Transfusion Medicine Informatics: A Review of Current Practice and a Glimpse into the Future

The practical use of artificial intelligence in Transfusion Medicine and Apheresis

BACKGROUND

Blood and plasma volume calculations are a daily part of practice for many Transfusion Medicine and Apheresis practitioners. Though many formulas exist, each facility may have their own modifications to consider. ChatGPT (Generative Pre-trained Transformer) provides a new and exciting pathway for those with no programming experience to create personalized programs to meet the demands of daily practice. Additionally, this pathway creates computer programs that provide accurate and reproducible outputs. Herein, we aimed to create a step-by-step process for clinicians to create customized computer programs for use in everyday practice.

METHODS

We created a process of inputs to ChatGPT-40, which generated computer programming code. This code was copied and pasted into Notepad (and saved as a Python file) and Google Colaboratory to verify functionality. We validated the durability of our process by repeating it over a 5-day timeframe and by recruiting volunteers to reproduce our outputs using the suggested process.

RESULTS

Computer code generated by ChatGPT-40 in response to our common language inputs was accurate and durable over time. The code was fully functional in both Python and Colaboratory. Volunteers reproduced our process and outputs with minimal assistance.

CONCLUSION

We analyzed the practical application of ChatGPT-40 and artificial intelligence (AI) to perform daily calculations encountered in Transfusion Medicine. Our results provide a proof of concept that people with no programming experience can create customizable solutions for their own facilities. Our future work will expand to the creation of comprehensive and customizable websites designed for each individual user.

Challenges in reliable preoperative blood ordering: A qualitative interview study

BACKGROUND

Presurgical blood orders are important for patient safety during surgery, but excess orders can be costly to patients and the healthcare system. We aimed to assess clinician perceptions on the presurgical blood ordering process and perceived barriers to reliable decision-making.

METHODS

This descriptive qualitative study was conducted at a single large academic medical center. Semi-structured interviews were conducted with surgeons, anesthesiologists, nurse anesthetists, nurse practitioners working in preoperative assessment clinics, and transfusion medicine physicians to assess perceptions of current blood ordering processes. Interview responses were analyzed using an inductive open coding approach followed by thematic analysis.

RESULTS

Twenty-three clinicians were interviewed. Clinicians felt that the current blood ordering process was frequently inconsistent. One contributor was a lack of information on surgical transfusion risk, related to lack of experience in ordering clinicians, insufficient communication between stakeholders, high turnover in academic settings, and lack of awareness of the maximum surgical blood ordering schedule. Other contributors included differing opinions about the benefits and harms of over- and under-preparing blood products, leading to variation in transfusion risk thresholds between clinicians, and disagreement about the safety of emergency-release blood.

CONCLUSION

Several barriers to reliable decision-making for presurgical blood orders exist. Future efforts to improve ordering consistency may benefit from improved information sharing between stakeholders and education on safe transfusion practices.

Avoiding Unintended Consequences of Pediatric Blood Order Set Updates through In Situ Usability Testing

BACKGROUND

 Blood product ordering is a complex process and mistakes can harm patients and lead to poor outcomes. Orders and order sets can be designed to help mitigate errors, but major changes in design can unintentionally cause new errors.

OBJECTIVES

 Our objective was as follows: (1) utilize formative in situ usability testing to iteratively improve the design of a redesigned blood product order set prior to go-live, (2) implement changes based on feedback derived from this testing, and (3) compare the error rate, system usability scale (SUS) score, time to task completion, and click counts between the prior order set in use at the time and the revised redesigned order set.

METHODS

 A multidisciplinary project team convened to redesign blood product orders and order sets from scratch based on a review of the literature and benchmarking against four pediatric academic institutions with the goal of addressing prior ordering errors. The newly redesigned blood product order set was iteratively updated via in situ formative usability testing performed with available clinical users using a concurrent think-aloud protocol in real clinical environments. Errors, SUS scores, time to task completion, and click counts were assessed for the revised redesigned order set using summative testing.

RESULTS

 Formative usability testing with 20 participants led to seven design changes in the redesigned order set which reduced the error rate at go-live. Summative usability testing showed that even though the usability scores were only slightly improved for the revised redesigned order set, the error rates in blood orders were significantly decreased.

CONCLUSION

 Usability testing can identify design errors early in the process which can be rectified prior to implementation, thus avoiding unintended consequences of changes.

Data-Driven Anomaly Detection in Laboratory Medicine: Past, Present, and Future

BACKGROUND

Anomaly detection is an integral component of operating a clinical laboratory. It covers both the recognition of laboratory errors and the rapid reporting of clinically impactful results. Procedures for identifying laboratory errors and highlighting critical results can be improved by applying modern data-driven approaches.

CONTENT

This review will prepare the reader to appraise anomaly detection literature, identify common sources of anomalous results in the clinical laboratory, and offer potential solutions for common shortcomings in current laboratory practices.

SUMMARY

Laboratories should implement data-driven approaches to detect technical anomalies and keep them from entering the medical record, while also using the full array of clinical metadata available in the laboratory information system for context-dependent, patient-centered result interpretations.