Women in Medical Physics and Biomedical Engineering: past, present and future

Women in Medical Physics and Biomedical Engineering (WiMPBME) is a Task Group established in 2014 under the International Union of Physical and Engineering Scientists in Medicine (IUPESM). The group’s main role is to identify, develop, implement, and coordinate various tasks and projects related to women’s needs and roles in medical physics and biomedical engineering around the world.

The current paper summarizes the past, present and future goals and activities undertaken or planned by the Task group in order to motivate, nurture and support women in medical physics and biomedical engineering throughout their professional careers. In addition, the article includes the historical pathway followed by various women’s groups and subcommittees from 2004 up to the present day and depicts future aims to further these professions in a gender-balanced manner.

The Biggest Challenges Resulting from the COVID-19 Pandemic on Gender-Related Work from Home in Biomedical Fields—World-Wide Qualitative Survey Analysis

(1) Background: This paper aims to present and discuss the most significant challenges encountered by STEM professionals associated with remote working during the COVID-19 lockdowns. (2) Methods: We performed a qualitative analysis of 921 responses from professionals from 76 countries to the open-ended question: “What has been most challenging during the lockdown for you, and/or your family?” (3) Findings: Participants reported challenges within the immediate family to include responsibilities for school, childcare, and children’s wellbeing; and the loss of social interactions with family and friends. Participants reported increased domestic duties, blurred lines between home and work, and long workdays. Finding adequate workspace was a problem, and adaptations were necessary, especially when adults shared the same setting for working and childcare. Connectivity issues and concentration difficulties emerged. While some participants reported employers’ expectations did not change, others revealed concerns about efficiency. Mental health issues were expressed as anxiety and depression symptoms, exhaustion and burnout, and no outlets for stress. Fear of becoming infected with COVID-19 and uncertainties about the future also emerged. Pressure points related to gender, relationship status, and ethnicities were also evaluated. Public policies differed substantially across countries, raising concerns about the adherence to unnecessary restrictions, and similarly, restrictions being not tight enough. Beyond challenges, some benefits emerged, such as increased productivity and less time spent getting ready for work and commuting. Confinement resulted in more quality time and stronger relationships with family. (4) Interpretation: Viewpoints on positive and negative aspects of remote working differed by gender. Females were more affected professionally, socially, and personally than males. Mental stress and the feeling of inadequate work efficiency in women were caused by employers’ expectations and lack of flexibility. Working from home turned out to be challenging, primarily due to a lack of preparedness, limited access to a dedicated home-office, and lack of previous experience in multi-layer/multi-scale environments.

Infrared Thermography for the Evaluation of Inflammatory and Degenerative Joint Diseases: A Systematic Review

OBJECTIVE

Inflammation plays a central role in the pathophysiology of rheumatic diseases as well as in osteoarthritis. Temperature, which can be quantified using infrared thermography, provides information about the inflammatory component of joint diseases. This systematic review aims at assessing infrared thermography potential and limitations in these pathologies.

DESIGN

A systematic review was performed on 3 major databases: PubMed, Cochrane library, and Web of Science, on clinical reports of any level of evidence in English language, published from 1990 to May 2021, with infrared thermography used for diagnosis of osteoarthritis and rheumatic diseases, monitoring disease progression, or response to treatment. Relevant data were extracted, collected in a database, and analyzed for the purpose of this systematic review.

RESULTS

Of 718 screened articles 32 were found to be eligible for inclusion, for a total of 2094 patients. Nine studies reported the application to osteoarthritis, 21 to rheumatic diseases, 2 on both. The publication trend showed an increasing interest in the last decade. Seven studies investigated the correlation of temperature changes with osteoarthritis, 16 with rheumatic diseases, and 2 with both, whereas 2 focused on the pre-post evaluation to investigate treatment results in patients with osteoarthritis and 5 in patients with rheumatic diseases. A correlation was shown between thermal findings and disease presence and stage, as well as the clinical assessment of disease activity and response to treatment, supporting infrared thermography role in the study and management of rheumatic diseases and osteoarthritis.

CONCLUSIONS

The systematic literature review showed an increasing interest in this technology, with several applications in different joints affected by inflammatory and degenerative pathologies. Infrared thermography proved to be a simple, accurate, noninvasive, and radiation-free method, which could be used in addition to the currently available tools for screening, diagnosis, monitoring of disease progression, and response to medical treatment.

