DSS 1-01.pdf

BME 5119 DECISION SUPPORT SYSTEMS [4 0 0 4] Syllabus Active Knowledge based system, which is developed using evidence-based medicine, with the computerized approach to improve patient care, Knowledge use, management, and representation. CDS methodology/functionality (disease / s...

BME 5119 DECISION SUPPORT SYSTEMS [4 0 0 4] Syllabus Active Knowledge based system, which is developed using evidence-based medicine, with the computerized approach to improve patient care, Knowledge use, management, and representation. CDS methodology/functionality (disease / specialty based) and CDS standards. Computer-based Clinical Decision Support: Overview, Status, and Challenges, Features of CDSS, Mathematical Foundations of Decision Support Systems, Data Mining and Clinical Decision Support Systems, Usability and Clinical Decision Support, Architectures for Clinical Decision Support. Role of Quality Measurement and Reporting Feedback as a Driver for Care Improvement, Decision support delivered using the outpatient electronic health record, Knowledge for Clinical Decision Support: Statistical and Machine Learning Techniques, Evidence-Based Medicine, statistical methods in meta-analysis, Meta-analysis of complex datasets. Big Data and Population-Based Decision Support, Clinical Decision Support for Personalized Medicine, Decision Rules and Expressions, Formal methods for modelling. Best Practices for Implementation of Clinical Decision Support, National Policies on the Use of Clinical Decision Support, Ethical and Legal Issues in Decision Support, Evaluation of Clinical Decision Support, Adoption of Clinical Decision Support system, Decision Support for Patients, Diagnostic Decision Support Systems, Applications. SDL: SOA Services and Capabilities Needed for CDS, Healthcare Services Specification Project Evaluation of Clinical Decision Support, Strategies for CDSS Evaluation, Types of CDSS Evaluations, Types of Outcomes Assessed in CDSS Evaluations Approach to Conducting an Evaluation of a CDSS, Challenges Associated with Evaluation of CDSS Adoption of Clinical Decision Support system References 1. Myriam Hunink and Paul Glaziou, “Decision Making in Health and Medicine”, 6th print 2007; Publisher: Cambridge University Press 2. *Berner, Eta S, “Clinical Decision Support Systems: Theory and Practice, (Ed.), 2nd ed., 2007, Publisher: Springer, Health Informatics Series (springer.com NOT springerpub.com) 3. Osheroff, Pifer, Teich, Sittig, Jenders, 2005; Publisher: Health Information and Management Systems Society (HIMSS) 4. *Robert Greenes Clinical Decision Support, The Road to Broad Adoption, 2nd Edition – March 26, 2014, eBook ISBN: 9780128005422, Hardcover ISBN: 9780123984760, Elsevier Program Objectives (POs) PO1- Attain the ability by utilizing fundamentals of basic science, engineering and medical science to work in a multidisciplinary environment of engineering and healthcare PO2- An ability to independently manage research problem pertaining to healthcare and gain competence in writing and presenting technical documents PO3- Attain higher level knowledge than bachelor and demonstrate professionalism and right ethical attitude. Program Specific Objectives (PSOs) PSO1- Identify analyze and resolve problems pertaining to healthcare PSO2- Develop the ability and required skills in multidisciplinary environment to translate acquired knowledge in developing diagnostic and therapeutic devices /tools for healthcare improvement. Basic Idea Clinical decision support systems (CDSS) are computer systems designed to impact clinician decision making about individual patients at the point in time that these decisions are made. Prevention of medical errors - computer-based physician order entry (CPOE) systems, coupled with CDSS, have been proposed as a key element of systems’ approaches to improving patient safety. Health Information Technology system; that is designed to provide physicians and other health professionals with clinical decision support Assistance with clinical decision-making task when dealing with the patients Narrow down the possible diagnosis, Software provides information support  Decision support systems have been incorporated in healthcare information systems for a long time, but these systems usually have supported retrospective analyses of financial and administrative data. Sophisticated data mining approaches have been proposed for similar retrospective analyses of both administrative and clinical data. CDSS differ among themselves in the timing at which they provide support (before, during, or after the clinical decision is made) and how active or passive the support is, that is, whether the CDSS actively provides alerts or passively responds to physician input or patient-specific information. CDSS vary in how easy they are for busy clinicians to access  CDSS also differ in whether the information provided is general or specialty-based. some of the originally noncommercial systems are now being more widely marketed, and other vendors are beginning to incorporate CDSS into their computer-based patient records and physician order entry systems.  