Biomedical subjects

Mattias Ohlsson

Publications and source records attributed to Mattias Ohlsson.

At least 19 recordsLinked to original sources

PubMed2007

Automated interpretation of PET/CT images in patients with lung cancer.

PURPOSE: To develop a completely automated method based on image processing techniques and artificial neural networks for the interpretation of combined [(18)F]fluorodeoxyglucose (FDG) positron emission tomography (PET) and computed tomography (CT) images for the diagnosis and staging of lung cancer. METHODS: A total of 87 patients who underwent PET/CT examinations due to suspected lung cancer comprised the training group. The test group consisted of PET/CT images from 49 patients suspected with lung cancer. The consensus interpretations by two experienced physicians were used as the 'gold standard' image interpretation. The training group was used in the development of the automated method. The image processing techniques included algorithms for segmentation of the lungs based on the CT images and detection of lesions in the PET images. Lung boundaries from the CT images were used for localization of lesions in the PET images in the feature extraction process. Eight features from each examination were used as inputs to artificial neural networks trained to classify the images. Thereafter, the performance of the network was evaluated in the test set. RESULTS: The performance of the automated method measured as the area under the receiver operating characteristic curve, was 0.97 in the test group, with an accuracy of 92%. The sensitivity was 86% at a specificity of 100%. CONCLUSIONS: A completely automated method using artificial neural networks can be used to detect lung cancer with such a high accuracy that the application as a clinical decision support tool appears to have significant potential.

Adult↗

PubMed2006

Gene expression profilers and conventional clinical markers to predict distant recurrences for premenopausal breast cancer patients after adjuvant chemotherapy.

A large proportion of breast cancer patients are treated with adjuvant chemotherapy after the primary operation, but some will recur in spite of this treatment. In order to achieve an improved and more individualised therapy, our knowledge in mechanisms for drug resistance needs to be increased. We have investigated to what extent cDNA microarray measurements could distinguish the likelihood of recurrences after adjuvant CMF (cyclophosphamide, methotrexate and 5-fluorouracil) treatment of premenopausal, lymph node positive breast cancer patients, and have also compared this with the corresponding performance when using conventional clinical variables. We tried several gene selection strategies, and built classifiers using the resulting gene lists. The best performing classifier with odds ratio (OR)=6.5 (95% confidence interval (CI)=1.4-62) did not outperform corresponding classifiers based on clinical variables. For the clinical variables, calibrated on the samples, either using all the clinical parameters or the Nottingham Prognostic Index (NPI) parameters, the areas under the receiver operating characteristics (ROC) curve were 0.78 and 0.79, respectively. The ORs at 90% sensitivity were 15 (95% CI=3.1-140) and 10 (95% CI=2.1-97), respectively. Our data have provided evidence for a comparable prediction of clinical outcome in CMF-treated breast cancer patients using conventional clinical variables and gene expression based markers.

Adult↗

PubMed2006

Comparison between neural networks and multiple logistic regression to predict acute coronary syndrome in the emergency room.

OBJECTIVE: Patients with suspicion of acute coronary syndrome (ACS) are difficult to diagnose and they represent a very heterogeneous group. Some require immediate treatment while others, with only minor disorders, may be sent home. Detecting ACS patients using a machine learning approach would be advantageous in many situations. METHODS AND MATERIALS: Artificial neural network (ANN) ensembles and logistic regression models were trained on data from 634 patients presenting an emergency department with chest pain. Only data immediately available at patient presentation were used, including electrocardiogram (ECG) data. The models were analyzed using receiver operating characteristics (ROC) curve analysis, calibration assessments, inter- and intra-method variations. Effective odds ratios for the ANN ensembles were compared with the odds ratios obtained from the logistic model. RESULTS: The ANN ensemble approach together with ECG data preprocessed using principal component analysis resulted in an area under the ROC curve of 80%. At the sensitivity of 95% the specificity was 41%, corresponding to a negative predictive value of 97%, given the ACS prevalence of 21%. Adding clinical data available at presentation did not improve the ANN ensemble performance. Using the area under the ROC curve and model calibration as measures of performance we found an advantage using the ANN ensemble models compared to the logistic regression models. CONCLUSION: Clinically, a prediction model of the present type, combined with the judgment of trained emergency department personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.