The impact of COVID-19 pandemic on gender-related work from home in STEM fields-Report of the WiMPBME Task Group

The COVID-19 pandemic has forced many people, including those in the fields of science and engineering, to work from home. The new working environment caused by the pandemic is assumed to have a different impact on the amount of work that women and men can do from home. Particularly, if the major burden of child and other types of care is still predominantly on the shoulders of women. As such, a survey was conducted to assess the main issues that biomedical engineers, medical physicists (academics and professionals), and other similar professionals have been facing when working from home during the pandemic. A survey was created and disseminated worldwide. It originated from a committee of International Union for Physical and Engineering Sciences in Medicine (IUPESM; Women in Medical Physics and Biomedical Engineering Task Group) and supported by the Union. The ethics clearance was received from Carleton University. The survey was deployed on the Survey Monkey platform and the results were analyzed using IBM SPSS software. The analyses mainly consisted of frequency of the demographic parameters and the cross-tabulation of gender with all relevant variables describing the impact of work at home. A total of 921 responses from biomedical professions in 76 countries were received: 339 males, 573 females, and nine prefer-not-to-say/other. Regarding marital/partnership status, 85% of males were married or in partnership, and 15% were single, whereas 72% of females were married or in partnership, and 26% were single. More women were working from home during the pandemic (68%) versus 50% of men. More men had access to an office at home (68%) versus 64% for women. The proportion of men spending more than 3 h on child care and schooling per day was 12%, while for women it was 22%; for household duties, 8% of men spent more than 3 h; for women, this was 12.5%. It is interesting to note that 44% of men spent between 1 and 3 h per day on household duties, while for women, it was 55%. The high number of survey responses can be considered excellent. It is interesting to note that men participate in childcare and household duties in a relatively high percentage; although this corresponds to less hours daily than for women. It is far more than can be found 2 and 3 decades ago. This may reflect the situation in the developed countries only-as majority of responses (75%) was received from these countries. It is evident that the burden of childcare and household duties will have a negative impact on the careers of women if the burden is not more similar for both sexes. It is important to recognize that a change in policies of organizations that hire them may be required to provide accommodation and compensation to minimize the negative impact on the professional status and career of men and women who work in STEM fields.

Solutions to Gender Balance in STEM Fields Through Support, Training, Education and Mentoring: Report of the International Women in Medical Physics and Biomedical Engineering Task Group

The aim of this article is to offer a view of the current status of women in medical physics and biomedical engineering, while focusing on solutions towards gender balance and providing examples of current activities carried out at national and international levels. The International Union of Physical and Engineering Scientists in Medicine is committed to advancing women in science and health and has several initiatives overseen by the Women in Medical Physics and Biomedical Engineering Task Group. Some of the main strategies proposed by the Task Group to attain gender balance are: (a) identify and promote female role models that achieve successful work-life balance, (b) establish programs to develop female leaders, (c) create opportunities for females to increase the international visibility within the scientific community, and (d) establish archives and databases of women in STEM.

Applying Data Preprocessing Methods to Predict Premature Birth

Data mining and pattern classification tools have{enabled prediction of several medical outcomes with high levels of accuracy. This is due to the capability of handling large datasets, even those with missing values. Preterm birth (PTB) can have damaging long-term effects for infants and rates have been increasing over the last two decades worldwide. The purpose of this work was to investigate whether preprocessing methods, when applied to two different prenatal datasets, can improve prediction accuracy of our software tool to predict PTB. The primary software used within this work was R. The software was used to deal with missing values and class imbalances found in these two datasets. The results show that in comparison to our past work, we have managed to increase the performance of the prediction tool using the metrics of sensitivity, specificity, and ROC values.

PPADS: Physician-PArent Decision-Support for Neonatal Intensive Care

Family-centered care is becoming the new standard for Neonatal Intensive Care Unit (NICU) patients. In support of this, we developed the Physician PArent Decision Support System (PPADS), which provides clinical updates and predictions of clinical outcomes for infants in the NICU to the neonatologists, and provides an aid to parents for making difficult decisions on the direction of care of their infant with the health care team. The tool may lead to earlier intervention, better allocation of resources, and reduction of the negative outcomes. The tool underwent a usability study with 8 parents whose infant survived the NICU stay and 5 neonatologists. Both parents and physicians thought the tool was easy to use, useful, and would help improve team communication. The next usability study will be with parents whose infant died while in the NICU, and then conduct a randomized prospective study with parents who have a sick infant admitted to the NICU.

