Biomedical subjects

A Hasman

Publications and source records attributed to A Hasman.

At least 37 records · Page 2Linked to original sources

PubMed1996

Building intelligent alarm systems by combining mathematical models and inductive machine learning techniques.

In this article a technique is described to develop knowledge-based alarm systems for ventilator therapy, using mathematical modeling and machine learning. With a mathematical model airway pressure, expiratory gas flow and CO2 concentration at the endotracheal tube are simulated for patients, undergoing volume-controlled ventilation with constant ventilator settings, during normal functioning of the breathing circuit and during breathing circuit mishaps (leaks and obstructions). Simulations were performed for 94 physiologically different 'patients', by varying airway resistance and lung/thorax compliance values in the model. Each simulated breath was described by a set of derived signal features and a label that constituted during which event (normal function or mishap) the breath was recorded. With an inductive machine learning algorithm rules, linking signal feature values to breathing circuit events, were created from data of 54 of the simulated patients. The resulting set of rules was able to classify 99% of events in the data of the remaining 40 patients correctly. Of signals, measured at a ventilated lung simulator, 100% of events were classified correctly.

Airway Resistance↗

PubMed1996

Care for records for care.

In this contribution the topic of this special issue is introduced: electronic patient records (EPRs). The characteristics of EPRs are presented. A number of problems that have to be solved before EPRs can be used on a large scale is discussed.

Computer Security↗

PubMed1996

Impact of a protocol processing system (ProtoVIEW) on clinical behaviour of residents and treatment.

A protocol processing system (ProtoVIEW), containing therapeutic trauma protocols, was used in the Accident and Emergency (A and E) department for a period of 7 months to investigate the impact of automated protocols on firstly, medical decision making of physicians and secondly, on quality of treatments eventually received by the patients. A randomized controlled trial showed that mandatory use of the system led to a more uniform working strategy while fracture treatment only seemed to improve in a subgroup of patient for whom residents established a correct diagnosis.

Adolescent↗

PubMed1996

From medical record to patient record through electronic data interchange (EDI).

In this contribution the role of Electronic Data Interchange (EDI) for patient records is discussed. It is our opinion that unlimited access to patient records of different care provides is not a wise thing to do and may even not be acceptable legally. The exchange of EDI messages may be a solution in that the relevant information is exchanged on a need to know basis under the responsibility of the care provider that generated the information. The state of the art with respect to the availability of EDI messages in Europe is presented.

Communication↗

PubMed1996

Building intelligent alarm systems by combining mathematical models and inductive machine learning techniques Part 2--sensitivity analysis.

In an earlier study an approach was described to generate intelligent alarm systems for monitoring ventilation of patients via mathematical simulation and machine learning. However, ventilator settings were not varied. In this study we investigated whether an alarm system could be created with which a satisfactory classification performance could be obtained under a wide variety of ventilator settings, by varying inspiratory to expiratory time (I:E) ratio, tidal volume and respiratory rate. In a first experiment three patient data sets were modeled, each with a different I:E ratio. A part of each data set was used to construct an alarm system for each I:E ratio. The remaining part was used to test the performance of the alarm systems. The three training sets were also combined to construct one alarm system, which was tested with the three test sets. Finally, all alarm systems were tested with data generated by a patient simulator. Similar experiments were performed for the tidal volume and the respiratory rate. It was concluded that an optimally functioning alarm system should contain a library of rule sets, one for each set of ventilator settings. A second best alternative is to take all possible settings into consideration when constructing the training set. Classification performance of the trees that were trained with multiple ventilator settings ranged from 98 to 100% for all test sets. When tested with the independent patient simulator data the classification performance of these trees ranged from 80 to 100%.

Airway Resistance↗

PubMed1996

Effects of a supportive protocol processing system (ProtoVIEW) on clinical behaviour of residents in the accident and emergency department.

