Computer-aided diagnosis and negligence

The phrase 'expert system' has been widely used to describe computer systems which are capable of performing at or near to the level of an expert. Expert systems may be recognized by their construction or by their performance. Structurally, expert systems usually comprise a knowledge-base, an inference engine and an interface with the user as shown in Figure 1. The knowledge-base contains the raw material of the expert system; the rules and facts representing the expertise. An important part of that knowledge-base usually will be heuristic in nature and this is particularly so with respect to expert systems in medicine. A large amount of a specialist's knowledge is informal and experimential in nature and this heuristic knowledge is often what sets the specialist apart from the general practitioner or indeed sets the latter apart from the medical student. The inference engine is a computer program which attempts to resolve the user's enquiries by operating on and interacting with the knowledge-base. Finally, the interface with the user serves two purposes: first, to make the system relatively easy to use and second, and very importantly, to provide an explanation and justification for the results, advice and suggestions obtained from using the system (Winfield, 1982). There will be other parts to an expert system which are used to refine and modify the knowledge-base. The performance of an expert system is of utmost importance and it is the most fundamental test for whether a computer system falls into this classification. d'Agapeyeff (1984) defines expert systems as being: a) programmed to a significant extent, from an explicit representation of empirical human knowledge; b) readable by those who provided the knowledge and, potentially, by similarly knowledgeable users and managers; c) able to provide explanations of their reasoning on demand; d) quickly alterable with (comparatively) low risk of unwanted side effects.' d'Agapeyeff describes the knowledge-base as being empirical, suggesting that it is informal or heuristic knowledge rather than comprising clear and formal rules as written in textbooks. This does not preclude the inclusion of formal knowledge in the expert system but it is clear that heuristic knowledge occupies a key role in the development of expert systems. Much medical knowledge is heuristic in nature; for example, an experienced doctor might use a rule in diagnosis such as: 'If symptoms A and B are observed then C is plausible but certainly not D'. In the field of medicine, expert systems will enable specialist expertise (a rare commodity) to be available to non-specialists such as general practitioners.(ABSTRACT TRUNCATED AT 400 WORDS)     

ICON: a computer-based approach to differential diagnosis in radiology

ICON is a computer-based expert system being developed to help radiologists with the process of differential diagnosis. ICON focuses on the domain of lung disease as seen on a chest radiograph in patients with lymphoproliferative disorders. Rather than attempt to tell the radiologist what the diagnosis is, the system asks him or her to propose a diagnosis and then discusses the evidence supporting that diagnosis or competing diagnoses. The system's output is in the form of an English prose critique. This approach combines the computer's ability to recall detailed information with human reasoning skills     

How sick is the defendant? Forensic and emergency medical aspects at trial

The evaluation of a defendant’s ability to stand trial is a core task in the field of legal medicine as a supportive instrument of jurisprudence. Before the trial, the court-appointed expert informs him-/herself regarding existing somatic and psychological illness(-es) within the context of preparing an expert evaluation, then composing the written expert evaluation, which reflects the condition of the subject at the time of the examination and arrives at an assessment of the ability to stand trial. The decompensation or aggravation of illnesses – in particular in stressful situations, as is to be expected for the defendant in the courtroom – can thus be taken into consideration such that alongside the current evaluation of the defendant’s health condition, emergency medical treatment may also become necessary in court at times. We present three case reports about forensic and emergency medical aspects at trial, considering how the forensic expert can be able to meet the subsequent challenges.     

Ultrasound breast tumor image computer-aided diagnosis with texture and morphological features

RATIONALE AND OBJECTIVES: Computer-aided diagnosis (CAD) systems based on shape analysis have been proved to be highly accurate in evaluating breast tumors. However, it takes considerable time to train the classifier and diagnose breast tumors, because extracting morphologic features require a lot of computation. Hence, to develop a highly accurate and quick CAD system, we combined the texture and morphologic features of ultrasound breast tumor imaging to evaluate breast tumors in this study. MATERIALS AND METHODS: This study evaluated 210 ultrasound breast tumor images, including 120 benign tumors and 90 malignant tumors. The breast tumors were segmented automatically by the level set method. The autocovariance texture features and solidity morphologic feature were extracted, and a support vector machine was used to identify the tumor as benign or malignant. RESULTS: The accuracy of the proposed diagnostic system for classifying breast tumors was 92.86%, the sensitivity was 94.44%, the specificity was 91.67%, the positive predictive value was 89.47%, and the negative predictive value was 95.65%. In addition, the proposed system reduced the training time compared to systems based only on the morphologic analysis. CONCLUSIONS: The CAD system based on texture and morphologic analysis can differentiate benign from malignant breast tumors with high accuracy and short training time. It is therefore clinically useful to reduce the number of biopsies of benign lesions and offer a second reading to assist inexperienced physicians in avoiding misdiagnosis.     

