Design and validation of an intelligent patient monitoring and alarm system based on a fuzzy logic process model

Artificial Intelligence With Robotics in Healthcare: A Narrative Review of Its Viability in India

This short review focuses on the emerging role of artificial intelligence (AI) with robotics in the healthcare sector. It may have particular utility for India, which has limited access to healthcare providers for a large growing population and limited health resources in rural India. AI works with an amalgamation of enormous amounts of data using fast and complex algorithms. This permits the software to quickly adapt the pattern of the data characteristics. It has the possibility to collide with most of the facets of the health system which may range from discovery to prediction and deterrence. The use of AI with robotics in the healthcare sector has shown a remarkable rising trend in the past few years. Functions like assistance with surgery, streamlining hospital logistics, and conducting routine checkups are some of the tasks that may be managed with great efficiency using artificial intelligence in urban and rural hospitals across the country. AI in the healthcare sector is advantageous in terms of ensuring exclusive patient care, safe working conditions where healthcare providers are at a lower risk of getting infected, and perfectly organized operational tasks. As the healthcare segment is globally recognized as one of the most dynamic and biggest industries, it tends to expedite development through modernization and original approaches. The future of this lucrative industry is looking forward to a great revolution aiming to create intelligent machines that work and respond like human beings. The future perspective of AI and robotics in the healthcare sector encompasses the care of elderly people, drug discovery, diagnosis of deadly diseases, a boost in clinical trials, remote patient monitoring, prediction of epidemic outbreaks, etc. However, the viability of using robotics in healthcare may be questionable in terms of expenditure, skilled workforce, and the conventional mindset of people. The biggest challenge is the replication of these technologies to the smaller towns and rural areas so that these facilities may reach the larger segment of the entire population of the country. This review aims to examine the adaptability and viability of these new technologies in the Indian scenario and identify the major challenges.

Machine learning methods for perioperative anesthetic management in cardiac surgery patients: a scoping review

Background

Machine learning (ML) is developing fast with promising prospects within medicine and already has several applications in perioperative care. We conducted a scoping review to examine the extent and potential limitations of ML implementation in perioperative anesthetic care, specifically in cardiac surgery patients.

Methods

We mapped the current literature by searching three databases: MEDLINE (Ovid), EMBASE (Ovid), and Cochrane Library. Articles were eligible if they reported on perioperative ML use in the field of cardiac surgery with relevance to anesthetic practices. Data on the applicability of ML and comparability to conventional statistical methods were extracted.

Results

Forty-six articles on ML relevant to the work of the anesthesiologist in cardiac surgery were identified. Three main categories emerged: (I) event and risk prediction, (II) hemodynamic monitoring, and (III) automation of echocardiography. Prediction models based on ML tend to behave similarly to conventional statistical methods. Using dynamic hemodynamic or ultrasound data in ML models, however, shifts the potential to promising results.

Conclusions

ML in cardiac surgery is increasingly used in perioperative anesthetic management. The majority is used for prediction purposes similar to conventional clinical scores. Remarkable ML model performances are achieved when using real-time dynamic parameters. However, beneficial clinical outcomes of ML integration have yet to be determined. Nonetheless, the first steps introducing ML in perioperative anesthetic care for cardiac surgery have been taken.

The Beginning of a New Era: Artificial Intelligence in Healthcare

The healthcare sector is considered to be one of the largest and fast-growing industries in the world. Innovations and novel approaches have always remained the prime aims in order to bring massive development. Before the emergence of technology, the healthcare sector was dependent on manpower, which was time-consuming and less accurate with lack of efficiency. With the recent advancements in machine learning, the condition has been steadily revolutionizing. Artificial intelligence (AI) lies in the computer science department, which stresses on the intelligent machines’ creation, that work and react just like human beings. Currently, the applications of AI have been expanding into those fields, which was once thought to be the only domain of human expertise such as healthcare sector. In this review, we have shed light on the present usage of AI in the healthcare sector, such as its working, and the way this system is being implemented in different domains, such as drug discovery, diagnosis of diseases, clinical trials, remote patient monitoring, and nanotechnology. We have also briefly touched upon its applications in other sectors as well. The public opinions have also been analyzed and discussed along with the future prospects. We have discussed the merits, and the other side of AI, i.e. the disadvantages in the last part of the manuscript.