Development and usability testing of a parent decision support tool for the neonatal intensive care unit

In this paper we present the development and evaluation of a parent decision support tool for a neonatal intensive care unit (NICU), known as PPADS or Physician and Parent Decision Support. The NICU interprofessional (IP) team uses advanced technology to care for the sickest infants in the hospital, some at the edge of viability. Many difficult care decisions are made daily for this vulnerable population. The PPADS tool, a computerized decision support system, aims to augment current NICU decision-making by helping parents make more informed decisions, improving physician-parent communication, increasing parent decision-making satisfaction, decreasing conflict, and increasing decision efficiency when faced with ethically challenging situations. The development and evaluation of the PPADS tool followed a five step methodology: assessing the clinical environment, establishing the design criteria, developing the system design, implementing the system, and performing usability testing. Usability testing of the PPADS tool with parents of neonates who have graduated (survived) from a tertiary level NICU demonstrates the usefulness and ease of use of the tool.

Assessment of piano-related injuries using infrared imaging

Playing the piano is a repetitive task that involves the use of the hands and the arms. Pain related to piano-playing can result in extending the tissues and ligaments of the hands and arms beyond their mechanical tolerance. Infrared imaging records the skin temperature and produces a thermal map of the imaged body part; small variations in the skin temperature could be a sign of inflammation or stress of the tissues. In this paper, we used statistical analysis to examine the difference in hand and arm temperatures of pianists with pain and pianists without pain related to piano-playing. We found that there is a statistically significant difference in hand temperatures between the two populations, but not in the lower arm and upper arm temperatures.

Estimating rheumatoid arthritis activity with infrared image analysis

This work describes the development of a new diagnostic tool to assess the severity of rheumatoid arthritis (RA) using infrared image collection and analysis. Early work showed that the temperature distribution of joints of hands and knees of patients with RA was statistically significantly different from that of normal subjects. Current work identified ankles as also significant for an assessment of RA. Moreover, the patients were classified in three levels of RA severity (High, Medium, and Low) using a C5.0 decision tree classifier with excellent results: Sensitivity (true positive cases) of 96 % and a specificity (true negative cases) of 92%. Future work will automate the image analysis and test clinically by comparing to MR as ground truth.

Preliminary results on the effect of sensor position on unobtrusive rollover detection for sleep monitoring in smart homes

Older adults experience increased sleep movement disorders and sleep fragmentation, and these are associated with serious health consequences such as falls. Monitoring sleep fragmentation and restlessness in older adults can reveal information about their daily and long-term health status. Long-term home monitoring is only realistic within the contact of unobtrusive, non-contact sensors. This paper presents exploratory work using the pressure sensor array as an instrument for rollover detection. The sensor output is used to calculate a center of gravity signal, from which five features are extracted. These features are used in a decision tree to classify detected movements in two categories; rollovers and other movements. Rollovers were detected with a sensitivity and specificity of 82% and 100% respectively, and a Mathew's correlation coefficient of 0.86 when data from all sensor positions were included. Intrapositional and interpositional effects of movements on sensors placed throughout the bed are described.

Simulated central apnea detection using the pressure variance

This paper presents use of an unobtrusive pressure sensor array for simulated central apnea detection. Data was collected from seven volunteers who performed a series of regular breathing and breath holding exercises to simulate central apneas. Results of the feature extraction from the breathing signals show that breathing events may be differentiated with epoch based variance calculations. Two approaches were considered: the single sensor approach and the multisensor vote approach. The multisensor vote approach can decrease false positives and increase the value of Matthew's Correlation Coefficient. The effect of lying position on correct classification was investigated by modifying the multisensor vote approach to reduce false positives segments caused by the balistocardiogram signal and as such increase sensitivity while maintaining a low false positive rate. Intersubject classification results had low variability in both approaches.

Complimentary artificial neural network approaches for prediction of events in the neonatal intensive care unit

In the neonatal intensive care unit, the early and accurate prediction of mortality, length of stay and duration of ventilation can improve decision making. For physiological events, non-linear prediction models generally out-perform statistical-based approaches, as was confirmed in these experiments. For three medical outcomes, the maximum-likelihood (ML) approximation was used in conjunction with a gradient descent artificial neural network (ANN) prototype to create models with risk estimation ranges. The ML ANN showed that the ML estimation function was successful at creating variable sensitivity models for three important outcomes. The flexibility of the ML ANN in terms of output values differentiates it from the more traditional ANN.

