The digital transformation has improved administrative and strategic management in the health area, allowing for a level of efficiency and agility never before imagined! The large volume of data generated in the process, brought information and insights that help decision-making and process improvements, but allows agents to deviate in behavior and new forms of fraudulent actions. Ynio's function is to shield institutions against these scenarios.
in hospital bills
suspected fraud
in laboratory tests
defrauded and/or wasted
in hospital bills
suspected fraud
in laboratory tests
defrauded and/or wasted
Through this technology, it is possible to collect, analyze data and relate them. In this way, there is continuous learning about patterns and behaviors, allowing to predict failures, streamlining and enriching decision-making. Thus, the company will always be ahead of the fraudulent event, being able to prevent it even before it happens.
Account audit
Authorization of procedures
Authorization of inputs
Gloss resource control
Payment to accredited
Taking care of the financial health of our customers
Serving more than 700 beneficiaries and reducing revenue losses with
deviations and fraud: this was the challenge of one of the largest
health plan in Brazil by contracting the Decision platform.
for hospitals
For health plan operators
The business areas can be independent because, in a friendly way, they can define, test online and put into production the rules that will adapt the solution to new threats of fraud or loss and adjust it according to the organization's strategies . Ynio contemsimple rules (based on transaction data and customer information or external for enrichment) and complex (event sequencing, event counting, temporizador), also supporting geolocalized information to compose decision and modeling rules.
The solution withtempla a reports and dashboards module that allows non-technical users to customize the type and format of information they wish to view. Management, analytical and synthetic reports can be made available online, based on information obtained from different sources of data stored in the system.tema (registrations, events, alerts, rules, etc.). Information can be updated manually or automatically and can be exported in different formats.
The solution allows the application of predictive models based on machine learning (Machine Learning) and the decision flow, allowing the detection of the risk of deviations and fraud before they occur.
The previously enabled access profiles can be easily audited, as the solution records the execution of all accesses, processes and changes made by users in the system.tema.
For greater efficiency, Ynio allows you to correlate data from other sources to the monitored events, enriching analysis and decision-making and thus streamlining case handling. The solution automates the integration between themtemas – accessing external services via Rest API and HTTP protocol –, internalizes and centralizes data and allows defining parameters to condition the use of information.
Ynio has an optional module to assist users/customers with suspected fraud via the contact center. The solution makes it possible to build a dialogue tree based on the fraud profile and guides the contact center attendant during the conversation, enabling the collection of information that assesses the suspicion and helps to deal with the case.
The solution has the ability to generate alerts, based on parameters based on received event data and on data from the Enrichment, Lists, Profiles and Templates functionalities. Alerts can be created for different areas of the company. The analysis of these alerts can be distributed to different treatment queues, as requested by the organization. It is also possible to configure the workflow to be executed in the handling of an alert, manually or automatically, allowing the control of task deadlines, escalating the alert given a situation, sending emails and SMS in specific situations, blocking, approving and cancellations. You can also trigger actions automatically, or the analyst trigger actions that are pre-configured.
Machine learning model to identify deviations in the pattern of use of inputs and procedures in medical care, identifying the main offenders within each service. The definition of expected patterns is based on historical data, using machine learning techniques for clustering, prediction and anomaly detection. The services are characterized in accordance with the procedures authorized for the same, in addition to the use of information from the patient, the plan and the responsible provider. The main gains are operational efficiency and effectiveness in auditing and the possibility of implementing automatic payment authorization/rejection rules. It is possible to extract knowledge that can serve as input for other processes, such as negotiating values and defining guidelines for providers.