A randomized two period crossover trial was performed at the Accident and Emergency (A & E) department of the University Hospital in Nijmegen (The Netherlands). We assessed what the impact was of (mandatory) consultation of a protocol for the management of isolated traumas on treatment decisions of residents. All eight surgical residents who regularly worked in the A & E department participated in the trial. All patients who entered the A & E department between October 13, 1992 and June 9, 1993, of age 16 years or older with an isolated fracture without concomitant lesions were admitted to the study. During the experimental periods, the management protocol was available on computer (using ProtoVIEW) and during the control periods on paper. Main measurements were treatment adjustments made by residents (after consulting different information sources), and their opinion about ProtoVIEW as an information source assessed by means of a questionnaire. When protocol consultation was mandatory, residents changed their treatments almost four times more often towards the protocol than during the control periods (P = 0.01 Chi-square test). Most residents found ProtoVIEW easy to use, liked it as a useful training source while half of them said they would use the system in daily clinical practice. We conclude that mandatory protocol consultation using ProtoVIEW influenced protocol adherence positively.

Attitude↗

PubMed1996

OpenLabs services for ordering laboratory investigations.

An automated system is described that screens requests for laboratory investigations from GPs and delivers feedback with respect to the adequacy of the requests. The system has to replace and extend the current system in which feedback is provided on a manual basis each half year, based on the tests requested during a period of one month, randomly selected from the previous half year. It has been reported elsewhere that the manual system reduced the number of tests requested considerably. The criteria used by the automated system and the manual system are based on guidelines and work agreements that GPs have agreed to follow when requesting investigations. It is concluded that the automated system is very user-friendly and that in the order of 4-17% of the requested tests could be identified as unnecessary, with a false negative rate in between 4% (for hyperthyroidism) and 23% (for hypothyroidism). The achieved reduction in the number of tests is in addition to the reduction obtained in the manual system.

Clinical Laboratory Information Systems↗

PubMed1996

Advanced management facilities for clinical laboratories.

As part of the OpenLabs (AIM 2028) programme a decision support system (DSS) for laboratory capacity management has been developed. This DSS contains a simulation module for determining the performance of planning rules given the equipment and staffing of the clinical laboratory and the demand for laboratory services. User requirements are discussed and a method is developed to (re-)define rules concerning various planning decisions. To show the functionality of the simulation module some simulation experiments are described.

Clinical Laboratory Information Systems↗

PubMed1996

A systematic view on medical informatics.

Medical informatics is defined as the scientific discipline concerned with the systematic processing of data, information and knowledge in medicine and health care. The domain of medical informatics (including health informatics), its aim, methods and tools, and its relevance to other disciplines in medicine and health sciences are outlined. It is recognized that one of the major tasks of medical informatics is modelling processes. In this context, biological, communication, decision, engineering, educational, organizational and computational processes are distinguished and described.

Computer Communication Networks↗

PubMed1996

The discriminative value of patient characteristics and dyspeptic symptoms for upper gastrointestinal endoscopic findings: a study on the clinical presentation of 1,147 patients.

The discriminative value of patient characteristics and dyspeptic symptoms for upper gastrointestinal endoscopic findings was prospectively assessed in 1,147 patients attending for their first diagnostic endoscopy and who answered paper (n = 431) or computerized (n = 716) questionnaires. The questionnaires provided detailed information concerning present dyspeptic symptoms, with special attention to provoking and/or relieving factors, and smoking and/or drinking habits. In logistic regression models each of a number of 'specific endoscopic diagnoses' was contrasted with normal endoscopy (n = 390), and 'relevant endoscopic disease' (oesophagitis, peptic ulcers, cancers; n = 269) was contrasted with 'irrelevant' and normal endoscopic findings (n = 878). From the regression model a receiver operating characteristic (ROC) curve could be constructed, and the area under the ROC curve (AUC) was calculated to summarize the discriminative power of the regression model. The best discrimination from patients with a normal endoscopy was achieved for patients with gastric (AUC = 0.86) or duodenal (AUC = 0.85) ulcers, followed by patients with hiatus hernia (AUC = 0.78 or oesophagitis (AUC = 0.77). The discriminative performance of the regression models was somewhat less for duodenitis/bulbitis (AUC = 0.75) and endoscopic gastritis (AUC = 0.73). In an open-access endoscopy unit setting, the value of preinvestigation history-taking for the prediction of clinically relevant endoscopic disease was very limited (AUC = 0.63).

