As nephrologists, we are perpetually searching for more time in our workdays. Oftentimes, we find ourselves juggling among inpatient, clinic, dialysis unit, and administrative duties, all within the same day. This begs the question: Can nephrologists be more efficient while still providing high-quality patient-centered care?
In the current fee-for-service Medicare payment model, dialysis patients are mandated to have a comprehensive nephrologist evaluation at least once monthly (1). Hemodialysis (HD) patients can be seen up to an additional three times with increasing levels of reimbursement. This encourages an increased number of visits, irrespective of medical necessity. While some have argued that an increased number of visits may improve patient outcomes, multiple studies have found that there was no significant difference in mortality among patients with more provider visits per month compared with those patients with fewer provider visits (2–6). As a result, the increased documentation time and “window time” contribute to physician burnout and fatigue with no tangible benefit to patients.
Although change is difficult, we need to implement ways to deliver care that makes a difference for our patients by providing the right treatment at the right time—without increasing the stress on ourselves. The pandemic-era loosening of restrictions in the use of telehealth services in dialysis has been a natural experiment that demonstrated we can deliver certain aspects of care to patients without the need to be at chairside (7). Moreover, new Centers for Medicare & Medicaid Services (CMS)-proposed payment models, such as the Kidney Care First (KCF) and the Comprehensive Kidney Care Contracting (CKCC), provide capitated payments adjusted for outcomes and utilization rather than rote fee for service. While the rollout of these initiatives is likely to initially involve a small percentage of nephrology practices, future expansion of these quality-based incentives can potentially entice nephrology practices to focus more on patient outcomes rather than number of patient visits.
To plan for upcoming payment model changes and deliver efficient patient-centered care, the nephrology industry needs to better utilize technology and data in new care-delivery models. This aspirational concept will require a three-pronged approach (Figure 1): 1) utilizing predictive analytic patient care models; 2) implementing communication platforms to allow seamless patient and care-team interactions; and 3) changing nephrologists from single-patient providers to population health providers.
Predictive analytics refers to predicting future outcomes based on historical data. Multiple studies exist to determine what patient characteristics invoke worse outcomes (8–11). Some have suggested reduced hospitalizations when early interventions are invoked in high-risk patients, although more studies are required. When utilizing such models, lower-risk groups would receive a required baseline level of care, whereas the higher-risk groups would have an increased number of provider and dialysis staff visits (dietitian, social worker, nurse) with a goal of improving outcomes.
With a decreasing number of touch-points between the physician and patient, the system needs to allow patients and chairside providers (nurses, techs) a way to relay information to the nephrologist without causing repeated disruption to the nephrologist's multiple day-to-day duties. A Health Insurance Portability and Accountability Act of 1996 (HIPAA)-compliant communication portal would allow patients and dialysis staff to communicate seamlessly with the nephrologist to address issues that come up between visits.
Lastly, while nephrologists still must care for individual patients, given the relative shortage of nephrologists compared to a growing number of patients, nephrologists need to implement population health into their practices. That entails configuring electronic medical records to allow for population-level data on specific quality metrics. Utilizing a multidisciplinary approach to care, the nephrologist would then work with the care team to address specific quality metrics (12, 13).
This systematic change will require a culture shift of expectations by dialysis providers, patients, and nephrologists in the way care is delivered. Although there are some potential downsides to this approach (weakened patient-physician relationship, more screen time), each patient interaction will be better focused on the patient's issues and quality metrics that are aimed at improving patient outcomes. Moreover, it could potentially lower the cost of care delivery by focusing resources on where they are needed most.
Although change is difficult, we need to implement ways to deliver care that makes a difference for our patients by providing the right treatment at the right time.
Anumudu SJ, Erickson KF. Physician reimbursement for outpatient dialysis care: Past, present, and future. Semin Dial 2020; 33:68–74. doi: 10.1111/sdi.12853
Kawaguchi T, et al. Associations of frequency and duration of patient-doctor contact in hemodialysis facilities with mortality. J Am Soc Nephrol 2013; 24:1493–1502. doi: 10.1681/ASN.2012080831
Slinin Y, et al. Predictors of provider-patient visit frequency during hemodialysis. Am J Nephrol 2013; 38:91–98. doi: 10.1159/000353565
Slinin Y, et al. Hemodialysis patient outcomes: Provider characteristics. Am J Nephrol 2014; 39:367–375. doi: 10.1159/000362286
Slinin Y, et al. Association of provider-patient visit frequency and patient outcomes on hemodialysis. J Am Soc Nephrol 2012; 23:1560–1567. doi: 10.1681/ASN.2012010051
Erickson KF, et al. Variation in nephrologist visits to patients on hemodialysis across dialysis facilities and geographic locations. Clin J Am Soc Nephrol 2013; 8:987–994. doi: 10.2215/CJN.10171012
Stauss M, et al. Opportunities in the cloud or pie in the sky? Current status and future perspectives of telemedicine in nephrology. Clin Kidney J 2020; 14:492–506. doi: 10.1093/ckj/sfaa103
Barbieri C, et al. Development of an artificial intelligence model to guide the management of blood pressure, fluid volume, and dialysis dose in end-stage kidney disease patients: Proof of concept and first clinical assessment. Kidney Dis (Basel) 2019; 5:28–33. doi: 10.1159/000493479
- Search Google Scholar
- Export Citation
, Barbieri C Development of an artificial intelligence model to guide the management of blood pressure, fluid volume, and dialysis dose in end-stage kidney disease patients: Proof of concept and first clinical assessment. Kidney Dis (Basel) 2019; 5: 28– 33. doi: 10.1159/000493479 10.1159/000493479
Goldstein BA, et al. Predicting mortality over different time horizons: Which data elements are needed? J Am Med Inform Assoc 2017; 24:176–181. doi: 10.1093/jamia/ocw057
Goldstein BA, et al. A comparison of risk prediction methods using repeated observations: An application to electronic health records for hemodialysis. Stat Med 2017; 36:2750–2763. doi: 10.1002/sim.7308
Chaudhuri S, et al. Artificial intelligence enabled applications in kidney disease. Semin Dial 2021; 34:5–16. doi: 10.1111/sdi.12915
Plantinga LC, et al. Frequency of sit-down patient care rounds, attainment of clinical performance targets, hospitalization, and mortality in hemodialysis patients. J Am Soc Nephrol 2004; 15:3144–3153. doi: 10.1097/01. ASN.0000146424.91128.2A
- Search Google Scholar
- Export Citation
, Plantinga LC Frequency of sit-down patient care rounds, attainment of clinical performance targets, hospitalization, and mortality in hemodialysis patients. J Am Soc Nephrol 2004; 15: 3144– 3153. doi: 10.1097/01. ASN.0000146424.91128.2A 10.1097/01.ASN.0000146424.91128.2A
Curtis BM, et al. The short- and long-term impact of multi-disciplinary clinics in addition to standard nephrology care on patient outcomes. Nephrol Dial Transplant 2005; 20:147–154. doi: 10.1093/ndt/gfh585