Survey of clinical engineering effectiveness in developing world hospitals: equipment resources, procurement and donations

This paper presents preliminary findings of a study of clinical engineering effectiveness within developing world hospitals. To date, 169 responses have been collected from 43 countries, primarily from Africa, Latin America and Asia, with some representation from the Middle East and Eastern Europe as well. Data is presented on: 1) hospital and clinical engineering department profiles; 2) human and equipment resources; and 3) equipment procurement and donation processes, with a focus on the role of the clinical engineering department. This is the first study to collect and analyze data on the complexity and state of hospital equipment across the developing world; additionally it is the first to collect significant responses from Africa. Prior to this study, only 10 developing countries had been profiled in international studies.

Integration of new technology in a legacy system for collecting medical data - challenges and lessons learned

Integrating new technology into a legacy medical system can be very challenging. Completely new systems cannot always be built due to the high cost of medical equipment, thus integrating some new technology into an existing system may be required. This paper looks at the issues and challenges surrounding the integration of new components into a legacy system for collecting medical data. We discuss how the issues were solved, the lessons learned, and how future upgrades can be made more easily.

Investigation into the past and future of women in science and engineering

Covering the Ancient Greek era, the Middle Ages, the Renaissance, the Enlightenment, the 19th and 20th C., this paper explores the visions of the abilities of women, their access to education, and their roles in these epochs. Recent data on the participation rate of women in science and engineering, the culture in these fields, and strategies to increase their presence are discussed. The paper ends with a discussion on how science and engineering could benefit from integrating and valuing a blend of masculine and feminine perspectives. Biomedical engineering as a field frequently chosen by women is mentioned.

The relationship between intellectual disability, Indigenous status and risk of reoffending in juvenile offenders on community orders

BACKGROUND

Intellectual disability (ID), age and aboriginal status have been independently implicated as risk factors for offending to varying degrees. This study examined the relationship between age, ID and the Indigenous status of juvenile offenders. It also examined the outcomes of the sample's offending in terms of court appearances and sentencing, criminogenic needs and risk of reoffending.

METHOD

The sample comprised 800 juvenile offenders on community orders of whom 19% were Indigenous, who completed the New South Wales Young People on Community Order Health Survey between 2003 and 2005. Risk and criminogenic needs were evaluated using the Youth Level of Service/Case Management Inventory (Australian Adaptation) (YLS/CMI: AA).

RESULTS

Those with an ID were found to have a higher risk of reoffending than those without an ID. Those with an ID were also more likely to be younger and Indigenous. For Indigenous young offenders, there was no difference between those with and without an ID in risk category allocation or number of court dates. For non-Indigenous young offender, those with an ID had higher risk scores and more court dates.

CONCLUSIONS

This study provided evidence that Indigenous status may play a significant role in the relationship between ID and offending in juvenile offenders on community orders. These findings have clear implications for the 'risk', 'needs' and 'responsivity' principles of offender classification for treatment. Emphasis is placed on the requirement for addressing the needs of Indigenous juvenile offenders with an ID.

Segmentation and landmark identification in infrared images of the human body

The segmentation and landmark identification in infrared images of the human body are key steps in a computerized processing of large database of thermal images. The segmentation task is especially challenging due to specific characteristics of thermal images. Few papers deal with segmentation techniques for clinical infrared images and available segmentation methods (e.g. for breast or military thermal images) do not perform well on other types of images. This paper presents a few strategies for the automated segmentation and registration of anatomical landmarks on thermal images of arms and hands. The segmentation method is based on mathematical morphological operations and simple rule based processing easily available through prior knowledge about the objects of interest.

Bayesian-based diagnostic decision-support for pediatrics

The goal of this project was to develop a Pediatric Decision Support system (PDS) that allows a resident physician to define a patient case based on symptoms (diagnostic signs and test results) and generates a list of possible diagnoses based on the World Health Organization's International Classification of Diseases (ICD10). The intent is to improve the diagnostic approach taken by resident physicians and eventually become a training tool in medical education programs.

Imputation of missing values by integrating neural networks and case-based reasoning

Missing values in a medical database present a problem when trying to develop a prediction model for a broad range of patients, if the data are not missing at random. We present a data imputation approach for physiologic parameters that incorporates individualized case information into the imputed values. We replaced missing values in a neonatal intensive care unit (NICU) database with relevant data by integrating aspects of artificial neural networks (ANNs) and case-based reasoning (CBR).

Women in biomedical engineering and health informatics

A valuable session for anyone whether student or not, interested in learning more about Biomedical Engineering and Health Informatics as a career choice for women. Prominent women within the domains Biomedical Engineering and Health Informatics will present their research and their humanitarian interests that motivate them. Utilise the fantastic networking opportunity that will conclude this session to build and establish new professional networks with other women interested in your fields of expertise. Bring your contact details and be ready to make new contacts that are relevant for you.

