk = 0.36; 95% confidence interval, 0.26 to 0.50) and an interval of at least 6 months between consultations (RR = 0.37; 95% CI, 0.25 to 0.55). The risk was greater in patients age 30 and older (RR = 1.37; 95% CI, 1.03 to 1.84), in those who were not treated with zidovudine (AZT) (RR = 1.91; 95% CI, 1.37 to 2.64), and those who were initially classified in stage "B" of the disease (RR = 4.83; 95% CI, 3.59 to 6.48). The results of this investigation show the dynamics of the supply and demand of services by these patients, and the information will be useful in planning and organizing care for persons with HIV. Recommendations include giving priority to early intervention with a focus on ongoing outpatient care, and more study of the process that persons with HIV follow in seeking and obtaining health care.     

Meteorological conditions and self-report of low back pain

STUDY DESIGN: Six months of daily low back pain ratings for 94 individuals were tested for the influence of prevailing weather conditions during the spring, summer, and fall seasons. Intergroup differences were tested for study participants who reported weather sensitivity and for those who did not. OBJECTIVES: To investigate the relation between pain ratings and prevailing weather conditions in a population with chronic or recurrent low back pain. SUMMARY OF BACKGROUND DATA: Weather conditions have been reported to influence pain perception in some disease states, including low back pain. Investigations of this relation in chronic or recurrent low back pain have involved varied methodologies, and conflicting results have been reported. METHODS: The effects of eight weather variables reported to influence musculoskeletal pain were tested on daily pain ratings. A post hoc weather sensitivity questionnaire was used to disperse 73 individuals into groups based on perceived weather sensitivity, and group differences were tested. RESULTS: Significant effects on pain scores were found, most notably for temperature and vapor pressure. The magnitude of the effects were small compared with autocorrelation of an individual's own pain scores. Significant differences were found between the group of individuals who were insensitive to weather conditions and that of individuals with perceived sensitivity to cold temperatures. No significant intergroup differences were found for damp, rainy conditions or changes in barometric pressure. CONCLUSIONS: Weather conditions may influence subjective reporting of low back pain significantly. Although the effects are small in magnitude, they should be considered in clinical treatment of the patient with chronic, nonspecific low back pain. Pain scores may demonstrate greater interaction with certain weather conditions in individuals perceiving sensitivity to those conditions.     

Five-year follow-up study of a controlled clinical trial using light mobilization and an informative approach to low back pain

STUDY DESIGN: A controlled clinical trial. OBJECTIVES: To examine the long-term effect of an informative approach to low back pain. SUMMARY OF BACKGROUND DATA: In management and prevention of low back pain, back school based on an ergonomic approach have played in important role. The effect of such informative interventions is not clear. METHODS: A 5-year follow-up study was done on patients included in a previous study. The outcome was measured by return to work or still on sick leave. The patients were allocated to an intervention group (n = 245) and a control group (n = 244). Only the intervention group was called in for examination and intervention and answered a battery of tests for psychological and health factors. The intervention apart from the clinical examination consisted of education in an "mini back school." The program was based on a new medical model for low back pain. RESULTS: Forty-seven (19%) of the patients in the intervention group, compared with 84 patients (34%) in the control group, were still on sick leave after 5 years (P < 0.001). There were fewer recurrences of sick leave (P < 0.03) in the intervention group than in the control group. Based on Internal Health Locus of Control, number of children, and income, 75% were correctly classified as nonreturners in the intervention group. CONCLUSIONS: This study indicates that subchronic low back pain may be managed successfully with an approach that includes clinical examination combined with information for patients about the nature of the problem, provided in a manner designed to reduce fear and give them reason to resume light activity.