CDSS is whether they are knowledge-based systems, or nonknowledge-based systems that employ machine learning and other statistical pattern recognition approaches What is CDSS? Tools used to help clinicians understand data Multiple types of alerts, there are reminders or There are alerts that have tools that help with a certain kind of patient to take care of them or determine their next steps meant to keep patients safe Knowledge-Based Clinical Decision Support Systems expert systems research: aim was to build a computer program that could simulate human thinking Earliest systems were diagnostic decision support systems to assist the clinician in his or her own decision making. The system was expected to provide information for the user, rather than to come up with “the answer,” as was the goal of earlier expert systems The user - to filter that information and to discard erroneous or useless information. The user - to be active and to interact with the system, rather than just be a passive recipient of the output  Parts of Clinical Decision Support Systems 1. Knowledge-Based 2. Inference engine or reasoning mechanism 3. Mechanism to communicate with User Parts of Clinical Decision Support Systems knowledge base consists of compiled information that is often, but not always, in the form of if–then rules Example: IF a new order is placed for a particular blood test that tends to change very slowly, AND IF that blood test was ordered within the previous 48 hours, THEN alert the physician the rule is designed to prevent duplicate test ordering Other types of knowledge bases might include probabilistic associations of signs and symptoms with diagnoses or known drug–drug or drug–food interactions.  inference engine or reasoning mechanism contains the formulas for combining the rules or associations in the knowledge base with actual patient data.  Communication mechanism, a way of getting the patient data into the system and getting the output of the system to the user who will make the actual decision In some stand-alone systems, the patient data need to be entered directly by the user In most of the CDSS incorporated into electronic medical records (EMR) systems, the data are already in electronic form and come from the computer-based patient record, where they were originally entered by the clinician, or may have come from laboratory, pharmacy, or other systems.  Output to the clinician may come in the form of a recommendation or alert at the time of order entry, or, if the alert was triggered after the initial order was entered, systems of email and wireless notification have been employed CDSS Development to assist system designed to provide support for laboratory test ordering provide a suggested list of potential diagnoses to the users The system might start with the patient’s signs and symptoms, entered either by the clinician directly or imported from the EMR knowledge base contains information about diseases and their signs and symptoms inference engine maps the patient signs and symptoms to those diseases and might suggest some diagnoses for the clinicians to consider systems generally do not generate only a single diagnosis, but usually generate a set of diagnoses based on the available information  There are CDSS that are part of computerized physician order entry (CPOE) systems that take a new medication order and the patient’s current medications as input, the knowledge base might include a drug database, and the output would be an alert about drug interactions so that the physician could change the order Input might be a physician’s therapy plan, where the knowledge base would contain local protocols or nationally accepted treatment guidelines, and the output might be a critique of the plan compared to the guidelines. structure of the CDSS knowledge base will differ depending on the source of the data and the uses to which they are put Nonknowledge-Based Clinical Decision Support Systems use a form of artificial intelligence called machine learning, which allows the computer to learn from past experiences and/or to recognize patterns in the clinical data Types: Artificial neural networks genetic algorithms Artificial Neural Networks simulate human thinking and learn from examples. ANN consists of nodes called neurons and weighted connections (which correspond to nerve synapses) that transmit signals between the neurons in a unidirectional manner ANN contains 3 layers, which include the input layer, output layer, and hidden layer The input layer is the data receiver, and the output layer communicates the results, while the hidden layer processes the incoming data and determines the results  ANN analyzes the patterns in the patient data, to derive the associations between the patient’s signs and symptoms and a diagnosis. The input may be the signs and symptoms exhibited by a patient and the output may be the possible diseases the patient may have. These systems can learn from examples when supplied with known results for a large amount of data  The system will study this information, make guesses for the correct output, compare the guesses to the given results, find patterns that match the input to the correct output, and adjust the weights of the connections between the neurons accordingly, in order, to produce the correct results. This iterative process is known as training the artificial network Example: with myocardial infarction, for instance, the data including a variety of signs and symptoms from large numbers of patients who are known to either have or not have a myocardial infarction can be used to train the neural network. Once the network is trained, i.e., once the weighted associations of signs and symptoms with the diagnosis are determined, the system can be used on new cases to determine if the patient has a myocardial infarction  Advantages and