Analysis of breast thermography with an artificial neural network

Thermal imaging has been used for early breast cancer detection and risk prediction since the sixties. Examining thermograms for abnormal hyperthermia and hyper-vascularity patterns related to tumor growth is done by comparing images of contralateral breasts. Analysis can be tedious and challenging if the differences are subtle. The advanced computer technology available today can be utilized to automate the analysis and assist in decision-making. In our study, computer routines were used to perform ROI identification and image segmentation of infrared images recorded from 19 patients. Asymmetry analysis between contralateral breasts was carried out to generate statistics that could be used as input parameters to a backpropagation ANN. A simple 1-1-1 network was trained and employed to predict clinical outcomes based on the difference statistics of mean temperature and standard deviation. Results comparing the ANN output with actual clinical diagnosis are presented. Future work will focus on including more patients and more input parameters in the analysis. Performance of ANN network can be studied to select a set of parameters that would best predict the presence of breast cancer.

Evolution of the surface temperature of pianists' arm muscles using infrared thermography

Musculoskeletal disorders are very frequent among musicians. Diagnosis is difficult due to the lack of objective tests and the multiplicity of symptoms. Treatment is also problematic and often requires that the musician stop playing. Most of these disorders are inflammatory in nature, and therefore involve temperature changes in the affected regions. Temperature measurements were recorded with an infrared camera. In this paper we present an overview of the temperature measurements made in the arms of 8 pianists during regular piano practice sessions.

An Analysis Of Chirpp Data To Predict Severe ATV Injuries Using Artificial Neural Networks

This paper describes the development of a tool to predict the severity of all-terrain vehicle (ATV) injuries using artificial neural networks (ANNs). The data was obtained from the Canadian Hospitals Injury Reporting and Prevention Program (CHIRPP). The main objective of the study was to identify the contribution of input variables in predicting severe injury or death. An ANN architecture with 9 hidden nodes and one hidden layer resulted in optimal performance: a logarithmic-sensitivity index of 0.099, sensitivity of 47.3%, specificity of 80.8%, correct classification rate (CCR) of 68.6% and receiver operating curve (ROC) area of 0.711. The minimum data set that can help predict injury severity is discussed.

Survey of clinical engineering in developing countries and model for technology acquisition and diffusion

An international survey was conducted in 2003 to assess the status of clinical engineering services delivered to hospitals in developing countries. Data was collected from Asia, Africa, Latin America and Mexico. The responses were compared to two previous studies done in industrialized countries. A model of medical technology acquisition and diffusion is presented.

Predicting clinical outcomes for newborns using two artificial intelligence approaches

Two different approaches, based on artificial neural networks (ANN) and fuzzy logic, were used to predict a number of outcomes of newborns: How they would be delivered, their 5 minute Apgar score, and neonatal mortality. The goal was to assess whether the methods would be comparable or whether they would perform differently for different outcomes. The results were comparable for Correct Classification Rate (CCR) and Specificity (true negative cases). Sensitivity (true positive cases) was slightly higher for the back-propagation feed-forward ANN than using the Fuzzy-Logic Classifier (FLC). Since this is one single database and a very large one, it is possible that the FLC would perform better than the ANN for very small databases, as shown by some of the co-authors in the past. The next step will be to test a small database with both methods to assess strengths and weaknesses with the intent to use both if needed with some medical data in the future.

Towards ethical decision support and knowledge management in neonatal intensive care

Recent studies in neonatal medicine, clinical nursing, and cognitive psychology have indicated the need to augment current decision-making practice in neonatal intensive care units with computerized, intelligent decision support systems. Rapid progress in artificial intelligence and knowledge management facilitates the design of collaborative ethical decision-support tools that allow clinicians to provide better support for parents facing inherently difficult choices, such as when to withdraw aggressive treatment. The appropriateness of using computers to support ethical decision-making is critically analyzed through research and literature review. In ethical dilemmas, multiple diverse participants need to communicate and function as a team to select the best treatment plan. In order to do this, physicians require reliable estimations of prognosis, while parents need a highly useable tool to help them assimilate complex medical issues and address their own value system. Our goal is to improve and structuralize the ethical decision-making that has become an inevitable part of modern neonatal care units. The paper contributes to clinical decision support by outlining the needs and basis for ethical decision support and justifying the proposed development efforts.