Acute Disease↗

PubMed2006

A simple statistical model for prediction of acute coronary syndrome in chest pain patients in the emergency department.

BACKGROUND: Several models for prediction of acute coronary syndrome (ACS) among chest pain patients in the emergency department (ED) have been presented, but many models predict only the likelihood of acute myocardial infarction, or include a large number of variables, which make them less than optimal for implementation at a busy ED. We report here a simple statistical model for ACS prediction that could be used in routine care at a busy ED. METHODS: Multivariable analysis and logistic regression were used on data from 634 ED visits for chest pain. Only data immediately available at patient presentation were used. To make ACS prediction stable and the model useful for personnel inexperienced in electrocardiogram (ECG) reading, simple ECG data suitable for computerized reading were included. RESULTS: Besides ECG, eight variables were found to be important for ACS prediction, and included in the model: age, chest discomfort at presentation, symptom duration and previous hypertension, angina pectoris, AMI, congestive heart failure or PCI/CABG. At an ACS prevalence of 21% and a set sensitivity of 95%, the negative predictive value of the model was 96%. CONCLUSION: The present prediction model, combined with the clinical judgment of ED personnel, could be useful for the early discharge of chest pain patients in populations with a low prevalence of ACS.

Acute Disease↗

PubMed2006

Risk factor identification and mortality prediction in cardiac surgery using artificial neural networks.

OBJECTIVE: The artificial neural network model is a nonlinear technology useful for complex pattern recognition problems. This study aimed to develop a method to select risk variables and predict mortality after cardiac surgery by using artificial neural networks. METHODS: Prospectively collected data from 18,362 patients undergoing cardiac surgery at 128 European institutions in 1995 (the European System for Cardiac Operative Risk Evaluation database) were used. Models to predict the operative mortality were constructed using artificial neural networks. For calibration a sixfold cross-validation technique was used, and for testing a fourfold cross-testing was performed. Risk variables were ranked and minimized in number by calibrated artificial neural networks. Mortality prediction with 95% confidence limits for each patient was obtained by the bootstrap technique. The area under the receiver operating characteristics curve was used as a quantitative measure of the ability to distinguish between survivors and nonsurvivors. Subgroup analysis of surgical operation categories was performed. The results were compared with those from logistic European System for Cardiac Operative Risk Evaluation analysis. RESULTS: The operative mortality was 4.9%. Artificial neural networks selected 34 of the total 72 risk variables as relevant for mortality prediction. The receiver operating characteristics area for artificial neural networks (0.81) was larger than the logistic European System for Cardiac Operative Risk Evaluation model (0.79; P = .0001). For different surgical operation categories, there were no differences in the discriminatory power for the artificial neural networks (P = .15) but significant differences were found for the logistic European System for Cardiac Operative Risk Evaluation (P = .0072). CONCLUSIONS: Risk factors in a ranked order contributing to the mortality prediction were identified. A minimal set of risk variables achieving a superior mortality prediction was defined. The artificial neural network model is applicable independent of the cardiac surgical procedure.

Adolescent↗

PubMed2006

A new computer-based decision-support system for the interpretation of bone scans.

OBJECTIVE: To develop a completely automated method, based on image processing techniques and artificial neural networks, for the interpretation of bone scans regarding the presence or absence of metastases. METHODS: A total of 200 patients, all of whom had the diagnosis of breast or prostate cancer and had undergone bone scintigraphy, were studied retrospectively. Whole-body images, anterior and posterior, were obtained after injection of 99mTc-methylene diphosphonate. The study material was randomly divided into a training group and a test group, with 100 patients in each group. The training group was used in the process of developing the image analysis techniques and to train the artificial neural networks. The test group was used to evaluate the automated method. The image processing techniques included algorithms for segmentation of the head, chest, spine, pelvis and bladder, automatic thresholding and detection of hot spots. Fourteen features from each examination were used as input to artificial neural networks trained to classify the images. The interpretations by an experienced physician were used as the 'gold standard'. RESULTS: The automated method correctly identified 28 of the 31 patients with metastases in the test group, i.e., a sensitivity of 90%. A false positive classification of metastases was made in 18 of the 69 patients not classified as having metastases by the experienced physician, resulting in a specificity of 74%. CONCLUSION: A completely automated method can be used to detect metastases in bone scans. Future developments in this field may lead to clinically valuable decision-support tools.

