Role of artificial neural networks in prediction of survival of burn patients—a new approach
Introduction
A burn injury is a disastrous trauma and can have very wide ranging complications making such cases difficult to manage and treat. Severe morbidity in victims is observed and mortality rates may be high. Burn patients generally have a long period of stay in the hospital, approximately 1.5 days per total body surface area (TBSA).
Outcome may be diverse. Some patients may have healing of wounds and develop minimal scars. Others may develop severe contractures, hypertrophic scars and various deformities. Some unfortunate victims may have suffered inhalation injury, severe chemical or electrical injuries. Victims may develop wound infections and septicaemia and eventually die as a result of these complications.
Several factors influence outcome among patients including age, TBSA, presence of inhalation injury, previous medical conditions, infections, pneumonia and septicaemia, depth of burn wounds and so on.
At the first examination the physician is usually confronted with the commonly encountered questions:
“Can the patient overcome this severe condition?”
“Will he live?”
“What is the percentage of his prognosis?”
Those questions are very difficult, challenging to the intellect and time consuming for the physician in the evaluation of the patient and the assessment of the probability of survival. Some linear statistical methods such as linear regression may help the physician in some aspects of problem, but evaluation of the whole condition of patient is generally not within the capability of these statistical methods.
Computer software and programs can help the physician to address the problem in three different ways:
First: linear connection software (Fig. 1), this is characterized by simple forward connection and/or simple “if … then phrases” can answer very simple questions with only “yes–no” type answers.
Second: expert systems (Fig. 2), these systems can save numerous phrases and consider several conditions or “if … then phrases” and may consider positive and negative influences. In this way answers to some complex questions can be found. These systems obviously need several previously defined phrases (or facts) and someone should write or input these facts using a special computer language into the system. The writer must consider all situations which may occur in the processing of the question and also consider very rare conditions (this is called supervised training). This means that these systems are very time consuming for development time before compiling and running. Some conditions may be omitted or neglected. This will reduce the reliability of the system.
Third: intelligent systems (Fig. 3), these systems simulate processes and systems in the human brain and neuronal connections, and can learn and judge. These systems have several units or neurons which resemble the neural cells in brain, and are called “artificial neural network (ANN)”. Like the brain, ANN can recognize patterns, manage data and most significantly “learn” in a way which simulates human intelligence. ANN constantly improves its functional accuracy, it does not need formulated factual input. These systems are used to supplement and even replace experts. They can classify and interpret various forms of medical data. Since predictive ability is a major advantage of ANN, such systems have the potential to assist with description of morbidity and help with mortality.
In this study, in the first instance retrospectively data was extracted retrospectively (including outcome) from all of burn patients files who were admitted during 1 year (1996–1997) and interpreted with traditional linear statistics such as logistic regression, Kaplan–Meier, and Cox proportional hazard in order to calculate mortality rate of patients.
In a second stage, an ANN system was constructed and patients were divided into two groups. One group served as a training group and the other as test group to evaluate total accuracy and sensitivity of the network.
Section snippets
Materials and methods
Fifteen different observations including: age, sex, TBSA, data of admission (month and season of year the burn injury has been incorporated, since burn injury is more common and often more extensive in the cold season), lapse time (time from burn to admission to hospital), refereed or non-refereed status, inhalation injury, haematology and biochemistry lab values, medical outcome, number and type of surgical episodes (debridement or skin graft) were obtained from medical files of a major
Results
The 2096 patients admitted during a 1 year in Motahary Burn Center required a variety of different burn management regimes including burn scar repair and reconstructive surgery. Among them 1082 patients were admitted because of acute burns, 40% were male and 60% female.
Age ranged from 6 months to 100 years with a mean age of 27.1 years. Most patients were in the age group 20–30 years (27%) and 10–15 years (14%) (Fig. 6).
Lapse times according to refereed and non-refereed status are shown in
Discussion
There is much morbidity associated with a major burn and many complications in the course of their treatment influence outcome [1], [3], [4], [17], [18]. Computing the minimum or maximum influence on burn patients of the various factors involved and their relative influence on each other is a very difficult task and may be impossible. Some very expert physicians in this area may reach and have the capability to assess the patient and roughly predict their outcome, but most of others, especially
Conclusion
ANNs exploit the massive parallel local processing and distributed representation properties that are believed to exist in the brain. A complex situation such as that afier a major burn injury is a most appropriate situation in which ANNs can be tested, developed and used.
This network can be utilized to assist the physician working in a Burn Care Unit.
Acknowledgements
The authors are very thankful to Mrs. Gevert and Mrs. Kazemi for their help in processing of this study and article.
References (21)
The state of burn care: past, present and future
Burns
(1994)- et al.
Artificial intelligence in the diagnosis of low back pain
Othop. Clin. North Am.
(1991) Advances in the treatment of burn patients
Burns
(1997)- Cotton P. chaos, other nonlinear dynamics research may have answers, application for clinical medicine, JAMA...
- EL Dabaf A. Burn variables influencing survival: a study of 144 patient, Burns...
The 1997 clinical research award health outcome for burn survivors
J. Burn Care Rehab.
(1997)Chaos predicting the unpredictable
BMJ
(1991)- et al.
Neural networks: what are they
Anna. Intern. Med.
(1991) - et al.
Altematice stataisicla methods to use with survival data
Nurs. Res.
(1996) Prediction of trauma mortality using an neural network
Am. Surh.
(1997)