Automated image segmentation for breast analysis using infrared images

In order to realize a fully automated thermogram analysis package for breast cancer detection, it is necessary to identify the region of interest in the thermal image prior to analysis. A nearly fully automated approach is outlined that is able to successfully locate the breast regions in most of the images analyzed. The approach consists of a sequence of Canny edge detectors to determine the body boundaries and to isolate the most likely candidates for the bottom breast boundary. Three different strategies for identifying the bottom breast boundary are investigated: a variation of the Hough transform to identify the curved edges in the image, an algorithm used to detect the longest connected edges that are not part of the body boundary, and a third approach involving the density of detected edges in the breast region. The last two methods show great promise in successfully segmenting the breasts.

Towards a web services infrastructure for perinatal, obstetrical, and neonatal clinical decision support

This paper presents the design of a unifying infrastructure for clinical decision support systems (CDSSs) and medical data relating to the perinatal life cycle. The diverse CDSSs designed for deployment within the perinatal life cycle to improve care, such as Artificial Neural Networks and Case-Based Reasoners, are integrated using the eXtended Markup Language (XML) and are subsequently offered as a secure web service. These web services are accessible from anywhere within the hospital information system and from remote authorized sites. The goal of such an infrastructure is to provide integrated CDSS processing in a complex distributed environment, in order to support real-time physician decision-making. This design provides a novel web services infrastructure implementation and offers a strong case study for deploying and evaluating the web services paradigm within a health care environment.

Predicting high-risk preterm birth using artificial neural networks

A reengineered approach to the early prediction of preterm birth is presented as a complimentary technique to the current procedure of using costly and invasive clinical testing on high-risk maternal populations. Artificial neural networks (ANNs) are employed as a screening tool for preterm birth on a heterogeneous maternal population; risk estimations use obstetrical variables available to physicians before 23 weeks gestation. The objective was to assess if ANNs have a potential use in obstetrical outcome estimations in low-risk maternal populations. The back-propagation feedforward ANN was trained and tested on cases with eight input variables describing the patient's obstetrical history; the output variables were: 1) preterm birth; 2) high-risk preterm birth; and 3) a refined high-risk preterm birth outcome excluding all cases where resuscitation was delivered in the form of free flow oxygen. Artificial training sets were created to increase the distribution of the underrepresented class to 20%. Training on the refined high-risk preterm birth model increased the network's sensitivity to 54.8%, compared to just over 20% for the nonartificially distributed preterm birth model.

Risk factors for Apgar score using artificial neural networks

Artificial Neural Networks (ANNs) have been used in identifying the risk factors for many medical outcomes. In this paper, the risk factors for low Apgar score are introduced. This is the first time, to our knowledge, that the ANNs are used for Apgar score prediction. The medical domain of interest used is the perinatal database provided by the Perinatal Partnership Program of Eastern and Southeastern Ontario (PPPESO). The ability of the feed forward back propagation ANNs to generate strong predictive model with the most influential variables is tested. Finally, minimal sets of variables (risk factors) that are important in predicting Apgar score outcome without degrading the ANN performance are identified.

Predicting probability of mortality in the neonatal intensive care unit

Artificial neural networks can be trained to predict outcomes in a neonatal intensive care unit (NICU). This paper expands on past research and shows that neural networks trained by the maximum likelihood estimation criterion will approximate the ;a posteriori probability' of NICU mortality. A gradient ascent method for the weight update of three-layer feed-forward neural networks was derived. The neural networks were trained on NICU data and the results were evaluated by performance measurement techniques, such as the Receiver Operating Characteristic Curve and the Hosmer-Lemeshow test. The resulting models applied as mortality prognostic screening tools are presented.

Identifying risk factors for two complication types for neonatal intensive care patients (NICU)

This paper discusses the results of applying artificial neural networks to predicting complication for neonatal intensive care patients. Risk factors that lead to necrotizing entero-colitis or broncho-pulmonary dysplasia were identified. Future work will expand this work to other outcomes and add probability information to the estimations.

Conceptual Framework of Knowledge Management for Ethical Decision-Making Support in Neonatal Intensive Care

This research is built on the belief that artificial intelligence estimations need to be integrated into clinical social context to create value for health-care decisions. In sophisticated neonatal intensive care units (NICUs), decisions to continue or discontinue aggressive treatment are an integral part of clinical practice. High-quality evidence supports clinical decision-making, and a decision-aid tool based on specific outcome information for individual NICU patients will provide significant support for parents and caregivers in making difficult "ethical" treatment decisions. In our approach, information on a newborn patient's likely outcomes is integrated with the physician's interpretation and parents' perspectives into codified knowledge. Context-sensitive content adaptation delivers personalized and customized information to a variety of users, from physicians to parents. The system provides structuralized knowledge translation and exchange between all participants in the decision, facilitating collaborative decision-making that involves parents at every stage on whether to initiate, continue, limit, or terminate intensive care for their infant.