Adult↗

PubMed2006

Patient gender and radiopharmaceutical tracer is of minor importance for the interpretation of myocardial perfusion images using an artificial neural network.

The purpose of this study was to assess the influence of patient gender and choice of perfusion tracer on computer-based interpretation of myocardial perfusion images. For the image interpretation, an automated method was used based on image processing and artificial neural network techniques. A total of 1000 patients were studied, all referred to the Royal Brompton Hospital in London for myocardial perfusion scintigraphy over a period of 1 year. The patients were randomized to receive either thallium or one of the two technetium tracers, methoxyisobutylisonitrile or tetrofosmin. Artificial neural networks were trained with either mixed gender or gender-specific and mixed tracer or tracer-specific training sets of different sizes. The performance of the networks was assessed in separate test sets, with the interpretation of experienced physicians regarding the presence or absence of fixed or reversible defects in the images as the gold standard. The neural networks trained with large mixed gender training sets were as good as the networks trained with gender-specific data sets. In addition, the neural networks trained with large mixed tracer training sets were as good as or better than the networks trained with tracer-specific data sets. Our results indicate that the influence of patient gender and perfusion tracer are of minor importance for the computer-based interpretation of the myocardial perfusion images. The differences that occur can be compensated for by larger training sets.

Adult↗

PubMed2006

Decision support for the initial triage of patients with acute coronary syndromes.

Early revascularization of acute coronary syndromes improves the prognosis. It is of vital importance that the decision to treat the patient is taken as early as possible. The aim of this study was (i) to develop an automated tool for the analysis of electrocardiograms (ECGs) with regard to changes that indicate possible transmural ischaemia and (ii) to assess the influence of the tool on the ECG classifications of three interns with less than 12 months of experience in ECG reading. An artificial neural network was trained to automatically interpret ECGs using 3000 ECGs recorded at an emergency department. Thereafter, the performance of the network was evaluated using 1000 test ECGs. In the second step, three interns classified these test ECGs twice on different occasions, with and without the advice of the neural network. The gold standard was the classification made by two experienced cardiologists. On average, the three interns showed a sensitivity of 68% at a specificity of 92% without the advice of the neural network and a sensitivity of 93% at a specificity of 87% with the advice. The neural network itself showed a sensitivity of 95% at a specificity of 88%. The increase in sensitivity of 23-26% was significant (P<0.001) for all three interns. In conclusion, an artificial neural network can be trained to the improve performance in the interpretation of ST-segment changes in accordance with that of the experienced cardiologists.

Automation↗

PubMed2006

The added value of ECG-gating for the diagnosis of myocardial infarction using myocardial perfusion scintigraphy and artificial neural networks.

To assess the value of ECG-gating for the diagnosis of myocardial infarction using myocardial perfusion scintigraphy (MPS) and an artificial neural network. A total of 422 patients referred for MPS were studied using a one day (99m)Tc-tetrofosmin protocol. Adenosine stress combined with submaximal dynamic exercise was used. The images were interpreted by one of three experienced clinicians and these interpretations regarding the presence or absence of myocardial infarction were used as the standard. A fully automated method using artificial neural networks was compared with the clinical interpretation. Either perfusion data alone or a combination of perfusion and function from ECG-gated images were used as input to different artificial neural networks. After a training session, the two types of neural networks were evaluated in separate test groups using an eightfold cross-validation procedure. The neural networks trained with both perfusion and ECG-gated images had a 4-7% higher specificity compared with the corresponding networks using perfusion data only, in four of five segments compared at the same level of sensitivity. The greatest improvement in specificity, from 70% to 77%, was seen in the inferior segment. In the septal and lateral segments the specificity rose from 73% to 77% and from 81% to 85%, respectively. In the anterior segment, the increase in specificity from 93% to 94% by adding functional data was not significant. The addition of functional information from ECG-gated MPS is of value for the diagnosis of myocardial infarction using an automated method of interpreting myocardial perfusion images.

Adenosine↗

PubMed2005

Toward personal eHealth in cardiology. Results from the EPI-MEDICS telemedicine project.

Despite many attempts to improve the management of acute myocardial infarction, only small trends to shorter time intervals before treatment have been reported. The self-care solution developed by the European EPI-MEDICS project (2001-2004) is a novel, very affordable, easy-to-use, portable, and intelligent Personal ECG Monitor (PEM) for the early detection of cardiac ischemia and arrhythmia that is able to record a professional-quality, 3-lead electrocardiogram (ECG) based on leads I, II, and V2; derive the missing leads of the standard 12-lead ECG (thanks to either a generic or a patient-specific transform), compare each ECG with a reference ECG by means of advanced neural network-based decision-making methods taking into account the serial ECG measurements and the patient risk factors and clinical data; and generate different levels of alarms and forward the alarm messages with the recorded ECGs and the patient's Personal electronic Health Record (PHR) to the relevant health care providers by means of a standard Bluetooth-enabled, GSM/GPRS-compatible mobile phone. The ECG records are SCP-ECG encoded and stored with the PHR on a secure personal SD Card embedded in the PEM device. The alarm messages and the PHR are XML encoded. Major alarm messages are automatically transmitted to the nearest emergency call center. Medium or minor alarms are sent on demand to a central PEM Alarm Web Server. Health professionals are informed by a Short Message Service. The PEM embeds itself a Web server to facilitate the reviewing and/or update of the PHR during a routine visit at the office of the general physician or cardiologist. Eighty PEM prototypes have been finalized and tested for several weeks on 697 citizens/patients in different clinical and self-care situations involving end users (188 patients), general physicians (10), and cardiologists (9). The clinical evaluation indicates that the EPI-MEDICS concept may save lives and is very valuable for prehospitalization triage.

Allied Health Personnel↗

PubMed2005

Interpretation of captopril renography using artificial neural networks.

The purpose of this study was to develop a method based on artificial neural networks for interpretation of captopril renography tests for the detection of renovascular hypertension caused by renal artery stenosis and to assess the value of different measurements from the test. A total of 250 99mTc-MAG3 captopril renography tests were used in the study. The material was collected from two different patient groups. One group consisted of 101 patients who also had undergone a renal angiography. The angiographies, which were used as gold standard, showed a significant renal artery stenosis in 53 of the 101 cases. The second group consisted of 149 patients, who's captopril renography tests all were interpreted as not compatible with significant renal artery stenosis by an experienced nuclear medicine physician. Artificial neural networks were trained for the diagnosis of renal artery stenosis using eight measures from each renogram. The neural network was then evaluated in separate test groups using an eightfold cross validation procedure. The performance of the neural networks, measured as the area under the receiver operating characteristic curve, was 0.93. The sensitivity was 91% at a specificity of 90%. The lowest performance was found for the network trained without use of a parenchymal transit measure, indicating the importance of this feature. Artificial neural networks can be trained to interpret captopril renography tests for detection of renovascular hypertension caused by renal artery stenosis. The result almost equals that of human experts shown in previous studies.

Angiotensin-Converting Enzyme Inhibitors↗

PubMed2004

Regional cerebral blood flow in Alzheimer's disease: classification and analysis of heterogeneity.

Neural networks have been successfully applied to brain perfusion images to classify patients with Alzheimer's disease from normal or other patient populations. Given the recognition that Alzheimer's disease constitutes a heterogeneous disorder, the identification of subgroups sharing common functional brain deficits would constitute a further improvement in the utility of such methods. Therefore, we aimed to investigate whether neural networks could discriminate cortical perfusion deficits of patients with Alzheimer's disease from normal brain perfusion. A second step was to identify subgroups of patients sharing similar perfusion deficits. The study population consisted of one group of 92 normal healthy subjects and one group of 132 patients with mild-to-moderate Alzheimer's disease. The patients were diagnosed according to established criteria (DSM-IV and NINCDS-ADRDA). Regional cerebral blood flow was assessed by the non-invasive (133)Xe inhalation method, using a 64-detector system for measurements of blood flow in superficial cortical areas. The regional blood flow values were used as the only input to artificial neural networks with multilayer Perceptron architecture. The networks were trained using the back-propagation updating algorithm. A fourfold cross validation procedure was used in order to obtain the most reliable performance of the networks. The performance of the neural network, measured as the area under the receiver-operating characteristic curve, was 0.94, with a sensitivity for Alzheimer's disease of 86% at a specificity of 90%. An analysis of the relative importance of cortical areas in the discrimination showed that left parietal areas were more important than the right homologous ones. A clustering analysis of the Alzheimer patients identified three or four subgroups of patients with clearly different combinations of blood flow pathology. A consistent finding in all subgroups was a significant deficit in temporoparietal blood flow of both hemispheres. Distinct group differences were seen in frontal, central and occipital areas with different combinations of involvement. This is the first study in which neural networks have been applied to brain perfusion images obtained with the (133)Xe inhalation method. The results demonstrate that a classification of patients with Alzheimer's disease obtained with this method is compatible with the best results obtained with other brain imaging methods. The identification of clearly distinguishable patterns of blood flow pathology in subgroups of patients lends further support to the notion that Alzheimer's disease is a heterogeneous disorder.

Adolescent↗

PubMed2004

Detecting acute myocardial infarction in the 12-lead ECG using Hermite expansions and neural networks.

We use artificial neural networks (ANNs) to detect signs of acute myocardial infarction (AMI) in ECGs. The 12-lead ECG is decomposed into Hermite basis functions, and the resulting coefficients are used as inputs to the ANNs. Furthermore, we present a case-based method that qualitatively explains the operation of the ANNs, by showing regions of each ECG critical for ANN response. Key ingredients in this method are: (i) a cost function used to find local ECG perturbations leading to the largest possible change in ANN output and (ii) a minimization scheme for this cost function using mean field annealing. Our approach was tested on 2238 ECGs recorded at an emergency department. The obtained ROC areas for ANNs trained with the Hermite representation and standard ECG measurements were 83.4 and 84.3% (P=0.4), respectively. We believe that the proposed method has potential as a decision support system that can provide good advice for diagnosis, as well as providing the physician with insight into the reason underlying the advice.

Acute Disease↗

PubMed2004

WeAidU-a decision support system for myocardial perfusion images using artificial neural networks.

This paper presents a computer-based decision support system for automated interpretation of diagnostic heart images (called WeAidU), which is made available via the Internet. The system is based on image processing techniques, artificial neural networks (ANNs) and large well-validated medical databases. We present results using artificial neural networks, and compare with two other classification methods, on a retrospective data set containing 1320 images from the clinical routine. The performance of the artificial neural networks detecting infarction and ischemia in different parts of the heart, measured as areas under the receiver operating characteristic curves, is in the range 0.83-0.96. These results indicate a high potential for the tool as a clinical decision support system.

Automation↗

PubMed2004

New paradigms in telemedicine: ambient intelligence, wearable, pervasive and personalized.

After decades of development of information systems dedicated to health professionals, there is an increasing demand for personalized and non-hospital based care. An especially critical domain is cardiology: almost two third of cardiac deaths occur out of hospital, and victims do not survive long enough to benefit from in-hospital treatments. We need to reduce the time before treatment. But symptoms are often interpreted wrongly. The only immediate diagnostic tool to assess the possibility of a cardiac event is the electrocardiogram (ECG). Event and transtelephonic ECG recorders are used to improve decision making but require setting up new infrastructures. The European EPI-MEDICS project has developed an intelligent Personal ECG Monitor (PEM) for the early detection of cardiac events. The PEM embeds advanced decision making techniques, generates different alarm levels and forwards alarm messages to the relevant care providers by means of new generation wireless communication. It is cost saving, involving care provider only if necessary and requiring no specific infrastructure. This solution is a typical example of pervasive computing and ambient intelligence that demonstrates how personalized, wearable, ubiquitous devices could improve healthcare.

