Demo di 2 min: Analytical Workspace ed Assistenza Sanitaria
L’Analytical Workspace di CCH Tagetik consente agli utenti di utilizzare i big data e le funzionalità di modeling flessibili per scoprire approfondimenti e previsioni nascoste con maggiore accuratezza. Questo video dimostra come i dettagli a livello di singolo paziente possono essere sfruttati per aiutare gli ospedali a prevedere i dati finanziari attraverso importanti fattori operativi come unità di terapia intensiva, interventi chirurgici, gruppi diagnostichi e pagatori.
Trascrizione
To stay competitive in today's fast-moving market organizations need to leverage their data, extrapolate better insights and improve their forecasting accuracy.
With CCH Tagetik's Analytical Workspace we can leverage the vast amount of data that organizations already warehouse and model on an unlimited number of dimentionalities to uncover hidden insights and build a better planning model.
In the healthcare industry Analytical Workspace can be used to analyze millions of patient level records, where we move beyond typical financial information to explore more statistical and operational data for detailed analysis.
Here we're analyzing entries at individual patient visit on array of different dates and health information such as 'Lenght of Stay' 'Intensive Care Units' and 'Ventilator Days', and on top of all of that we can leverage a multitude of different dimensionalities such as insurances and payers, districts, patients, doctors, and diagnostic related groups.
With that level of granularity and a large volume of data in the Analytical Workspace, we can start analyzing that data to see some interesting insights.
On the patient side, I can review quarter over quarter changes in 'Patient Volume', 'Frequency in Surgery' and 'Intensive Care Units' to break out the volume by different diagnostic related groups and their financial ranking by expenses and revenue.
On the payer side, I can start breaking down information by individual insurance companies or different government policies to analyze how often they're reimbursing the patients expenses and how much often they're covering as well, not only the simple averages but also the distribution across all transactions, to better understand their behavior.
Here I'm understanding patterns such as the baseline trend and seasonality to help me predict operational drivers, such as 'Patient Volume' and 'Intensive Care Units' on detailed diagnostic related groupings for the future year.
From here, I can start applying my experience in judgement to adjust and tweak this model, make some mashed different models for different predictions to find the best fit.
With these insights analysis and analytical techniques in an analytical workspace, I can produce a much more insightful and accurate financial forecast.
