Impact

Quantify the impact of clinical and operational interventions and strategic decisions at scale via cross-system longitudinal patient journeys

CareQuery® gives health systems the ability to...

• 🗺️ Visualize full, longitudinal patient journeys across your entire market, with line-item detail
• 🐰 Reveal patterns between intervention and non-intervention populations
• 🧮 Quantify impact of a clinical intervention or strategic decision on key health system metrics
• 👣 Uncover the intervention's impact and patterns on the longitudinal footprint left behind

---

Determine the Impact of Tools, Decisions or Interventions

CareQuery® longitudinal journey data can be readily used to quantify the impact of strategic decisions and clinical interventions on key health system metrics, such as total cost of care, network leakage, practice throughput, etc.

The below use case highlights the impact of remote patient monitoring (RPM) on the total cost of care for high-touch hypertensive patients who saw a UCDavis provider at any point in time during the period in question.

Use CareQuery® to Identify Analysis Population and Intervention Metric

Python

# 1) import 
from care_query.care_query import CareQuery

# 2) instantiate and connect
cq = CareQuery(email = "your-email", 
               token = "your-api-token",
               sftp_key = "path/to/your/company.PEM")

# 3) identify the general population and execute
gen_query = cq.careJourney(diag_subcategory = ['hypertensive heart and renal disease',
 																					    'hypertensive heart disease'],
                       		 metro = 'sacramento-roseville-folsom, ca',
                           min_date = "2022-01-01",
                           max_date = "2022-12-31",
                           alias = "sacramento-hypertensive", 
                           limit = False)

gen_job = gen_query.execute()

# 4) identify the rpm intervention populations
int_query = cq.careEncounter(diag_subcategory = ['hypertensive heart and renal disease',
 																					    'hypertensive heart disease'],
                       		  metro = 'sacramento-roseville-folsom, ca',
                            proc_code = ['99453','99454','99457','99459'],
                            min_date = "2022-01-01",
                            max_date = "2022-12-31",
                            alias = "sacramento-hypertensive-rpm", 
                            limit = False)

int_job = int_query.execute()

# 6) upon successful completion of query, read data directly into pandas environment
result_data = query_name.sftpToPandas()

Leverage Comprehensive Volume

Exploratory data analysis on the population in question showcases the overall volumetric increases of the intervention population over the last two years, with some diversity in sub-types of interventions therein.

Learn from Longitudinal Context

Beneath any line of healthcare data is actually a the full story of an individual patient and the care they have received. The detailed patient journey context reveals another dimension of analysis which helps us better understand how RPM patient journeys look materially different from that of the non-RPM population.

Measure ROI/Impact

Diving deeper, we can see that these two populations are different in size, but most of all in the distribution of total cost of care over the period, indicating that RPM is associated with a decrease in total cost of care.

Discover the Why Beneath the Metric

The radar chart below concisely shows why the total cost of care for RPM patient journeys was lower - these patient are spending less time in inpatient care and the ED - and more time in office and outpatient visits over the course of their journey.

The data back up something that we anecdotally know, that well-managed/remotely-monitored patients have fewer acute events and frankly better outcomes than were they to not receive RPM care.