Novel Interface Designs for Patient Monitoring Applications in Critical Care Medicine: Human Factors Review

Background

The patient monitor (PM) is one of the most commonly used medical devices in hospitals worldwide. PMs are used to monitor patients’ vital signs in a wide variety of patient care settings, especially in critical care settings, such as intensive care units. An interesting observation is that the design of PMs has not significantly changed over the past 2 decades, with the layout and structure of PMs more or less unchanged, with incremental changes in design being made rather than transformational changes. Thus, we believe it well-timed to review the design of novel PM interfaces, with particular reference to usability and human factors.

Objective

This paper aims to review innovations in PM design proposed by researchers and explore how clinicians responded to these design changes.

Methods

A literature search of relevant databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, identified 16 related studies. A detailed description of the interface design and an analysis of each novel PM were carried out, including a detailed analysis of the structure of the different user interfaces, to inform future PM design. The test methodologies used to evaluate the different designs are also presented.

Results

Most of the studies included in this review identified some level of improvement in the clinician’s performance when using a novel display in comparison with the traditional PM. For instance, from the 16 reviewed studies, 12 studies identified an improvement in the detection and response times, and 10 studies identified an improvement in the accuracy or treatment efficiency. This indicates that novel displays have the potential to improve the clinical performance of nurses and doctors. However, the outcomes of some of these studies are weakened because of methodological deficiencies. These deficiencies are discussed in detail in this study.

Conclusions

More careful study design is warranted to investigate the user experience and usability of future novel PMs for real time vital sign monitoring, to establish whether or not they could be used successfully in critical care. A series of recommendations on how future novel PM designs and evaluations can be enhanced are provided.

Hypoglycemia Prevention via Personalized Glucose-Insulin Models Identified in Free-Living Conditions

BACKGROUND

The objective of this research is to show the effectiveness of individualized hypoglycemia predictive alerts (IHPAs) based on patient-tailored glucose-insulin models (PTMs) for different subjects. Interpatient variability calls for PTMs that have been identified from data collected in free-living conditions during a one-month trial.

METHODS

A new impulse-response (IR) identification technique has been applied to free-living data in order to identify PTMs that are able to predict the future glucose trends and prevent hypoglycemia events. Impulse response has been applied to seven patients with type 1 diabetes (T1D) of the University of Amsterdam Medical Centre. Individualized hypoglycemia predictive alert has been designed for each patient thanks to the good prediction capabilities of PTMs.

RESULTS

The PTMs performance is evaluated in terms of index of fitting (FIT), coefficient of determination, and Pearson's correlation coefficient with a population FIT of 63.74%. The IHPAs are evaluated on seven patients with T1D with the aim of predicting in advance (between 45 and 10 minutes) the unavoidable hypoglycemia events; these systems show better performance in terms of sensitivity, precision, and accuracy with respect to previously published results.

CONCLUSION

The proposed work shows the successful results obtained applying the IR to an entire set of patients, participants of a one-month trial. Individualized hypoglycemia predictive alerts are evaluated in terms of hypoglycemia prevention: the use of a PTM allows to detect 84.67% of the hypoglycemia events occurred during a one-month trial on average with less than 0.4% of false alarms. The promising prediction capabilities of PTMs can be a key ingredient for new generations of individualized model predictive control for artificial pancreas.

Adaptive online monitoring for ICU patients by combining just-in-time learning and principal component analysis

Offline general-type models are widely used for patients' monitoring in intensive care units (ICUs), which are developed by using past collected datasets consisting of thousands of patients. However, these models may fail to adapt to the changing states of ICU patients. Thus, to be more robust and effective, the monitoring models should be adaptable to individual patients. A novel combination of just-in-time learning (JITL) and principal component analysis (PCA), referred to learning-type PCA (L-PCA), was proposed for adaptive online monitoring of patients in ICUs. JITL was used to gather the most relevant data samples for adaptive modeling of complex physiological processes. PCA was used to build an online individual-type model and calculate monitoring statistics, and then to judge whether the patient's status is normal or not. The adaptability of L-PCA lies in the usage of individual data and the continuous updating of the training dataset. Twelve subjects were selected from the Physiobank's Multi-parameter Intelligent Monitoring for Intensive Care II (MIMIC II) database, and five vital signs of each subject were chosen. The proposed method was compared with the traditional PCA and fast moving-window PCA (Fast MWPCA). The experimental results demonstrated that the fault detection rates respectively increased by 20 % and 47 % compared with PCA and Fast MWPCA. L-PCA is first introduced into ICU patients monitoring and achieves the best monitoring performance in terms of adaptability to changes in patient status and sensitivity for abnormality detection.

