AI, NLG, and Machine Learning

The Role of NLP and Computer Vision in Healthcare

The healthcare sector is one of the most sought-after industries and, by leveraging NLP, we can improve results, deliver a high standard of care, and optimize prices.

By Akshat Gupta
July 23, 2020

Human beings are the most advanced species. We are ranked at the highest order because of our ability to communicate and share information. It is surprising to know that only 21 percent of the available information is in the structured form. Text mining is the process of deriving meaningful information from natural language text. Natural language processing (NLP) is the artificial intelligence (AI) method of communicating with a system using natural language. In simple words, it is the blend of computer science, artificial intelligence (AI), and human language. Applications of NLP can be witnessed in chatbots, voice assistants like Siri, Cortana, Google Translate, and the like. The healthcare sector is one of the most sought-after industries and, by leveraging NLP, we can improve results, deliver a high standard of care, and optimize prices.

1. Research

Early drug discovery requires a lot of deep probing into research. Due to the plethora of information being available for research, it becomes difficult to extract, explore, and describe. Moreover, research is still done using orthodox methods. Mining unstructured data to support medical research has been prevalent for many years. This requires analysis of big data sets and often includes a manual chart review to identify patients and extract specific attributes.

Chart review by qualified professionals is extremely costly and time consuming, and it is hard to achieve a good coverage of variations in language and format. Gene disease mapping requires identifying biological origin of the disease, comprehensive understanding of the genes involved, and prioritizing the key targets. Key information is often distorted, altered, or missed. NLP helps the project teams analyze the key targets.

Natural language processing–-based text mining can provide a solution to more rapidly access and analyze key information relevant to discovery project teams. An NLP platform can dramatically shorten the time needed for analysis, providing a detailed and focused gene profile for the genotype, variants, mutations, and phenotypes under investigation. NLP is a great method of supporting disease registrars in an augmented intelligence workflow by pre-extracting information. This data can then be integrated into disease registries, allowing data-rich registries to be utilized both prospectively for clinical trials and retrospectively for informed decisions on disease interventions utilizing real- world data.

2. Patient call centres

Call centres bridge the communication gap between the healthcare professionals and the patients. However, it is a cumbersome process to extract the desired information because of the following:

  • Language used is informal and not scientific.
  • Vocabulary is inconsistent.
  • It is not easy to analyze critical information.

    By integrating the latest technologies with proven business practices, pharmaceutical companies can optimize and streamline their call centrer communications, which will yield significant returns and competitive advantages. Healthcare organizations will also gain valuable information on their patient population health.

    3. Disease registries

    NLP is an efficacious method of supporting disease registrars in an augmented intelligence workflow by pre-extracting information. This data can then be integrated into disease registries, allowing data-rich registries to be utilized both prospectively for clinical trials and retrospectively for informed decisions on disease interventions utilizing real- world data.

  • For cancer, extract clinical attributes, such as cancer stage, grade, tumor size, histology, lymph node involvement, TNM, and biomarker values
  • For diabetes, body mass index (BMI), laboratory values, such as hemoglobin A1c, retinopathies, skin ulcerations, annual screenings, etc.
  • For heart failure patients, ejection fraction (EF), dyspnea, fatigue, edema, exercise intolerance, cough, weight gain, decreased concentration, etc.
  • For chronic obstructive pulmonary disease (COPD), pulmonary function tests dyspnea, wheezing, fatigue, unintended weight loss
  • For overall contributing factors for any disease, BMI, smoking status, alcohol consumption, and behavioral factors; adding social determinants of health to all registries, such as limited access to proper medications and healthy foods, barriers to physical activity, high stress levels, and social isolation

    4. Identifying patients who need improved care

    Machine learning and NLP tools have the capabilities needed to detect patients with complex health conditions who have a history of mental health or substance abuse and who need improved care. Factors such as food insecurity and housing instability can deter the treatment protocols, thereby compelling these patients to incur more cost in their lifetimes. The data of a patient’s social status and demography is often harder to locate than their clinical information since it is usually in an unstructured format. NLP can help solve this problem. NLP can also be used to improve care coordination with patients who have behavioral health conditions. Both natural language processing and machine learning can be utilized to mine patient data and detect those that are at risk of falling through any gaps in the healthcare system. Since the healthcare industry generates both structured and unstructured data, it is crucial for healthcare organizations to refine both before implementing NLP in healthcare.