disadvantages to using artificial neural networks Advantages: ▪ Eliminating the need to program IF–THEN rules ▪ Eliminating the need for direct input from experts ▪ Process incomplete data by inferring what the data should be Disadvantages: ▪ The training process involved can be time consuming ▪ Formula Weights are often not easily interpretable ▪ System cannot explain or justify. Why it uses certain data the way it does Accountability and reliability of this system is a concern Artificial neural networks have many applications in the medical field. In a review article on the use of neural networks in health care, provides a chart that shows various applications of ANNs, which include the diagnosis of appendicitis, back pain, dementia, myocardial infarction, psychiatric emergencies, sexually transmitted diseases, skin disorders, and. Another Study results have shown that ANNs’ diagnostic predictions for pulmonary embolisms were as good as, or better than, physicians’ predictions. Another study also showed that neural networks did a better job than two experienced cardiologists in detecting acute myocardial infarction in electrocardiograms with concomitant left bundle branch block  Studies have also shown that ANNs can predict which patients are at high risk for cancers such as oral cancer. The studies described in Baxt’s chart illustrate other applications of ANNs, including predicting outcomes for things such as surgery recovery, liver transplants, cardiopulmonary resuscitation, and heart valve surgery, as well as the analysis of waveforms of electrocardiograms (ECGs) and electroencephalograms (EEGs) Genetic Algorithms based on the evolutionary theories by Darwin that dealt with natural selection and survival of the fittest Reproduce themselves in various recombination's to find a new recombinant that is better adapted than its predecessors. without any domain-specific knowledge, components of random sets of solutions to a problem are evaluated, the best ones are kept and are then recombined and mutated to form the next set of possible solutions to be evaluated, and this continues until the proper solution is discovered. The fitness function is used to determine which solutions are good and which ones should be eliminated Effectiveness of Clinical Decision Support Systems Improve both patient outcomes, as well as the cost of care The systems can minimize errors by alerting the physician to potentially dangerous drug interactions Minimize problem severity and prevent complications The factors accounting for successful implementation of CDSS 1. Providing alerts/reminders automatically as part of the workflow 2. Providing the suggestions at a time and location where the decisions were being made 3. Providing actionable recommendations 4. Computerizing the entire process  Integration into both the culture and the process of care is going to be necessary for these systems to be optimally used. Institutions that have developed such a culture provide a glimpse of what is potentially possible Some of the problems include issues of how the data are entered. development and maintenance of the knowledge base and issues around the vocabulary and user interface. there is a question of what will motivate their use, which also relates to how the systems are evaluated.  Implementation Challenges Data entry, or how the data will actually get into the system Enter patient data manually, it is also time consuming, and, especially in the ambulatory setting Much of this disruption can be mitigated by integrating the CDSS with the hospital information system and EMR If the data are already entered into the medical record, the data are there for the decision support system to act upon Not all clinical decision support systems are integrated For standalone systems that patient data have to be entered twice once into the medical record system, and again, into the decision support system  A related question is who should enter the data in a stand-alone system or even in the integrated hospital systems Physicians are usually the key decision makers, but they are not always the person who interacts with the hospital systems. systems can be useful, but their full benefits cannot be gained without collaboration between the information technology professionals and the clinicians decision support system or computer-based patient record or some other system with a controlled vocabulary, that they realize either the system cannot understand what they are trying to say or, worse yet, that it uses the same words for totally different concepts or different words for the same concept. Future Uses of Clinical Decision Support Systems CDSS, when properly used they have the potential to make significant improvements in the quality of patient care. CDSS for non-clinician users such as patients are likely to grow as well Increasing interest in clinical computing and, as handheld and mobile computing become more widely adopted, better integration into the process of care may be easier Concerns over medical errors and patient safety are prompting a variety of initiatives that will lead to increased incorporation of CDSS.  