Improvement and automation of artificial neural networks to estimate medical outcomes

The lengthy process of manually optimizing a feedforward backpropagation artificial neural network (ANN) provided the incentive to develop an automated system that could fine-tune the network parameters without user supervision. A new stopping criterion was introduced--the logarithmic-sensitivity index--that manages a good balance between sensitivity and specificity of the output classification. The automated network automatically monitored the classification performance to determine when was the best time to stop training-after no improvement in the performance measure (either highest correct classification rate, lowest mean squared error or highest log-sensitivity index value) occurred in the subsequent 500 epochs. Experiments were performed on three medical databases: an adult intensive care unit, a neonatal intensive care unit and a coronary surgery patient database. The optimal network parameter settings found by the automated system were similar to those found manually. The results showed that the automated networks performed equally well or better than the manually optimized ANNs, and the best classification performance was achieved using the log-sensitivity index as a stopping criterion.

Quantitative assessment of pain-related thermal dysfunction through clinical digital infrared thermal imaging

Background

The skin temperature distribution of a healthy human body exhibits a contralateral symmetry. Some nociceptive and most neuropathic pain pathologies are associated with an alteration of the thermal distribution of the human body. Since the dissipation of heat through the skin occurs for the most part in the form of infrared radiation, infrared thermography is the method of choice to study the physiology of thermoregulation and the thermal dysfunction associated with pain. Assessing thermograms is a complex and subjective task that can be greatly facilitated by computerised techniques.

Methods

This paper presents techniques for automated computerised assessment of thermal images of pain, in order to facilitate the physician's decision making. First, the thermal images are pre-processed to reduce the noise introduced during the initial acquisition and to extract the irrelevant background. Then, potential regions of interest are identified using fixed dermatomal subdivisions of the body, isothermal analysis and segmentation techniques. Finally, we assess the degree of asymmetry between contralateral regions of interest using statistical computations and distance measures between comparable regions.

Results

The wavelet domain-based Poisson noise removal techniques compared favourably against Wiener and other wavelet-based denoising methods, when qualitative criteria were used. It was shown to improve slightly the subsequent analysis. The automated background removal technique based on thresholding and morphological operations was successful for both noisy and denoised images with a correct removal rate of 85% of the images in the database. The automation of the regions of interest (ROIs) delimitation process was achieved successfully for images with a good contralateral symmetry. Isothermal division complemented well the fixed ROIs division based on dermatomes, giving a more accurate map of potentially abnormal regions. The measure of distance between histograms of comparable ROIs allowed us to increase the sensitivity and specificity rate for the classification of 24 images of pain patients when compared to common statistical comparisons.

Conclusions

We developed a complete set of automated techniques for the computerised assessment of thermal images to assess pain-related thermal dysfunction.

Weight-elimination neural networks applied to coronary surgery mortality prediction

The objective was to assess the effectiveness of the weight-elimination cost function in improving classification performance of artificial neural networks (ANNs) and to observe how changing the a priori distribution of the training set affects network performance. Backpropagation feedforward ANNs with and without weight-elimination estimated mortality for coronary artery surgery patients. The ANNs were trained and tested on cases with 32 input variables describing the patient's medical history; the output variable was in-hospital mortality (mortality rates: training 3.7%, test 3.8%). Artificial training sets with mortality rates of 20%, 50%, and 80% were created to observe the impact of training with a higher-than-normal prevalence. When the results were averaged, weight-elimination networks achieved higher sensitivity rates than those without weight-elimination. Networks trained on higher-than-normal prevalence achieved higher sensitivity rates at the cost of lower specificity and correct classification. The weight-elimination cost function can improve the classification performance when the network is trained with a higher-than-normal prevalence. A network trained with a moderately high artificial mortality rate (artificial mortality rate of 20%) can improve the sensitivity of the model without significantly affecting other aspects of the model's performance. The ANN mortality model achieved comparable performance as additive and statistical models for coronary surgery mortality estimation in the literature.

