Digitization in healthcare

Konfuzio

Health insurance status quo  

Wrong decisions in the health examination when changing or taking out health insurance can have far-reaching consequences. Based on the medical history, the risk of an illness is estimated and the corresponding premium amount is calculated, or private health insurers may refuse to accept an application [1]. Applications may be falsely rejected or accepted. Can automated data processing by AI-supported systems simplify decision-making bases, reduce sources of error and relieve all parties involved?

Information from documents is mostly processed manually. Increasing competition in the insurance industry is creating a wave of digitization. Rule-based processes such as OCR and RPA robots now offer only small digitization advantages in automated data processing [2]. Increasingly, learning systems using artificial intelligence are supporting humans in decision-making and manual data processing and data extraction from documents such as advance risk inquiries for disability insurance. Diverse use cases exist:

1. AI supports prevention and diagnostics

AI can be applied in the context of prevention and diagnostics, for example in radiology, to identify diseases such as cancer at an early stage with the help of pattern recognition. A first step in this direction was taken by the Norwegian University Hospital "Ahus". In Norway, nationally agreed processes exist for the diagnosis and treatment of cancer patients. With the aim of increasing the efficiency of these processes and the quality of its own work in this context, the hospital initiated a study. Using IBM Watson Explorer-tools, the MRI findings of patients with prostate cancer documented in medical records were analyzed. Machine learning was used to examine unstructured data and put it into a quantifiable format. This approach allowed the hospital to better organize diagnostic information and more quickly examine content quantitatively. In the long run, this can optimize hospital resources and improve patient care. But therapy decisions are also supported by this approach.

2. AI gives people in need of care more independence

Another area of application that could benefit from the use of AI in the future is care. Here, intelligent devices, such as wearables, can offer the possibility of living as long as possible in a self-determined manner despite the need for care. Companies such as AiServe are making a start here by helping blind and visually impaired people get around independently. A combination of computer vision and AI enables the wearable, which is attached to the user's glasses, to detect obstacles and navigate the user accordingly via voice instructions.

3. AI-based health check as a service of the SHI.

AI not only enables new treatment methods, but also has the potential to improve administrative processes and the points of contact with customers or patients. Statutory health insurance (SHI) is an important component of German healthcare, and the use of AI here could benefit not only employees, but above all the approximately 72 million insured persons.

The Technician health insurance is leading the way: Since the end of 2018, the portfolio has been enriched by a digital service offering, as it now provides its insureds with the AI-based symptom check of the Berlin-based company "Ada Health" is available. This is a chat-based application in which the insured person is asked questions about their symptoms with the aim of providing a qualified analysis. The health information provided is presented in a comprehensible manner and is quality assured. The user is informed about possible causes of his complaints and next steps, such as a consultation with the doctor, are suggested. In addition, this information will be able to be shared and discussed with physicians in the future. A Offer like Ada's not only saves time and resources for doctors and patients, but also strengthens patient empowerment. In addition, the current "Digital Health" study by Bitkom that 42 percent of all Internet users obtain information online before visiting a doctor.

4. simplify SHI administrative processes with AI support

The internal, administrative processes of health insurance companies could also benefit from the use of AI - for example, in the context of receipt verification. As part of the reimbursement of costs for bonus programs, health insurers first require the insured to submit electronic image receipts before reimbursement. These vary depending on the benefit and are currently checked manually by responsible administrators at the health insurer. This process proves to be time-consuming and involves the risk that incorrect documents are not verified or not all documents are checked.

One proposed improvement could be as follows: After receipts are submitted electronically by the insured, an algorithm - based on AI - evaluates all documents. The AI recognizes the respective document type, analyzes its content and finally assigns it to a corresponding, predefined group. Subsequently, only those documents that have been flagged as conspicuous by the system undergo a manual review by the clerk. The goal here is a fully automated intelligent process that allows the clerk to focus on specific and complex cases. This would speed up the document review process and enable faster feedback. This would leave more time again for exchanges with the insured.

5. occupational disability risk pre-inquiry: automatic health check for PKV, GKV and BKK

AI cannot and should not completely replace human cognitive processes. But AI can support and relieve human beings. Artificially intelligent systems make it easier for the person in charge to examine critical cases. Thus, AI enables exact evaluation and individual health checks.

There are already solution models for this: Intelligent algorithms that combine Deep Learning-based image processing and Natural Language Processing [5]. They not only understand how to structure unstructured information, but also how to understand and logically link the content of texts. Based on trained data sets, the cognitive systems learn and the AI continues to improve. 

