How hospitals are using AI software to improve outcomes in value-based care

Listen

Physicians today face increased pressure to produce more accurate, complete and compliant clinical documentation while simultaneously maintaining their focus on patient care and satisfaction. However, without better clinical documentation processes and technology in place, physicians and hospitals risk receiving inaccurate quality scores and lower reimbursement rates.

CMS continues to advance the level of reimbursement it ties to clinical performance. By 2018, CMS expects to base payment criteria for Medicare value-based purchasing programs wholly on clinical performance according to efficiency of care (25 percent), patient outcomes (25 percent), patient experience (25 percent) and safety (25 percent).

To achieve full reimbursement from payers in value-based care, "clinical coding should capture the complexity of the patient's condition — the number and severity of comorbidities, the relationships between conditions and the results of treatments and interventions," Anthony Oliva, MD, vice president and CMO at Nuance, said during a webinar sponsored by Becker's Hospital Review Jan. 24. Accurate clinical coding requires accurate and complete clinical documentation. That means it is vital providers correctly capture the acuity of their patient population to best represent the level and quality of medical care administered.

Many hospitals have realized the value of certain technological solutions, such as automated intelligence, to support clinical documentation. With such tools, clinicians can be sure their notes are accurate, detailed, specific and adhere to ICD-10 standards.

Issues with poor clinical documentation adversely affects coding and reimbursement
"Once the final patient bill is established and sent out, that becomes what the rest of the world sees about the care you provided for that patient," Dr. Oliva says. Government and commercial payers then use ICD-10 codes in the bill to determine physician reimbursement and clinical quality scores. Clinicians unfamiliar with ICD-10 coding standards can have difficulty writing a complete, high-quality clinical note, however.

"Clinicians may think they are doing an excellent job with clinical documentation by writing thorough notes, but often, their notes fail to meet heightened standards," Dr. Oliva said. When this is the case, hospitals deploy clinical documentation improvement specialists to ensure each patient's clinical story is complete and accurate to avoid delays in downstream coding processes.

This retrospective approach often means CDI specialists must chase after physicians to get information on patient cases that occurred weeks prior. "It is incredibly irritating for physicians to get sidelined by a CDS on their way to the bathroom or the cafeteria or in the elevator," said Reid Coleman, MD, CMIO for evidence-based medicine at Nuance. More than 80 percent of physicians find queries for information after they entered the note or after the patient is discharged disruptive and time consuming, according to a 2014 survey from Nuance.

Poor EHR data entry can hurt physicians' individual quality scores
As consumers gain awareness of physician-rating websites, providers are paying more attention to individual quality scores. Some physicians fall short of quality standards not because of their care or treatment decisions, but because their EHR data entry is deficient. Poor quality scores may also reflect unspecific documentation that didn't accurately capture medical acuity or treatment in a codeable way under ICD-10.

How artificial intelligence technology can help
Artificial intelligence technology can actually help move the bar in terms of clinical performance for hospitals and physicians.

"Artificial intelligence software gives physicians clerical support to help them meet the pressing needs of a value-based world," said Dr. Coleman. Different categories of AI software deployed thoughtfully in the clinical environment can help physicians improve documentation specificity to meet ICD-10 coding standards and ensure all diagnoses are captured to show medical acuity.  

Dr. Coleman recommended hospitals invest in two specific types of AI technology.

1. Natural language software. Similar conceptually to "spell check," AI software that uses natural language processing can analyze physician documentation and advise physicians on ways to improve the specificity of their notes on the patient's medical condition. It does this by analyzing the clinical note and looking for certain combinations of words, their relationship to one another and their position in the note to extract clinical concepts. The software advises a physician on documentation improvement in real-time so he or she can resolve common coding problems on the front-end of the clinical documentation lifecycle. With natural language software, CDS don't have to waste time cornering physicians to clarify clinical notes that lack information or specificity, which helps make both professionals' lives easier.  

2. Computer-assisted physician documentation. CAPD software analyzes patient medical information captured in a physician's note and draws out diagnoses that are supported by medical evidence but not explicitly documented. By providing feedback in real time, AI software helps physicians complete documentation in a way that enables coders to fully capture the complexity, severity and quality of medical care in ICD-10 terminology. When CAPD software is implemented effectively physicians can realize substantial gains in clinical quality scores, continuity of patient care and reimbursement rates.

To rewatch the webinar, click here

© Copyright ASC COMMUNICATIONS 2021. Interested in LINKING to or REPRINTING this content? View our policies by clicking here.

 

Featured Whitepapers

Featured Webinars