Pneumonie

Pneumonia is a medical entity with currently increasing incidence and has become a major issue in public and private health systems especially as a complication of patients in hospitals and nursing homes. In cases of (fatal) pneumonia with allegations of medical malpractice the forensic expert can rely on precise and well-developed guidelines from different medical associations (S3 level) concerning diagnostic and therapeutic aspects of the disease. Guidelines can serve as control mechanisms for the line of arguments within an expert statement and enhance the scientific accuracy. Furthermore, these guidelines guarantee a certain degree of standardization within a given group of experts. Authoritative epidemiological data concerning morbidity and mortality as well as evidence-based studies have elucidated different spectra of pathogens, diagnostic and therapeutic approaches. These data have demonstrated that a standardized and diligently documented but still individualized risk assessment is crucial for the choice of diagnostic and therapeutic options. Community-acquired (CAP) and hospital-acquired pneumonia (HAP) should be differentiated in the subsequent forensic expertise as differing hygienic and diagnostic requirements will result from this differentiation. A structured forensic expertise with partitions broaching the issues of diagnostic, therapeutic, work organization-related and structural medical malpractice is suggested to enable the expert to identify potential malpractice aspects which are not usually attributable to the responsibility of the accused physician. The forensic expert is confronted with the problem of assessing an individual case on the basis of current scientific evidence which has to be available, reliable, valid, and suitable for the case. Pneumonia as a medical entity with very complex and stratified algorithms concerning diagnostic and therapeutic aspects serves as an ideal example to demonstrate that even with detailed knowledge of the medical literature forensic experts needs to rely on subject-specific experts for a conclusive expertise.     

Grading in soft tissue tumors: principles and problems

Histologic grading has been considered the most important prognostic factor for soft tissue sarcomas. Several grading systems have been proposed based on the assessment of morphologic features in heterogeneous groups of sarcomas. Currently, the French Federation of Cancer Centers (FNCLCC) and the National Cancer Institute (NCI) grading systems are the most commonly used. These systems are based on a few morphologic predictors of biologic behavior, which is justifiable because of the rarity of soft tissue sarcomas. Nonetheless, over- or underestimation of prognosis may occur because of an uneven representation of specific sarcomas with rather distinct biologic behaviors among studies of grading systems. In addition, lack of standardization of morphologic criteria and frequent omission of the influence of clinical factors on the final survival analyses preclude universal acceptance of a particular grading system. New advances in diagnostic imaging, quantitative morphometric technologies, cytogenetics, and molecular genetics, allied with alternative analytic data systems, may provide better validation, reproducibility, and prognostic capabilities for current and future grading systems. This article summarizes and critically analyzes the various important grading systems that have thus far been proposed and suggests alternatives for the elaboration of more reproducible systems with higher predictive capabilities.     

Die Rolle des medizinischen Sachverständigen – gesetzliche Vorgaben und Entscheidungen der Rechtsprechung

There are special circumstances, named by the jurisprudence, when experts can be refused as prejudiced and there is a civil law concerning the liability of medical experts in cases where an incorrect expert opinion was presented. Additionally, every physician working as an expert has to achieve personal requirements, such as strict neutrality and objectiveness. This includes an appropriate appearance in court, but also personal liability insurance and an expert opinion written or presented understandable also for prosecutors, lawers and judges.     

Akute Lungenthrombembolie

Acute pulmonary embolism (PE), e.g. following deep vein thrombosis, is a life-threatening incident. Immediate correct diagnosis of the disease with subsequent initiation of the correct therapy regimen is crucial for the prognosis of affected patients. Allegations of medical malpractice may not only concern missed diagnoses but also initial diagnostic efforts and initiation of a specific therapy. In forensic casework a classical set of symptoms as well as well established and durable diagnostic algorithms and therapy regimen enable the forensic expert to reliably assess the quality of treatment in a given case and derive the necessary conclusions to refute or substantiate a suspected case of medical malpractice. This publication is intended to enable the forensic expert to assess the diagnostic and therapeutic approaches in cases of clinically suspected and autoptically proven acute pulmonary embolism following deep vein thrombosis on the basis of current medical research. Thus it may serve to further implement and strengthen evidence-based aspects in forensic casework.     