Healthcare administrators, payers, and patients, are concerned, now more than ever before, that clinicians use the available technology to reduce medical errors use of CDSS may lower a hospital’s risk of medical errors, healthcare systems may incur new risks if the systems either cause harm or are not implemented properly Guidelines for Selecting and Implementing Clinical Decision Support Systems Assuring That Users Understand the Limitations The vendors of CDSS must inform the clinicians its strengths and limitations Physicians and software developers differ in regard on perfection of product  Physicians expect perfection from themselves and those around them. Physicians undergo rigorous training, have to pass multiple licensing examinations, and are held in high esteem by society for their knowledge and skills software developers often assume that initial products will be “buggy” and that eventually most errors will be fixed, often because of user feedback and error reports Assuring That the Knowledge Is From Reputable Sources Users of CDSS need to know the source of the knowledge if they purchase a knowledge-based system What rules are included in the system and what is the evidence behind the rules How was the system tested before implementation? Assuring That the System Is Appropriate for the Local Site Vendors need to alert the client about the features that are either built into the system or need to be added by the user Does the clinical vocabulary in the system match that in the EMR? client have to define the normal values as well as the thresholds for the alerts Assuring That Users Are Properly Trained vendor should also inform the client how much technical support and/or clinician training is needed for physicians to use the system appropriately and/or understand the systems’ recommendations. Part of the reason for integrating CDSS with physician order entry is that it is assumed the physician has the expertise to understand, react to, and determine whether to override the CDSS recommendation vendors of CDSS need to be clear about what expertise is assumed in using the system, and those who implement the systems need to assure that only the appropriate users are allowed to respond to the CDSS advice. Monitoring Proper Utilization of the Installed Clinical Decision Support Systems Simply having a CDSS installed, and working does not guarantee that it will be used. Automated alerting or reminder systems that prompt the user can address the issue of the user not recognizing the need for the system, another set of problems arises with the more automated systems. must be calibrated to alert the user often enough to prevent serious errors, but not so frequently that they will be ignored eventually Assuring the Knowledge Base Is Monitored and Maintained responsibility for updating the knowledge base in a timely manner New diseases are discovered, new medications come on the market, prompt a need for new information to be added to the CDSS Who is at fault if the end user decides based on outdated knowledge, or, conversely, if updating one set of rules inadvertently affects others, causing them to function improperly If CDSS are required to pass a premarket approval process, monitoring would need to be ongoing to ensure the knowledge does not get out of date, and that what functioned well in the development process still functions properly at the client site Features of CDS Computer-based clinical decision support (CDS) can be defined as “the use of information and communication technologies to bring relevant knowledge to bear on the health care and well- being of a patient.” although clinical decisions are the focus, it is often difficult to separate out aspects of the decision-making process that relate to business processes, workflow, local preferences, and other aspects of choice that enter in to operationalizing the decision- making process and also into determining how support for the decision should be best provided.  aiding decisions rather than making them means that there is an intermediary – the recipient – in the loop, and that CDS is not a “closed-loop” process typically There are some situations in which closed-loop decision support is possible, e.g. in implantable devices such as pacemakers or drug infusion pumps, but the usual norm is for an open-loop process, with a human in the loop General aim of CDS To make data about a patient easier to assess by, or more apparent to, a human. To foster optimal problem solving, decision making, and action by the human. The exact nature of a particular form of CDS depends on its specific purpose. The decision support is provided to a user – who may be a physician, a nurse, a laboratory technologist, a pharmacist, a patient (or family member or caregiver), or other individual with a need for it.  In some instances, the user may be a computer program rather than a human user Many possible settings can give rise to the need for CDS, such as a problem arising in clinical practice, a health maintenance/ preventive care question of a patient, or a training/educational exercise A primary task of the computer is to select or group knowledge that is pertinent, and/or to process data to create the pertinent knowledge. To the extent that the computer can make the selection based on patient-specific data, the relevance of the CDS to the individual patient is enhanced  The selection or grouping of knowledge and processing of data involve carrying out some sort of inferencing process, algorithm, rule, or association method The result of CDS is to perform some action, usually to make a recommendation In some forms of CDS the action is implicit. A rule with an if and a then part is a form of CDS that has an explicit action, in the then part. An order set is a form of CDS that groups information that has an association