A Cognitive Modeling Approach to Decision Support Tool Design for Anesthesia Provider Crisis Management

Prior research has revealed existing operating room (OR) patient monitors to provide limited support for prompt and accurate decision making by anesthesia providers during crises. Decision support tools (DSTs) developed for this purpose typically alert the anesthesia provider to existence of a problem but do not recommend a treatment plan. There is a need for a human-centered approach to the design and development of a crisis management DST. A hierarchical task analysis was conducted to identify anesthesia provider procedures in detecting, diagnosing, and treating a critical incident and a cognitive task analysis to elicit goals, decisions, and information requirements. This information was coded in a computational cognitive model using GOMS (Goals, Operators, Methods, Selection rules) Language. An OR monitor interface was prototyped to present output from the cognitive model following ecological interface design principles. A preliminary assessment of the DST was performed with anesthesiology and usability experts. The anesthesiologists indicated they would use the tool in the perioperative environment and would recommend its use by junior anesthesia providers. Future research will focus on formal validation of the DST design approach and comparison of tool output to actual anesthesia provider decisions in real or simulated crises.

Smart alarms from medical devices in the OR and ICU

Alarms in medical devices are a matter of concern in critical and perioperative care. The high rate of false alarms is not only a nuisance for patients and caregivers, but can also compromise patient safety and effectiveness of care. The development of alarm systems has lagged behind the technological advances of medical devices over the last 20 years. From a clinical perspective, major improvements in alarm algorithms are urgently needed. This review gives an overview of the current clinical situation and the underlying problems, and discusses different methods from statistics and computational science and their potential for clinical application. Some examples of the application of new alarm algorithms to clinical data are presented.

Surface electromyography and muscle force: limits in sEMG-force relationship and new approaches for applications

The estimation of the force generated by an activated muscle is of high relevance not only in biomechanical studies but also more and more in clinical applications in which the information about the muscle forces supports the physician's decisions on diagnosis and treatment. The surface electromyographic signal (sEMG) reflects the degree of activation of skeletal muscles and certain that the sEMG is highly correlated to the muscle force. However, the largest disadvantage in predicting the muscle force from sEMG is the fact that the force generated by a muscle cannot be directly measured non-invasively. Indirect measurement of muscle force goes along with other unpredictable factors which influence the detected force but not necessarily the sEMG data. In addition, the sEMG is often difficult to interpret correctly. The sEMG-force relationship has been investigated for a long time and numerous papers are available. This review shows the limitations in predicting the muscle force from sEMG signals and gives some perspectives on how these limitations could be overcome, especially in clinical applications, by using novel ways of interpretation.

Anesthetic level prediction using a QCM based E-nose

Anesthetic level measurement is a real time process. This paper presents a new method to measure anesthesia level in surgery rooms at hospitals using a QCM based E-Nose. The E-Nose system contains an array of eight different coated QCM sensors. In this work, the best linear reacting sensor is selected from the array and used in the experiments. Then, the sensor response time was observed about 15 min using classic method, which is impractical for on-line anesthetic level detection during a surgery. Later, the sensor transition data is analyzed to reach a decision earlier than the classical method. As a result, it is found out that the slope of transition data gives valuable information to predict the anesthetic level. With this new method, we achieved to find correct anesthetic levels within 100 s.

E-Nose system for anesthetic dose level detection using artificial neural network

In this study, an E-Nose system was realized for the anesthetic dose level prediction. For this purpose, sevoflurane anesthetic agent was measured using the E-Nose system implemented with sensor array of quartz crystal microbalances (QCM). In surgeries, anesthetic agents are given to the patients with carrier gases of oxygen (02) and nitrous oxide (N20). Frequency changes on QCM sensors to the eight sevoflurane anesthetic dose levels were recorded via RS-232 serial port. A multilayer feed forward artificial neural network (MLNN) structure was used to provide the relationship between the frequency change and the anesthetic dose level. The MLNNs were trained with the measured data using Levenberg-Marquardt algorithm. Then, the trained MLNNs were tested with random data. The results have showed that, acceptable anesthetic dose level predictions have been obtained successfully.