The problem can be illustrated using the example of the occupational disability risk pre-enquiry: Automatically processed data can make it easier to identify people with pre-existing conditions in prior risk inquiries. In health insurance, AI enables the pre-filtering of illnesses that could lead to an exclusion. If the BU applicant has an "asthma spray", it is assumed that he belongs to the risk group "asthma". However, if this patient only has the spray for emergencies and does not use it regularly, an exclusion from the BU insurance would still occur, even though the patient does not clearly belong to a risk group. In general, in Germany up to 25% of all prior risk inquiries with pre-existing conditions are either rejected or only conditionally accepted due to exclusions and surcharges [3]. Approximately 75% of all BU inquiries with pre-existing conditions are accepted without aggravation. AI can recognize this information from the BI request and structure the relevant information for further examination by humans.

Illustration of the acceptance rate for BU requests
Illustration of the acceptance rate for BU requests

But it's not just occupational health risk inquiries that can be processed by health insurers' AI. Personal data, medical histories, hospital and medical bills can be quickly analyzed and prepared for further human processing by AI and without human labor. Post-processing times and errors are reduced, saving everyone involved a lot of time, money and effort. Components of BU competence define to 30% from workflow management, standardization of processes, cover letters and questionnaires [4]. 

Pie chart assumption in the event of prior illness in the case of occupational disability insurance
Occupational disability Acceptance rate for pre-existing conditions

AI offers opportunities in health assessment. Thanks to artificially intelligent and automated processes, AI helps to identify individual risks and sort the acquired pre-existing conditions from the BU inquiries into the non-critical 75% and the critical 25%. This subsequently facilitates manual further processing of the critical 25% by humans. Ultimately, decisions can be made more easily on resilient information, processes can be accelerated, and process deviations in risk assessment can be reduced.

Conclusion for artificial intelligence in healthcare

Artificial intelligence offers some promising opportunities in the context of administration and patient care. Applied correctly, all players in the healthcare system could benefit in the long term. The SHI system in particular should therefore engage intensively with the topic and procure the necessary expertise. Due to its responsibility for more than 70 million insured persons, this is where - in addition to diagnostics and treatment - the greatest potential for a promising use of AI in the healthcare sector lies.

Find your partner for digitization in healthcare

Founded in 2016 and managed by its employees, Helm & Nagel GmbH is the manufacturer of the AI platform Konfuzio. An AI that is already usable without AI knowledge. Our partners distribute the software to our customers. This offers you various advantages.

  • System houses and consulting with industry expertise relevant to you are available to assist you with the implementation of Konfuzio
  • Cost savings through automation by the software
  • Ad-hoc access to latest AI algorithms without lengthy R&D

Are you interested in having us arrange a no-obligation meeting with a partner active in your industry?

Contact us and we will connect you with the right Konfuzio partner who knows your industry inside out.

To the contact form

SOURCES

[1] Knowledge-PKV.de (June 2020): What health questions do you have to answer when applying for private health insurance?

[2] McKinsey & Company (June 2017): Artificial intelligence in health insurance: smart auditing with self-learning software. S.2.

[3] MORGEN & MORGEN Press Release (May 2018): M&M Rating Occupational Disability: Psyche issue continues to gain importance. S.4.

[4] Morgen & Morgen BU Rating (May 2020): Excellent performance of NLV: Market Management Life Private. S.7.

[5] AOK (December 2018): Scientific Advisory Board for Digital Transformation: comments on an AI strategy for a statutory health insurance company. S.5

LIST OF ILLUSTRATIONS

Fig.1: Pexels - Typewriter, after: Andrea Piacquadio, as of 02/2020

Fig.2: Occupational disability - acceptance in the case of pre-existing conditions, according to: Morgen & Morgen, as of 05/2018

More Articles

colorful umbrellas in the air

AI in Insurance: OCR AI in Input Management | Update 2023

AI-driven input management through OCR and NLP In insurance companies, it has long been nothing new to use input management systems to...

Read article

Extract data

Do you want to extract data from PDF files? PDFs are widely used for sending and presenting information. Not only suppliers...

Read article
Process optimization

Process optimization: definition and implementation in your company

Process optimization is an inevitable process for the efficient functioning of a modern company. Abstract What is process optimization? When companies...

Read article

    Contact us!

    Arrow-up