Adolescent↗

PubMed1996

[Towards congruence in nursing information provision in The Netherlands].

Few reliable data are available about nursing care in the Netherlands, whereas pressure from society to support the contributions of the discipline of nursing to health care delivery increases. This paper presents an information model to support analytical access to nursing labour and services. This model, the nursing information reference model (Dutch acronym 'VIRM') focuses on the structure to achieve congruence between data from the primary process of nursing care and data derived from that process for clinical practice, management, research, and policy purposes. The model is based on the 'collect-once/use-often' principle of data collection and management, which emphasizes single collection and registration through the patient record for multiple subsequent uses and purposes. In this paper core elements of the VIRM are being discussed. Determination of data from the primary process of nursing care to be provided for certain aims is currently being conducted by the Dutch Nursing Minimum Data Set (VMDNS) initiative. The article at issue should be understood as a starting point in the discussion about the development of a Nursing Minimum Data Set in the Netherlands.

Data Collection↗

PubMed1995

Functional and neurochemical profile of place learning after L-nitro-arginine in the rat.

Rats in which near-total inhibition of the nitric oxide synthesizing enzyme (NOS) had been obtained by a 5-day pretreatment during which two daily injections of L-nitro-arginine (50 mg/kg per injection) had been administered were subjected to five sessions of training on a place learning task (one session per day). NOS inhibition was associated with significantly impaired task acquisition but on the fifth training session normal task proficiency was achieved. Subsequent pharmacological and behavioral challenges established that dissimilar neural substrates mediated the task in NOS-inhibited and normal animals. In NOS-inhibited rats the neural substrate of task mediation depended less than normally on cholinergic mechanisms while potentially relying more on catecholaminergic mediation. In a separate experiment rats that had acquired the place learning task to asymptotic quality of performance were subjected to a L-nitro-arginine treatment similar to the pretreatment of the first experiment. Such a NOS inhibition did not impair subsequent task performance. It is concluded that nitric oxide participates in processes subserving acquisition rather than performance of at least some forms of place learning.

Amino Acid Oxidoreductases↗

PubMed1995

Decision support for clinical laboratory capacity planning.

The design of a decision support system for capacity planning in clinical laboratories is discussed. The DSS supports decisions concerning the following questions: how should the laboratory be divided into job shops (departments/sections), how should staff be assigned to workstations and how should samples be assigned to workstations for testing. The decision support system contains modules for supporting decisions at the overall laboratory level (concerning the division of the laboratory into job shops) and for supporting decisions at the job shop level (assignment of staff to workstations and sample scheduling). Experiments with these modules are described showing both the functionality and the validity.

Clinical Laboratory Information Systems↗

PubMed1995

Evaluation of a decision support system in a medical environment.

This paper describes the impact of a decision support system on the quality of recorded diagnoses and the completeness of medical records. The assumption is that for quality assessment purposes enough data have to be recorded in an electronic medical record so that diagnostic decisions can be justified. The hypotheses were tested that active decision support will lead to better quality recorded diagnoses and more complete medical records. Three groups of ten GPs were presented with 10 cases each. The GPs had to enter the data about these cases in a GP information system. One group of GPs was not supported. The second group was presented with the ICHPPC-II-Defined criteria that had to be fulfilled when a diagnosis was entered. In a third group, the GPs were asked those data that were needed to justify an entered diagnosis (active support). It could be shown that the last group of GPs entered better quality diagnoses than the other two groups. These latter groups also entered so little data that most of their diagnoses could not be justified. It is concluded from the study that only active decision support will lead to better diagnoses and a more complete medical record that can be used for quality assessment.