A fuzzy logic-based decision support system on anesthetic depth control for helping anesthetists in surgeries

In this study, a fuzzy logic-based anesthetic depth decision support system (ADDSS) was realized for anesthetic depth control to help anesthetists in surgeries. Depth of anesthesia for a patient can change according to anesthetic agent and characteristic properties of a patient such as age, weight, etc. During the surgery, depth of anesthesia of a patient is determined by the experience of anesthetist controlling of systolic arterial pressure (SAP) and heart pulse rate (HPR) parameters. Anesthetists could have tired and lost attention by inhaling of anesthetic gas leaks in long lasted operations. For that reason, improper anesthetic depth could be applied to the patients. So anesthesia could not be safety and comfortable. To remove this unwanted situation, an ADDSS was proposed for anesthetists. By the help of this system, precise anesthetic depth could have provided. Thus, the anesthetist will spend less time to provide anesthetic and the patient will have a safer and less expensive operation. This study was performed under sevoflurane anesthetic.

A randomised controlled trial of the effect of continuous electronic physiological monitoring on the adverse event rate in high risk medical and surgical patients

We conducted a randomised controlled trial of mandated five-channel physiological monitoring vs standard care, in acute medical and surgical wards in a single UK teaching hospital. In all, 402 high-risk medical and surgical patients were studied. The primary outcome was the proportion of patients experiencing one or more major adverse events, including urgent staff calls, changes to higher care levels, cardiac arrests or death, in 96 h following randomisation. Secondary outcomes were the proportion of patients requiring acute treatment changes, and the 30-day and hospital mortality. In the 96 h following randomisation, 113 (56%) patients in the monitored arm and 116 (58%) in the control arm (OR 0.94, 95% CI 0.63-1.40, p = 0.76) had a major event. An acute change in treatment was necessary in 107 (53%) monitored patients and 101 (50%) control patients (OR 0.55, 95% CI 0.87-1.29). Thirty-four (17%) monitored patients and 35 (17%) control patients died within 30 days. Thirteen patients in the control group received full five-channel monitoring at the request of the ward staff. We conclude that mandated electronic vital signs monitoring in high risk medical and surgical patients has no effect on adverse events or mortality.

Alarm Algorithms in Critical Care Monitoring

The alarms of medical devices are a matter of concern in critical and perioperative care. The frequent false alarms not only are a nuisance for patients and caregivers but can also compromise patient safety and effectiveness of care. The development of alarm systems has lagged behind the technological advances of medical devices over the last 20 years. From a clinical perspective, major improvements of alarm algorithms are urgently needed. We give an overview of the current clinical situation and the underlying problems and discuss different methods from statistics and computational science and their potential for clinical application.

Interpretation of surface EMGs in children with cerebral palsy: An initial study using a fuzzy expert system

Surface EMG detected simultaneously at different muscles has become an important tool for analysing the gait of children with cerebral palsy (CP), as it offers essential information about muscular coordination. However, the interpretation of surface EMG is a difficult task that assumes extensive knowledge and experience. As such, this noninvasive procedure is not frequently used in the general clinical routine. An Artificial Intelligence (AI) system for interpreting surface EMG signals and the resulting muscular coordination patterns could overcome these limitations. To support such interpretation, an expert system based on fuzzy inference methodology was developed. The knowledge-base of the system implemented 15 rules, from which the fuzzy inference methodology performs a prediction of the effectiveness of the muscular coordination during gait. Our aim was to assess the feasibility and value of such an expert system in clinical applications. Surface EMG signals were recorded from the tibialis anterior, soleus muscle, and gastrocnemius muscles of children with CP to assess muscular coordination patterns of ankle movement during gait. Nineteen children underwent 114 surface EMG measurements. Simultaneously, the gait cycles of each patient were determined using foot switches and videotapes. From the EMG signals, the effectiveness of the ankle movement was predicted by the expert system, and predictions were classified using a three-point ordinal scale. In 91 cases (80%), the clinical findings matched the predictions of the expert system. In 23 cases (20%) the predictions of the expert system differed from the clinical findings with 12 cases revealing worse and 11 cases revealing better results in comparison to the clinical findings. As this study is a first attempt to verify the feasibility and correctness of this expert system, the results are promising. Further study is required to assess the correlation with the kinematic data and to include the whole leg.

Intelligent alarm processing into clinical knowledge

Alarmed physiological monitors have become a standard part of the ICU. While the alarms generated by these monitors can be important indicators of an altered physiological condition, most are unhelpful to medical staff due to a high incidence of false and clinically insignificant alarms. High numbers of false/insignificant alarms can lead to several adverse consequences such as increased patient anxiety,distraction of clinicians, and decreased efficiency in delivery of care. Furthermore, repeated false/insignificant alarms may increase the chance that healthcare providers ignore clinically significant alarms. In this paper we review the current state of intelligent alarm processing and describe an integrated systems methodology to extract clinically relevant information from physiological data. Such a method would aid significantly in the reduction of false alarms and provide nursing staff with a more reliable indicator of patient condition.