A step towards increased understanding by non-scientists of expert reports: recommendations for readability

Communication about forensic science to non-scientists is a key aspect of the role of forensic scientists – and one that poses significant challenges. Police, lawyers, and judges read expert reports written by forensic scientists, and jurors usually have the content of such reports explained to them in court. Readability can be defined as the ease with which something can be read as a function of the way it is written. This paper draws on past studies of the readability of Australian expert reports of DNA analysis and forensic comparison of glass, and conclusions written as part of an international proficiency test of forensic comparison of glass. The purpose of the paper is twofold: (1) to alert scientists to the most common readability issues identified in the studies; and (2) to suggest solutions to these readability issues drawn from theory and past research. The suggested solutions may be helpful to case-reporting scientists in affirming their current practices or in modifying those practices to enhance the readability of their expert reports for non-scientist report readers.     

Do written consent forms provide medicolegal protection from litigation in radiotherapy?

Two methods were used in an attempt to determine whether written consent forms serve a useful medicolegal purpose in Australian radiotherapy departments. First a survey was posted to all practising radiation oncologists to ask about their use of written consent forms and whether they had ever been useful in any claims made against them. Second, the largest medical defence organization in Australia was contacted for de-identified details about every claim ever made against a radiation oncologist. The survey yielded a response rate of 50.3%. Only one respondent indicated that any consent form had ever played a role in any claim and was not prepared to discuss it. Many radiation oncologists did not routinely use a consent form and its use could not be considered standard practice. The submitted consent forms generally did not contain warnings to the patient about specific risks of treatment. The details of the previous claims provided by the medical defence organization indicated that more often claims arose from circumstances in which a written consent form could not provide any useful protection such as radiation dose calculation errors. The medicolegal value of written consent forms in radiotherapy seems low, although further research may be necessary before dispensing with them completely.     

Nicht oder versp?tet diagnostizierte letale Sch?del-Hirn-Traumen

Craniocerebral injury (CCI) including the central nervous system (CNS) and intracranial hemorrhages are well known to be caused by blunt force, either due to e.g. beating or due to a fall. Rapid diagnostic investigations and therapeutic actions are necessary and decisive for the course of disease and sometimes for survival. Delays in the discovery of injuries or those first uncovered by autopsy, such as subdural hematomas, subarachnoidal bleeding and brain contusions can lead to death. In such cases, malpractice charges may arise, especially concerning an unacceptable delay to initiate radiological investigations. Patients under the influence of alcohol are often affected. The following study includes 151 cases of malpractice charges with suspected errors in treatment. Data concerning the patients were collected and the circumstances leading to craniocerebral injury were analyzed as well as the medical measures undertaken. There were 120 cases with craniocerebral injury following falls and 10 cases were found with medical malpractice ascertained by expert opinions and leading to death. The omission of further radiological investigations was criticized by the courts dealing with the accusations as constituting medical negligence.     

Decision support systems in diuresis renography

The volume of diagnostic imaging studies performed in the United States is rapidly increasing resulting from an increase in the number of patients as well as an increase in the volume of studies per patient. Concurrently, the number and complexity of images in each patient data set are also increasing. Nuclear medicine physicians and radiologists are required to master an ever-expanding knowledge base whereas the hours available to master this knowledge base and apply it to specific tasks are steadily shrinking. The convergence of an expanding knowledge base and escalating time constraints increases the likelihood of physician errors. The problem is particularly acute for low-volume studies such as MAG3 diuresis renography where many imagers may have had limited training or experience. To address this problem, renal decision support systems (DSS) are being developed to assist physicians evaluate suspected obstruction in patients referred for diuresis renography. Categories of DSS include neural networks, case-based reasoning, expert systems and statistical systems; RENEX and CART are examples of renal DSS currently in development. RENEX (renal expert) uses a set of rules obtained from human experts to analyze a knowledge base of expanded quantitative parameters obtained from diuresis MAG3 scintigraphy whereas CART (classification and regression tree analysis) is a statistical method that grows and prunes a decision tree based on an analysis of these quantitative parameters in a training data set. RENEX can be queried to provide the reasons for its conclusions. Initial data show that the interpretations provided by RENEX and CART are comparable to the interpretations of a panel of experts blinded to clinical information. This project should serve as a benchmark for the scientific comparison and collaboration of these 2 fields of medical decision-making. Moreover, we anticipate that these DSS will better define the essential interpretative criteria, foster standardized interpretation, teach trainees to better interpret renal scans, enhance diagnostic accuracy and provide a methodology applicable to other diagnostic problems in radiology and medicine.     

