Ever find an acute problem such as a fracture, which shows in a Problem List, but healed months ago? Or perhaps the problem list states a case of bronchitis that may have been transient or may actually be Chronic Obstructive Pulmonary Disease (COPD)? After all, a diagnosis of COPD is a collaboration of symptoms and test results. How many clinicians find the spare time to go retrospectively back in the EHR and calculate a patient’s, “coughing with excessive sputum nearly everyday for at least 3 months of the year, for 2 years in a row” ?
But fixing the problem list can be time-consuming and complicated. Isn’t there an alternative (better) way?
Many organizations believe that in order to derive an accurate picture of their population’s health, medication lists can be just as good as their problem list. What if you find a patient taking an atypical antipsychotic medication and they don’t have a diagnosis that coincides on their Problem List? Can we just assume a mental health diagnosis? After all, this conclusion seems logical. Or is it? Is it an oversight on their Problem List or are they prescribed it for an off-label reason? According to the Agency for Healthcare Research and Quality (AHRQ), a 2011 report stated off-label atypical antipsychotic medications uses. This included areas such as; anxiety, ADHD, behavioral disturbances of dementia and severe geriatric agitation, MDD, eating disorders, insomnia, OCD, PTSD, personality disorders, substance abuse, and Tourette's syndrome. .
Therefore, can we really make assumptions?
It makes me wonder how many insomniacs, desperate to seek relief in the form of an off-label prescription medication, now carry the diagnosis of schizophrenia or bipolar disorder, as part of a population health data mining initiative. To me, this thought is just frightening.
What other reasons make it important to fix the problem?
Improving Problem list reconciliation with NLP
Problem list reconciliation is a vital requirement to 1) maintain quality care and 2) ensure appropriate reimbursement. Inconsistencies between the coded list and the patient notes, especially when patients have relocated or been referred, are not uncommon. In other cases, the coded disease may not provide enough detail which may directly affect a payer/ government reimbursement rate that is well below the cost of care. For example, a patient with complicated diabetes, who has a retinopathy, and skin ulcerations will require more in-depth care than a patient with well-controlled diabetes.
How can NLP fix the problem?
By utilizing NLP platforms like Linguamatics Health, significant information can be extracted and assessed for reconciliation by the clinician. With a beneficial workflow in place (for example at the time a discharge summary is signed off), the diseases that are detailed in the summary can be automatically extracted and presented for adding to the problem list in the EHR. This can drastically reduce any time delays due to the process being done manually - or not at all! As long as medical condition are correctly documented - clinicians can remain vigilant. This is essential to ensure precautionary measures and those that require action are put in place- when it comes to healthcare...ignorance is by no means bliss!
Improvements to problem list accuracy can significantly improve short-term care and long-term health by boosting clinical insights for an accurate picture of the patient's state of health.
Which is the very reason I got into healthcare in the first place.
To find out more: