Advanced Research and Data Methods in Women's Health: Big Data Analytics, Adaptive Studies, and the Road Ahead

Technical/Algorithm, Stakeholder, and Society (TASS) barriers to the application of artificial intelligence in medicine: A systematic review

INTRODUCTION

The use of artificial intelligence (AI), particularly machine learning and predictive analytics, has shown great promise in health care. Despite its strong potential, there has been limited use in health care settings. In this systematic review, we aim to determine the main barriers to successful implementation of AI in healthcare and discuss potential ways to overcome these challenges.

METHODS

We conducted a literature search in PubMed (1/1/2001-1/1/2023). The search was restricted to publications in the English language, and human study subjects. We excluded articles that did not discuss AI, machine learning, predictive analytics, and barriers to the use of these techniques in health care. Using grounded theory methodology, we abstracted concepts to identify major barriers to AI use in medicine.

RESULTS

We identified a total of 2,382 articles. After reviewing the 306 included papers, we developed 19 major themes, which we categorized into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). These themes included: Lack of Explainability, Need for Validation Protocols, Need for Standards for Interoperability, Need for Reporting Guidelines, Need for Standardization of Performance Metrics, Lack of Plan for Updating Algorithm, Job Loss, Skills Loss, Workflow Challenges, Loss of Patient Autonomy and Consent, Disturbing the Patient-Clinician Relationship, Lack of Trust in AI, Logistical Challenges, Lack of strategic plan, Lack of Cost-effectiveness Analysis and Proof of Efficacy, Privacy, Liability, Bias and Social Justice, and Education.

CONCLUSION

We identified 19 major barriers to the use of AI in healthcare and categorized them into three levels: the Technical/Algorithm, Stakeholder, and Social levels (TASS). Future studies should expand on barriers in pediatric care and focus on developing clearly defined protocols to overcome these barriers.

Distribution of Extreme Vital Signs and Complete Blood Count Values of Healthy Parturients: A Retrospective Database Analysis and Review of the Literature

BACKGROUND

The impact of physiological adjustments throughout pregnancy on maternal vital signs and laboratory values has yet to be fully defined. The present study was designed to determine the normal range of these parameters among healthy pregnant women during the peripartum period.

METHODS

This is a retrospective analysis of data collected during real-time deliveries in a single medical center. Vital signs and laboratory results from the 24 hours preceding delivery room admission and up to 72 hours postpartum were collected. Only pregnant women at term (37 to 41 weeks' gestation) with a liveborn, singleton gestation, and no chronic disease or obstetric complication that could affect the physiological parameters under study were included. The mean, range, and standard deviations of the extremes of all parameters at 3 distinct time points (prelabor, intrapartum, and postpartum) were calculated. The 2.5 and 97.5 percentiles for each parameter were reported as the normal range.

RESULTS

A total of 32,161 cases fulfilled inclusion criteria. The average gestational age at delivery was 39 weeks ± 8 days, and one-third of the cases were primiparous. During labor and after delivery, the upper limits of normal blood pressure values were 147/94 and 145/94 mm Hg, respectively. The lower limits were 83/43 and 83/42 mm Hg, respectively. Normal heart rates were 60-115 beats/min prelabor, 51-120 beats/min intrapartum, and 50-120 beats/min postpartum. Lowest normal temperatures ranged between 36.0°C and 36.3°C in the 3 study time points, and highest normal temperatures were 37.2°C prelabor and 37.6°C intra- and postpartum. The normal ranges of white blood cell counts were 6.1-16.8 prelabor, 6.5-22.5 intrapartum, and 6.4-23.9 K/µL postpartum. Normal low values of hemoglobin were 9.7, 8.7, and 7.1 g/dL and of platelets were 117, 113, and 105 K/µL, respectively.

CONCLUSIONS

Our findings justify the practice of using ≥2 repeated measurements for diagnosing hypertensive disorders of pregnancy. Lower normal blood pressure limits may be below those defining hypotensive shock. Normal heart rates exceed the accepted definitions of both tachy- and bradycardia. Normal temperatures at all times have a more narrow range than previously thought, and the normal range of white blood cell count has outliers exceeding the current definitions of leukocytosis or leukopenia at all times. The normal lower range of hemoglobin was constantly below 10 g/dL, and normal platelet counts were considerably lower than those previously described. The vital signs and complete blood count values thus far considered normal for the peripartum period may require some adjustment. New definitions for hypotension, tachy- and bradycardia, fever, and leukocyte quantitative disorders should be considered.

Using patient data to optimize an expert-based guideline on convalescence recommendations after gynecological surgery: a prospective cohort study

BACKGROUND

Convalescence advice is often based on tradition and anecdote from health care providers, rather than being based on experiences from patients themselves. The aim of this study was to analyse recovery in terms of resumption of various daily activities including work, following different laparoscopic and abdominal surgery in order to optimize an expert-based guideline on convalescence recommendations.

METHODS

This is a prospective cohort study conducted in nine general and one university hospital in the Netherlands. Women aged 18-65 years and scheduled for a hysterectomy (laparoscopic, vaginal, abdominal) and/or laparoscopic adnexal surgery (n = 304) were eligible to participate. Preoperatively, participants were provided with tailored expert-based convalescence recommendations on the graded resumption of several daily activities including sitting, standing, walking, climbing stairs, bending, lifting, driving, cycling, household chores, sport activities and return to work (RTW). Postoperatively, time until the resumption of these activities was tracked. Convalescence recommendations were considered correct when at least 25% and less than 50% of the women were able to resume an activity before or at the recommended recovery time.

RESULTS

There was a wide variation in the duration until the resumption of daily activities within and between groups of patients undergoing different types of surgery. Recovery times lengthened with increasing levels of physical burden as well as with increasing levels of invasiveness of the surgery. For the majority of activities actual recovery times exceeded the recovery time recommended by the expert panel.

CONCLUSIONS

This study provided insight in the resumption of daily activities after gynecological surgery and the adequacy of an expert-based convalescence guideline in clinical practice. Patient data was used to optimize the convalescence recommendations.

TRIAL REGISTRATION

Dutch trial registry, NTR2087 (August 2009) and NTR2933 (June 2011).