    5. Empower patients with health literacy

    With conversational AI already being a success within the healthcare space, a key use case and benefit of implementing this technology is the ability to help patients understand their symptoms and gain more knowledge about their conditions. By becoming more aware of their health conditions, patients can make informed decisions and keep their health on track by interacting with an intelligent chatbot.

    In a 2017 study, researchers used NLP solutions to match clinical terms from their documents with their layperson language counterparts. By doing so, they aimed to improve patient electronic health record (EHR) understanding and the patient portal experience. Natural language processing in healthcare could boost patients’ understanding of EHR portals, opening up opportunities to make them more aware of their health.

    Four companies offering NLP software to healthcare providers are:

  • IQVIA’s platform makes use of unstructured and alternative data sources, like social
    media, in conjunction with medical documents to generate analytics regarding regulations and compliance. The software is advertised to find helpful information about changes to the client company’s compliance requirements.

  • 3M offers a system called CodeRyte CodeAssist that can recognize statements about
    diseases and treatments within a physician’s report. The software labels the report with International Classification of Diseases (ICD) and Current Procedural Terminology (CPT) codes so that expenses can be automatically reimbursed by a patient’s insurer.

  • Amazon’s NLP solution can be used for cohort analysis—or the process of finding the
    correct patients to be enrolled in a clinical trial for a new drug. The software is touted to comb through patient data to find which patients would make the best participants.

  • Nuance Communications has a solution for doctors and physicians, called Dragon Medical One, which transcribes doctor’s’ words into an EHR.

    As a scientific discipline, computer vision is concerned with the theory and technology for building artificial systems that obtain information from images or multi-dimensional data.

  • Precise diagnosis. Computer vision systems offer accurate diagnoses, minimizing false positives. The technology can potentially obliterate the requirement for redundant surgical procedures and expensive therapies. Computer vision algorithms trained using a huge amount of training data can detect the slightest presence of a condition which may typically be missed by human doctors because of their sensory limitations. The use of computer vision in healthcare diagnoses can provide significantly high levels of precision which may, in coming days, go up to 100 percent.
  • Timely detection of illness. Most fatal illnesses, such as cancer, need to be diagnosed in their early stages. Computer vision enables the detection of early symptoms with high certainty, owing to its finely tuned pattern-recognition capability. This benefit results in timely treatment and saves countless lives in the long run.
  • Heightened medical process. The use of computer vision in healthcare can considerably lessen the time doctors usually take in analysing reports and images. It frees them up with more time to spend with patients and to provide personalized and constructive advice. By enhancing the quality of physician-patient interactions, it can also assist medical professionals give consultations to more and more patients.

    The use of computer vision in healthcare supports caregivers in delivering efficient and accurate healthcare services through its life saving applications.

  • Medical imaging. For the past few decades, computer-supported medical imaging application has been a trustworthy help for physicians. It doesn’t only create and analyse images, but also becomes an assistant and helps doctors with interpretations. The application is used to read and convert 2D scan images into interactive 3D models that enable medical professionals to gain a detailed understanding of a patient’s health condition.
  • Health monitoring. By leveraging computer vision technology, doctors can analyse health and fitness metrics to assist patients to make faster and better medical decisions. Today it is being utilized by healthcare centers to measure the blood lost during surgeries, especially during C-section procedures. This can assist in taking emergency measures, if the quantity of blood lost reaches the last stage. Additionally, the technology can also be leveraged to measure the body fat percentage of people using images taken from regular cameras.
  • Nuclear medicine. As a section of clinical medicine, nuclear medicine deals with the use of radionuclide pharmaceuticals in diagnosis. Sometimes computer vision techniques of remote radiation therapy are also referred to nuclear medicine. In diagnostics, it mainly utilizes single photon emission computed tomography (SPECT) and positron emission tomography (PET).