ACR Appropriateness Criteria Imaging in the Diagnosis of Thoracic Outlet Syndrome

Thoracic outlet syndrome is a clinical entity characterized by compression of the neurovascular bundle, and may be associated with additional findings such as venous thrombosis, arterial stenosis, or neurologic symptoms. The goal of imaging is to localize the site of compression, the compressing structure, and the compressed organ or vessel, while excluding common mimics. A literature review is provided of current indications for diagnostic imaging, with discussion of potential limitations and benefits of the respective modalities.The ACR Appropriateness Criteria are evidence-based guidelines for specific clinical conditions that are reviewed every 3 years by a multidisciplinary expert panel. The guideline development and review include an extensive analysis of current medical literature from peer-reviewed journals and the application of a well-established consensus methodology (modified Delphi) to rate the appropriateness of imaging and treatment procedures by the panel. In those instances in which evidence is lacking or not definitive, expert opinion may be used to recommend imaging or treatment. In this document, we provided guidelines for use of various imaging modalities for assessment of thoracic outlet syndrome.     

Inference systems for automated image analysis.

The radiodiagnostic process is a complicated activity involving the integration of knowledge from low-level image features into more abstract, higher-order entities. This involves spatial and density information at a lower level and area and features at a higher level. The spatial density distribution in a radiographic image is not uniquely related to the three-dimensional structure of the object. Therefore, more information other than just first-order density characteristics of radiographs must be utilized to improve automated interpretation of the image. Prior knowledge of the size, shape and location of anatomical structures and pathognomic features is very useful for improving the process of computer-aided image analysis. Inference systems as used in expert systems can be applied to facilitate the integration of information obtained from the patient and the radiograph in the diagnostic process.     

Selection system for forensic expert witness and their qualification in Japan

The origin of modern Japanese criminal procedure can be traced back to 1880, when the Code of Criminal Procedure saying that the judge can summon an expert to make an expert opinion was enacted. Broadly speaking, this procedure derived from continental law. After the end of World War II, some Anglo-American approaches were fused with the former continental system. Ex-officio examination of evidence by the court was abolished and the system of cross-examination by the parties was adopted. However, the system of 'expert opinion' did not change basically. Now-a-days, we have two experts; expert and expert witness. When the judge asked 'expert opinion' to expert, he is an expert. However, when either of parties asked, then he is called 'expert witness'. Usually, expert witnesses are selected from professors or associate professors of universities. But accepting expert witness is not estimated for promotion in Japanese Medical College, so sometimes to select expert witness is difficult. Then, justice began to educate medical doctors to receive expert witness and has asked to medical society to offer the list of adequate expert witnesses, and also our society cooperates with this. Japanese Society of Legal Medicine instituted the medical speciality certification system, which includes such specialities as inspection of corpses and legal medicine that focuses on forensic practice. This means that our society certifies those who having diploma of legal medicine as expert witness.     

Intraventricular mass lesions

Determining the precise etiology of an intraventricular mass can be a difficult diagnostic problem. CT and angiographic findings were reviewed in a series of 73 patients who had intraventricular masses. The histologic diagnosis can be suggested preoperatively by an analysis of the frequency of lesions occurring at a given ventricular location, lesion density before and after administration of contrast material, age and sex of the patient, morphologic appearance of the mass, and presence or absence of hydrocephalus. Angiography is useful when meningioma, choroid plexus papilloma and carcinoma, or arteriovenous malformation are considered. The differential features of each diagnostic entity are discussed.     

Management of medicolegal natural deaths from hemopericardium or hemothorax using postmortem CT scanning

At the Victorian Institute of Forensic Medicine the forensic pathologist provides expert medical advice to the Coroner. Cases of natural death from hemopericardium and hemothorax are reasonably common in the forensic setting and are readily identifiable on postmortem CT (PMCT) scanning. The management of these cases raises interesting and challenging issues for the forensic pathologist. We present three cases in which PMCT angiography was useful in the management of each individual case and illustrate the potential of the technique in medico-legal death investigation.     

Development of a radiation therapy information system and linked medical image server using techniques of WWW-DB

We developed management system for medical information such as radiation therapy information and associated medical image information. Features of the system are to browse medical information with web browser through network. The system was constructed by open source software, which made proprietary client software unnecessary. Clinical studies suggested that the system proved useful in terms of paperless managemet. In addition, useful features are visibility and portability to browse medical information using PDA (Personal Data Assistant) via wireless LAN (Local Area Network). We also proposed a new approach which can contribute to remote areas by providing medical information using the Internet.