On line extraction of temporal episodes from ICU high-frequency data: a visual support for signal interpretation

This paper presents a method to extract on line temporal episodes from high-frequency physiological parameters monitored in ICU, as a visual support for signal interpretation. Temporal episodes are expressions such as: "systolic blood pressure is steady at 120 mmHg from time t(0) until time t(1); it increases from 120 to 160 mmHg from time t(1) to time t(2) ...". Three words are used to describe the data evolution: {steady, increasing, decreasing}. The method deals with noisy data and missing values. It uses a segmentation algorithm that was developed previously and a classification of the segments into temporal patterns. The results obtained on simulated data are quite satisfactory. They show that the method is able to detect rapid variations as well as slow trends. Episodes extracted from real S(p)o(2) data recorded over a period of 44 h from 10 different adult patients are analysed. The visual representation of the temporal episodes is a powerful tool to help the physicians analyse in a glance the evolution in time of the variables monitored. It can help carer personnel to make quicker decisions in alarm situations.

On-Line Segmentation Algorithm for Continuously Monitored Data in Intensive Care Units

An on-line segmentation algorithm is presented in this paper. It is developed to preprocess data describing the patient's state, sampled at high frequencies in intensive care units, with a further purpose of alarm filtering. The algorithm splits the signal monitored into line segments--continuous or discontinuous--of various lengths and determines on-line when a new segment must be calculated. The delay of detection of a new line segment depends on the importance of the change: the more important the change, the quicker the detection. The linear segments are a correct approximation of the structure of the signal. They emphasise steady-states, level changes and trends occurring on the data. The information returned by the algorithm, which is the time at which the segment begins, its ordinate and its slope, is sufficient to completely reconstruct the filtered signal. This makes the algorithm an interesting tool to provide a processed time history record of the monitored variable. It can also be used to extract on-line information on the signal, such as its trend, in the short or long term.

Evaluation of two new ecological interface approaches for the anesthesia workplace

OBJECTIVE

Currently, vital parameters are commonly displayed as trends along a timeline. However, clinical decisions are more often based upon concepts, such as the depth of anesthesia, that are derived by combining parameter relationships and additional context information. The current displays do not visualize such concepts and therefore do not optimally support the decision process. A new display should present an ecological interface (EI). The principle of EI design is to visualize all of the information necessary for decision making in one single display.

METHODS

In the first approach, we developed an EI that visualizes 35 relevant parameters for anesthesia monitoring. All of the parameters are generated by an anesthesia software simulator. Sixteen anesthetists had to administer two simulated general anesthetics: in one setting working only with the simulator's monitors ("Sim Only"), and in another setting working with the simulator's monitors in combination with the EI ("Combi1"). During each experiment, one unexpected critical incident (either blood loss or a cuff leakage) had to be identified. The control and monitoring behavior was analyzed by recording the subjects' eye movements and think-aloud protocol. With the help of the eye-tracking results, we re-designed the EI. The new EI was then tested with no eye tracking ("Combi2") on eight anesthetists under analogous conditions as in "Combi1."

RESULTS

Cuff leakage was identified significantly quicker in "Combi1" (7 of 8 cases; time (T): 65 s +/- 73 s) than in "SimOnly" (6 of 8 cases; T: 222 s +/- 187 s). Blood loss was identified in 5 of 8 cases (T: 215 s +/- 76 s) in "Combi1" as quickly as in "SimOnly" (all cases; T: 217 s +/- 72 s). In "Combi1," the EI was used as the main source of information (in 43 +/- 19% of time) and was frequently favored when identifying an evolving critical incident. In "Combi2," cuff leakage was identified in 7 of 8 cases (T: 70 s +/- 111 s) as quickly as in "Combi1." Blood loss was identified significantly quicker in all cases (T: 147 s +/- 62 s) in "Combi2" than in "Combi1" and in "SimOnly."

CONCLUSION

The results have shown that appropriately designed EIs may improve the anesthetist's decision making and focus attention on specific problems. Now, the findings have to be tested in future studies by widening the scope using other simulated scenarios and being closer to reality under real conditions in the OR. Eye tracking proved to be a useful method to analyze the anesthetists' decision making and appropriately re-design interfaces.

