In contrast to clinical reference material, such as continuously updated online journals and medical texts, computerized clinical decision support directly assists the clinician in making decisions about a specific patient. Decision support does not need to be sophisticated to have significant impact. For example, simple dose-range checking for medications, drug-drug interaction checking, and drug-allergy checking are conceptually straightforward but can catch a critical source of human error that no amount of training or personal vigilance can entirely eliminate. Slightly more advanced are systems that analyze clinical data (such as calculating a creatinine clearance) and present guidance based on those data. More sophisticated systems look for trends in values, such as the rate of fall of the hematocrit or the rising body weight of an intensive care unit (ICU) patient who is accumulating extracellular fluid, where an absolute number may not be notable, but an alert to the trend may be important and prompt action.
Decision support is challenging to implement and maintain. The most vexing problem is “alert fatigue.” Studies within and outside health care show that the benefit of an alert, such as a pop-up interaction in a software system, is rapidly extinguished if the alert becomes a routine part of using the system. A familiar clinical example is the minimal attention paid to most audible alerts produced by cardiac telemetry systems. If a clinical decision support in a CPOE system provides an “alert” to the drug-drug interaction of two medications routinely used together safely, such as enoxaparin and warfarin, in the same way as to unfamiliar but dangerous interactions, such as theophylline and fluoroquinolones, clinicians become desensitized to the alerts and dismiss critically important guidance when it does appear. Alert fatigue is a fact of human cognition and cannot be eliminated through training, education, or self-discipline. The best clinical systems offer fine-grained tuning of the system's behavior, such as altering the system's response by drug and provider specialty, and offer a range of interruptive and noninterruptive support mechanisms. The price of this flexibility is the institutional effort required to design and maintain the system. However, even these measures have yet to demonstrate consistent improvement in the effectiveness of alerts.
The most complex decision support systems attempt to aid clinical diagnosis. The application of artificial intelligence to medicine has a long history; however, most diagnostic expert systems have been stand-alone, requiring effort by the clinician outside of their normal workflow, and have thus had limited clinical implementation. Examples of clinical diagnostic systems directly imbedded in an electronic health record are few but are an area of increasing research and commercial interest (Table e3–2).
Table e3–2.Functional classes and examples of clinical decision support systems. ||Download (.pdf) Table e3–2. Functional classes and examples of clinical decision support systems.
|Class ||Function ||Examples |
|Feedback ||Provide feedback by responding to an action taken by the clinician or to new data entered into the system || |
Drug family checking results in alerts on allergies, drug-drug interactions, and other patient-specific conflicts.
Parameter checking looks for dosing errors and other parameter discrepancies in patient-specific scenarios (eg, gentamicin dosing in chronic kidney disease).
Redundant utilization checking alerts physicians to duplicate test orders.
|Data organization ||Organization and presentation of disparate data into logical, intuitive schemas at the point of need ||Aggregate data trending observes key indicators for large numbers of patients over time (eg, emergence of antibiotic resistance patterns). |
|Proactive information ||Provision of information to the clinician at the point of need (eg, clinical pathway for pneumonia when patient with pneumonia is being admitted to hospital) ||Template and order sets can be provided to given situations. |
|Intelligent actions ||Automation of routine and repeated tasks for the clinician on a regular time schedule (eg, provision of all new laboratory values on current patient lists every morning) || |
Rule-based event detection allows users to create logical rules to be checked when triggering events occur (eg, check glucose level in hyponatremia).
Time-based checks to post reminders when expected transactions have not occurred (eg, warfarin order not filled by 8:00 PM).
|Communication ||Alert clinician and other providers who need to know about unusual data (eg, test results) or communications regarding specific patients || |
Parameter alerts provide clinicians with key information on panic values.
Automated e-mails send information to specified clinicians when certain clinician patient encounters occur (eg, e-mail to primary doctor when patient is evaluated in the emergency department).
|Expert advice ||Diagnostic and therapeutic advice using a comprehensive knowledge base and a problem-solving method, such as probabilistic reasoning, neural nets, or heuristic rules || |
Differential diagnosis and suggestions for further testing generated from patient-specific data.
Reducing uncertainty in test interpretation (eg, probability of pulmonary embolism given patient demographics and indeterminate ventilation-perfusion scan).
et al. The role of electronic health records in clinical reasoning. Ann N Y Acad Sci. 2018;1434:109.
et al. Artificial intelligence for decision support in acute stroke—current roles and potential. Nat Rev Neurol. 2020;16:575.
et al. Quality of decision support in computerized provider order entry: systematic literature review. JMIR Med Inform. 2018;6:e3.
M. Clinical decision support systems for triage in the emergency department using intelligent systems: a review. Artif Intell Med. 2020;102:101762.
et al. Decision support tools: realizing the potential to improve quality of care. Can J Cardiol. 2018;34:821.
et al. Clinical prediction rules: a systematic review of healthcare provider opinions and preferences. Int J Med Inform. 2019;123:1.
et al. Reasons for physicians not adopting clinical decision support systems: critical analysis. JMIR Med Inform. 2018;6:e24.
et al. Precision oncology decision support: current approaches and strategies for the future. Clin Cancer Res. 2018;24:2719.
et al. Laboratory testing in primary care: a systematic review of health IT impacts. Int J Med Inform. 2018;116:52.
R. The impact of clinical decision support systems (CDSS) on physicians: a scoping review. Stud Health Technol Inform. 2020;272:470.
et al. Effects of chemotherapy prescription clinical decision-support systems on the chemotherapy process: a systematic review. Int J Med Inform. 2019;122:20.
et al. Using EMR-enabled computerized decision support systems to reduce prescribing of potentially inappropriate medications: a narrative review. Ther Adv Drug Saf. 2018;9:559.
L. Clinical decision support systems for chronic diseases: a systematic literature review. Comput Methods Programs Biomed. 2020;195:105565.
et al. Improving medication-related clinical decision support. Am J Health Syst Pharm. 2018;75:239.
Van de Velde
et al. A systematic review of trials evaluating success factors of interventions with computerised clinical decision support. Implement Sci. 2018;13:114.
et al. Clinical decision support for the diagnosis and management of adult and pediatric hypertension. Curr Hypertens Rep. 2020;22:67.