Artificial Intelligence↗

PubMed1995

Consultation behaviour of residents supported with a protocol processing system (ProtoVIEW) at the emergency ward.

We evaluated the consultation behaviour of residents using a protocol processing system in routine clinical practice. A total of 125 consecutive patients, of age 16 years or older with an isolated fracture without concomitant lesions, were treated with computer support between 13 October 1992 and 9 June 1993. All eight surgical residents who worked at the emergency ward of the University Hospital in Nijmegen, The Netherlands participated. The mean consultancy time, method of information retrieval, number of correct protocols found, number of windows retrieved and attitude towards ProtoVIEW as a useful information source were estimated. Main results are: a mean consultancy time of 1.5 min per case, residents browsed through the protocol information more often than using keyword search. The correct protocols were found in 98% of the cases while on average a minimum number of text-browse windows was retrieved. Residents were positive about the way protocols were presented and about the information supplied by ProtoVIEW. From this study we may conclude that ProtoVIEW consultation is hardly time consuming, and easy to use. Since keyword search was hardly used, expanding the number of synonyms may stimulate searching by keyword more often.

Adolescent↗

PubMed1995

Utilization of laboratory resources: developments in knowledge-based ordering systems.

This paper describes two rule based decision support systems. The first system is used to screen incoming test requests for adequacy on the basis of signs and symptoms volunteered by the requesting GPs. The system was tested using a database of 794 requests for a TSH test. About 17% of the test requests were correctly identified as unnecessary. In total, 0.5% of the tests were incorrectly labelled as unnecessary. This concerned 4% of the patients that appeared to have hyperthyroidism and 23% of the patients that appeared to have hypothyroidism on the basis of TSH and FT4 results. The other system is a rule-based clinical decision support system for the requesting of laboratory investigations, originally designed for use at a hospital within the UK, that was implemented in a predominantly French-speaking hospital in Belgium. This involved the modification of the system to allow multilingual operation, and also the implementation of a completely new set of investigation protocols. The purpose of this study was to assess the transferability, both of the system itself, and of its benefits. The system was introduced gradually and has only recently been in full operation. However, the findings from the first months of routine use of the system indicate that the transfer of the system to a different clinical environment has been successful. Although it is too early to assess fully the impact on laboratory utilization, the clinicians believe that it is improving the appropriateness of investigations.

Artificial Intelligence↗

PubMed1995

Development, implementation and a first evaluation of a protocol processing system (ProtoVIEW).

In this contribution the protocol information system ProtoVIEW is presented. The system provides the necessary information to physicians about diagnostic procedures and therapies. It is implemented as a stand alone system. The design criteria are discussed and the results of a first evaluation presented. It appears that interns can easily find the required information with the help of the system. The time that they need for accessing the relevant information is relatively short (about 1 min). The users expressed the opinion that the system is easy to use and does support them in the management of their patients. On the basis of this evaluation and evaluations reported elsewhere it is concluded (a) that stand-alone protocol systems can support daily patient management in a positive way and (b) that the design criteria for a protocol information system as presented in this paper are useful for prospective protocol information system developers.

Attitude of Health Personnel↗

PubMed1995

User satisfaction of general practitioners with HIOS+, a medical decision support system.

In this article, a user satisfaction study is described. The Formal Interpreter (FI) and the Free-text Formalizer (FF) are modules of the medical DSS HIOS+. With FF, medical experts can formalize topics selected from free-text ICHPPC-II-defined criteria into queries. FI gives decision support to GPs in their daily work by interpreting queries belonging to entered ICPC codes and presenting advice/warnings concerning the validity (correctness) of the diagnoses in patient cases. In the study, FI was used in field and laboratory test situations by GPs. User satisfaction was assessed using questionnaires consisting of an adapted version of the Bailey questionnaire. Answers given were analysed using Bailey's approach and the 'two-sample t-test'. The most important result of the FI evaluation was that users given active decision support were more satisfied with FI than users given none or only textual decision support.

Attitude to Computers↗