Data acquisition is the foundation for the data-information-knowledge-wisdom (DIKW) paradigm in informatics (Mastrian & McGonigle, 2017, p. 6). It represents the initial phase in obtaining the necessary information for making informed decisions within any healthcare system. Regardless of the discipline, data plays a vital role in achieving accurate results and can be utilized in various ways.
Real-time reporting in a digital health system is a significant benefit of data acquisition. One area where this is particularly evident is in nursing care. Nurses comprise the largest segment of the healthcare workforce (Stevens & Ferrer, 2016), and their most common errors often stem from process failures, such as staff unavailability or a lack of essential supplies. Real-time reporting by nurses can have a direct impact on the timeliness of care while streamlining the entire process.
Clinical laboratories also reap the rewards of data acquisition. As a substantial portion of a patient’s medical records are generated through lab tests, data plays a crucial role in improving accuracy, efficiency, and speed (Osborne, 2016). For instance, implementing better labeling and logistics for lab specimens can optimize turnaround time, leading to faster diagnoses. Better data can reduce errors and modernizing the processes will improve operational efficiency.
Social media data can also provide real time surveillance information for public health. Social media provides early identification of potential public health problems. An example of this might be using Twitter to identify keywords associated with disease outbreaks among groups that typically do not seek medical services or to complement existing surveillance systems (Edo-Osagie et al., 2019). This approach enhances the completeness and quality of data necessary for informed public policy decisions.
Data acquisition also helps with patient centric care. For example, the ubiquitous use text messaging allows clinicians to collect real time survey data from patients (Rai et al., 2017). This data enables researchers to gain insights into patients’ knowledge and perspectives regarding their own healthcare. Survey responses can take various formats, including open-ended answers, numerical ratings, or simple “yes” or “no” choices. The real time data would provide patient centric information without any delay.
Another beneficiary of data acquisition is machine learning. By utilizing computer algorithms to identify patterns within data, machine learning facilitates the development of more accurate predictive models. For example, machine learning uses images for diagnosis in oncology and mobile apps have been created to spot eye diseases (Tseng et al., 2020). The adaptive behavior of machine learning creates predictive models that have the characteristics of human intelligence.
Data acquisition represents the initial step towards ensuring accurate healthcare decision-making. It should serve as the foundation for evidence-based care. An ideal healthcare system should continuously learn and analyze data, thereby significantly improving overall healthcare outcomes while ensuring that valuable data is not wasted.
References
Edo-Osagie, O., Smith, G., Lake, I., Edeghere, O., & De La Iglesia, B. (2019). Twitter mining using semi-supervised classification for relevance filtering in syndromic surveillance. PLoS ONE, 14(7), e0210689. https://doi.org/10.1371/journal.pone.0210689
Mastrian, K., & McGonigle, D. (2017). Informatics for health professionals . Jones & Bartlett Learning.
Osborne, J. (2016). Increasing lab excellence with three principles of peak performance. MLO: Medical Laboratory Observer, 48(5), 34.
Rai, M., Moniz, M., Blaszczak, J., Richardson, C., & Chang, T. (2017). Real-Time Data Collection Using Text Messaging in a Primary Care Clinic. Telemedicine and e-Health, 23(12), 955–963. https://doi.org/10.1089/tmj.2017.0022
Stevens, K., & Ferrer, R. (2016). Real-Time Reporting of Small Operational Failures in Nursing Care. Nursing Research and Practice, 2016, 8416158. https://doi.org/10.1155/2016/8416158
Tseng, H., Wei, L., Cui, S., Luo, Y., Ten Haken, R., & El Naqa, I. (2020). Machine Learning and Imaging Informatics in Oncology. Oncology, 98(6), 344–362. https://doi.org/10.1159/000493575