Artificial Intelligence↗

PubMed2003

Matching protein structures with fuzzy alignments.

Unraveling functional and ancestral relationships between proteins as well as structure-prediction procedures require powerful protein-alignment methods. A structure-alignment method is presented where the problem is mapped onto a cost function containing both fuzzy (Potts) assignment variables and atomic coordinates. The cost function is minimized by using an iterative scheme, where at each step mean field theory methods at finite "temperatures" are used for determining fuzzy assignment variables followed by exact translation and rotation of atomic coordinates weighted by their corresponding fuzzy assignment variables. The approach performs very well when compared with other methods, requires modest central processing unit consumption, and is robust with respect to choice of iteration parameters for a wide range of proteins.

Algorithms↗

PubMed2003

Role of ventilation scintigraphy in diagnosis of acute pulmonary embolism: an evaluation using artificial neural networks.

The purpose of this study was to assess the value of the ventilation study in the diagnosis of acute pulmonary embolism using a new automated method. Either perfusion scintigrams alone or two different combinations of ventilation/perfusion scintigrams were used as the only source of information regarding pulmonary embolism. A completely automated method based on computerised image processing and artificial neural networks was used for the interpretation. Three artificial neural networks were trained for the diagnosis of pulmonary embolism. Each network was trained with 18 automatically obtained features. Three different sets of features originating from three sets of scintigrams were used. One network was trained using features obtained from each set of perfusion scintigrams, including six projections. The second network was trained using features from each set of (joint) ventilation and perfusion studies in six projections. A third network was trained using features from the perfusion study in six projections combined with a single ventilation image from the posterior view. A total of 1,087 scintigrams from patients with suspected pulmonary embolism were used for network training. The test group consisted of 102 patients who had undergone both scintigraphy and pulmonary angiography. Performances in the test group were measured as area under the receiver operation characteristic curve. The performance of the neural network in interpreting perfusion scintigrams alone was 0.79 (95% confidence limits 0.71-0.86). When one ventilation image (posterior view) was added to the perfusion study, the performance was 0.84 (0.77-0.90). This increase was statistically significant ( P=0.022). The performance increased to 0.87 (0.81-0.93) when all perfusion and ventilation images were used, and the increase in performance from 0.79 to 0.87 was also statistically significant ( P=0.016). The automated method presented here for the interpretation of lung scintigrams shows a significant increase in performance when one or all ventilation images are added to the six perfusion images. Thus, the ventilation study has a significant role in the diagnosis of acute lung embolism.

Adolescent↗

PubMed2003

Pervasive self-care solutions in telecardiology. Typical use cases from the EPI-MEDICS project.

In western countries, heart disease is the main cause of premature death. Most of cardiac deaths occur out of hospital. Because of a continuously growing elderly population, the number of heart attacks is steadily increasing. Symptoms are often interpreted incorrectly. Victims do not survive long enough to benefit from inhospital treatments. To reduce the time before treatment, the only useful diagnostic tool to assess the presence of a cardiac event is the electrocardiogram (ECG). Event and transtelephonic ECG recorders are used to improve decision-making but require setting up new infrastructures. The pervasive solution proposed by the European EPI-MEDICS project is an intelligent Personal ECG Monitor for the early detection of cardiac events. It includes part of the patient electronic health record (EHR), embeds a web server and decision-making techniques, generates different alarm levels and forwards alarm messages to the relevant care providers by means of new generation wireless communication. It is cost saving, involving care providers only if necessary, without requiring to set-up specific infrastructures. Healthcare becomes personalized, wearable and ubiquitous.

Arrhythmias, Cardiac↗