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 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 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 vigilance. 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 seen 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. |Favorite Table|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 on 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 list 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 clinicians when provider-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 Dec;1434(1):109–14.
et al. Quality of decision support in computerized provider order entry: systematic literature review. JMIR Med Inform. 2018 Jan 24;6(1):e3.
et al. Decision support tools: realizing the potential to improve quality of care. Can J Cardiol. 2018 Jul;34(7):821–6.
et al. Clinical prediction rules: a systematic review of healthcare provider opinions and preferences. Int J Med Inform. 2019 Mar;123:1–10.
et al. Reasons for physicians not adopting clinical decision support systems: critical analysis. JMIR Med Inform. 2018 Apr 18;6(2):e24.
et al. Professional, structural and organisational interventions in primary care for reducing medication errors. Cochrane Database Syst Rev. 2017 Oct 4;10:CD003942.
et al. Precision oncology decision support: current approaches and strategies for the future. Clin Cancer Res. 2018 Jun 15;24(12):2719–31.
et al. Laboratory testing in primary care: a systematic review of health IT impacts. Int J Med Inform. 2018 Aug;116:52–69.
et al. Trigger tool-based automated adverse event detection in electronic health records: systematic review. J Med Internet Res. 2018 May 30;20(5):e198.
et al. Effects of chemotherapy prescription clinical decision-support systems on the chemotherapy process: a systematic review. Int J Med Inform. 2019 Feb;122:20–6.
et al. Specifications of computerized provider order entry and clinical decision support systems for cancer patients undergoing chemotherapy: a systematic review. Chemotherapy. 2018;63(3):162–71.
et al. Using EMR-enabled computerized decision support systems to reduce prescribing of potentially inappropriate medications: a narrative review. Ther Adv Drug Saf. 2018 Jul 12;9(9):559–73.
et al. Advances in sharing multi-sourced health data on decision support science 2016–2017. Yearb Med Inform. 2018 Aug;27(1):16–24.
et al. Asynchronous automated electronic laboratory result notifications: a systematic review. J Am Med Inform Assoc. 2017 Nov 1;24(6):1173–83.
et al. Improving medication-related clinical decision support. Am J Health Syst Pharm. 2018 Feb 15;75(4):239–46.
et al. Computerised decision support in physical activity interventions: a systematic literature review. Int J Med Inform. 2018 Mar;111:7–16.
Van de Velde
et al. A systematic review of trials evaluating success factors of interventions with computerised clinical decision support. Implement Sci. 2018 Aug 20;13(1):114.