The graphical presentation of decision support information in an intelligent anaesthesia monitor

This contribution examines the graphical presentation of decision support information generated by an intelligent monitor, named SENTINEL, developed for use during anaesthesia. Clinicians make diagnoses in real-time during operations by examining clinically significant trends in multiple signals. SENTINEL attempts to mimic this decision process by using a system of fuzzy trend templates. SENTINEL's implementation of fuzzy trend templates is capable of providing the dual fuzzy measures of belief and plausibility, which are derived from the theory of evidence. It is thus capable of generating fairly rich diagnostic decision support information. However, for SENTINEL to be effective, the visual presentation of this information must be intuitive to the anaesthetist, who may not be familiar with the theory of evidence. This paper discusses techniques that are being evaluated to meet the requirements of the SENTINEL anaesthesia monitor. Specifically, the paper presents methods for highlighting clinically significant trends in physiological (or derived) signals by superimposing a coloured band on the signal that reflects fuzzy output from the intelligent monitor. This paper also discusses the intuitive graphical presentation of binary diagnostic fuzzy measures, including their further interpretation and presentation as crisp "alarm" and "warning" conditions.

Multiple signal integration by decision tree induction to detect artifacts in the neonatal intensive care unit

The high incidence of false alarms in the intensive care unit (ICU) necessitates the development of improved alarming techniques. This study aimed to detect artifact patterns across multiple physiologic data signals from a neonatal ICU using decision tree induction. Approximately 200 h of bedside data were analyzed. Artifacts in the data streams were visually located and annotated retrospectively by an experienced clinician. Derived values were calculated for successively overlapping time intervals of raw values, and then used as feature attributes for the induction of models trying to classify 'artifact' versus 'not artifact' cases. The results are very promising, indicating that integration of multiple signals by applying a classification system to sets of values derived from physiologic data streams may be a viable approach to detecting artifacts in neonatal ICU data.

Ergonomic evaluation of an ecological interface and a profilogram display for hemodynamic monitoring

OBJECTIVE

Comprehensive monitoring of the patient state and subsequent decision making is an essential part of the task of an anaesthetist. The physicians' decision making process is based upon a concept of partly abstract physiologic parameters such as depth of anaesthesia or contractility. This concept is derived from the measured parameters given on todays' trend displays in addition to context information available for the anaesthetist. We investigated two alternative approaches of display design for hemodynamic monitoring: 1) integrated displays based on ecological interface design, and 2) profilogram displays based on intelligent alarms.

METHOD

To evaluate differences in decision making, the two displays and a trend display were compared in an experimental set-up with computer simulated vital parameter curves. From a start state with random parameter deviations from the ideal state, subjects had to achieve the ideal circulatory performance as fast as possible by manipulating vasomotor tone, heart rate, blood volume and contractility. To analyse subjects' decision making process, eye-tracking, event-logging, and the method of think aloud protocols were used. Twenty anaesthesiologists performed 113 experiments (approximately 2 with each display).

RESULTS

The anaesthetists failed to achieve the task in 37% using the trend display, in 19% using the profilogram display, and in 13% using the ecological interface. Hence, a safer task solution was possible with the ecological interface and the profilogram display but at the expense of various performance parameters such as higher trial time, more interactions with the simulated system, and more frequent eye movements. In contrast to the trend display and the profilogram display, where anaesthetists were mainly focussed on controlling the left atrial pressure, such an behaviour was less observed with the ecological interface.

CONCLUSION

Our results have shown that subjects came to more effective solutions with the traditional trend display. The main reason for this result may be their years of experience with this kind of display type. Regarding safe and goal-intended decision finding, the results are encouraging for further experiments with redesigned ecological displays. But these displays ought to have smoother changes with respect to the traditional trend displays. Furthermore, new experiments have to be performed under real or fairly real (e.g. together with an anaesthesia simulator) conditions to underline the positive results for ecological interfaces.

Diagnostic monitoring in anaesthesia using fuzzy trend templates for matching temporal patterns

A technique based on the concept of a 'fuzzy trend template' has been developed to identify characteristic patterns in multiple time-series. The method has its foundation in fuzzy logic and allows for the intuitive and transparent description of 'templates', which preserve nuances of vagueness, temporal relationships and quantitative descriptors. Evaluation of fuzzy trend templates can provide both belief and plausibility information for use in diagnostic applications. The technique has been applied to the diagnosis of specific problems in anaesthesia and has demonstrated sensitivity and specificity of 95 and 65%, respectively. Evaluation of fuzzy trend templates is, computationally, relatively efficient and has allowed a real-time implementation. The technique has the potential to be useful in any domain that requires temporal pattern recognition based on linguistic rules.