Extending ventilation duration estimations approach from adult to neonatal intensive care patients using artificial neural networks

In earlier work, the research group successfully used artificial neural networks (ANNs) to estimate ventilation duration for adult intensive care unit (ICU) patients. The ANNs performed well in terms of correct classification rate (CCR) and average squared error (ASE) classifying the outcome into two classes: whether patients were ventilated for less than/equal to or for more than 8 h (< or >). The objective of new work was to apply this adult model to the estimation of ventilation with neonatal ICU (NICU) patient records. The performance obtained with the neonatal patients was comparable to that previously found with the adult database, again as measured in terms of a maximum CCR and a minimum ASE. The effectiveness of using the weight-elimination technique in controlling overfitting was again validated for the neonatal patients as it had been for our adult patients. It was concluded that the approach developed for ICU adult patients was also successfully applied to a different medical environment: neonatal ICU patients.

Influence of missing values on artificial neural network performance

The problem of databases containing missing values is a common one in the medical environment. Researchers must find a way to incorporate the incomplete data into the data set to use those cases in their experiments. Artificial neural networks (ANNs) cannot interpret missing values, and when a database is highly skewed, ANNs have difficulty identifying the factors leading to a rare outcome. This study investigates the impact on ANN performance when predicting neonatal mortality of increasing the number of cases with missing values in the data sets. Although previous work using the Canadian Neonatal Intensive Care Unit (NICU) Network s database showed that the ANN could not correctly classify any patients who died when the missing values were replaced with normal or mean values, this problem did not arise as expected in this study. Instead, the ANN consistently performed better than the constant predictor (which classifies all cases as belonging to the outcome with the highest training set a priori probability) with a 0.6-1.3% improvement over the constant predictor. The sensitivity of the models ranged from 14.5-20.3% and the specificity ranged from 99.2- 99.7%. These results indicate that nearly 1 in 5 babies who will eventually die are correctly classified by the ANN, and very few babies were incorrectly identified as patients who will die. These findings are important for patient care, counselling of parents and resource allocation.

Clinical decision support systems for intensive care units: using artificial neural networks

The paper provides an overview of applications of artificial neural networks (ANNs) to various medical problems, with a particular focus on the intensive care unit environment (ICU). Several technical approaches were tested to see whether they improve the ANN performance in estimating medical outcomes and resource utilization in adult ICUs. These experiments include: (1) use of the weight-elimination cost function; (2) use of 'high' and 'low' nodes for input variables; (3) verifying the effect of the total number of input variables on the results; (4) testing the impact of the value of the constant predictor on the performance of the ANNs. The developments presented intend to help medical and nursing personnel to assess patient status, assist in making a diagnosis, and facilitate the selection of a course of therapy.

Clinical decision-support systems for intensive care units using case-based reasoning

The artificial intelligence approach used in this work focusses on case-based reasoning techniques for the estimation of medical outcomes and resource utilization. The systems were designed with a view to help medical and nursing personnel to assess patient status, assist in making a diagnosis, and facilitate the selection of a course of therapy. The initial prototype provided information on the closest-matching patient cases to the newest patient admission in an adult intensive care unit (ICU). The system was subsequently re-designed for use in a neonatal ICU. The results of a short clinical pilot evaluation performed in both adult and neonatal units are reported and have led to substantial improvement of the prototype. Future work will include longer-term clinical trials for both adult and neonatal ICUs, once all the software changes have been made to both prototypes in response to the comments of the users made during the preliminary evaluations. To date, the results are very encouraging and physician interest in the potential clinical usefulness of these two systems remains high, and particularly so in the new testing environment in Ottawa.

Decision-support and intelligent tutoring systems in medical education

One of the challenges in medical education is to teach the decision-making process. This learning process varies according to the experience of the student and can be supported by various tools. In this paper we present several approaches that can strengthen this mechanism, from decision-support tools, such as scoring systems, Bayesian models, neural networks, to cognitive models that can reproduce how the students progressively build their knowledge into memory and foster pedagogic methods.

Selective sampling to overcome skewed a priori probabilities with neural networks

Highly skewed a priori probabilities present challenges for researchers developing medical decision aids due to a lack of information on the rare outcome of interest. This paper attempts to overcome this obstacle by artificially increasing the mortality rate of the training sets. A weight pruning technique called weight-elimination is also applied to this coronary artery bypass grafting (CABG) database to assess its impact on the artificial neural network's (ANN) performance. The results showed that increasing the mortality rate improved the sensitivity rates at the cost of the other performance measures, and the weight-elimination cost function improved the sensitivity rate without seriously affecting the other performance measures.