Evaluating the reliability of ChatGPT as a tool for imaging test referral: a comparative study with a clinical decision support system.

OBJECTIVES: As the technology continues to evolve and advance, we can expect to see artificial intelligence (AI) being used in increasingly sophisticated ways to make a diagnosis and decisions such as suggesting the most appropriate imaging referrals. We aim to explore whether Chat Generative Pretrained Transformer (ChatGPT) can provide accurate imaging referrals for clinical use that are at least as good as the ESR iGuide. METHODS: A comparative study was conducted in a tertiary hospital. Data was collected from 97 consecutive cases that were admitted to the emergency department with abdominal complaints. We compared the imaging test referral recommendations suggested by the ESR iGuide and the ChatGPT and analyzed cases of disagreement. In addition, we selected cases where ChatGPT recommended a chest abdominal pelvis (CAP) CT (n = 66), and asked four specialists to grade the appropriateness of the referral. RESULTS: ChatGPT recommendations were consistent with the recommendations provided by the ESR iGuide. No statistical differences were found between the appropriateness of referrals by age or gender. Using a sub-analysis of CAP cases, a high agreement between ChatGPT and the specialists was found. Cases of disagreement (12.4%) were further analyzed and presented themes of vague recommendations such as "it would be advisable" and "this would help to rule out." CONCLUSIONS: ChatGPT's ability to guide the selection of appropriate tests may be comparable to some degree with the ESR iGuide. Features such as the clinical, ethical, and regulatory implications are still warranted and need to be addressed prior to clinical implementation. Further studies are needed to confirm these findings. CLINICAL RELEVANCE STATEMENT: The article explores the potential of using advanced language models, such as ChatGPT, in healthcare as a CDS for selecting appropriate imaging tests. Using ChatGPT can improve the efficiency of the decision-making process KEY POINTS: • ChatGPT recommendations were highly consistent with the recommendations provided by the ESR iGuide. • ChatGPT's ability in guiding the selection of appropriate tests may be comparable to some degree with ESR iGuide's.

Inappropriate CT examinations: how much, who and where? Insights from a clinical decision support system (CDSS) analysis.

OBJECTIVE: To assess the appropriateness of Computed Tomography (CT) examinations, using the ESR-iGuide. MATERIAL AND METHODS: A retrospective study was conducted in 2022 in a medium-sized acute care teaching hospital. A total of 278 consecutive cases of CT referral were included. For each imaging referral, the ESR-iGuide provided an appropriateness score using a scale of 1-9 and the Relative Radiation Level using a scale of 0-5. These were then compared with the appropriateness score and the radiation level of the recommended ESR-iGuide exam. DATA ANALYSIS: Pearson's chi-square test or Fisher exact test was used to explore the correlation between ESR-iGuide appropriateness level and physician, patients, and shift characteristics. A stepwise logistic regression model was used to capture the contribution of each of these factors. RESULTS: Most of exams performed were CT head (63.67%) or CT abdominal pelvis (23.74%). Seventy percent of the actual imaging referrals resulted in an ESR-iGuide score corresponding to "usually appropriate." The mean radiation level for actual exam was 3.2 ± 0.45 compared with 2.16 ± 1.56 for the recommended exam. When using a stepwise logistic regression for modeling the probability of non-appropriate score, both physician specialty and status were significant (p = 0.0011, p = 0.0192 respectively). Non-surgical and specialist physicians were more likely to order inappropriate exams than surgical physicians. CONCLUSIONS: ESR-iGuide software indicates a substantial rate of inappropriate exams of CT head and CT abdominal-pelvis and unnecessary radiation exposure mainly in the ED department. Inappropriate exams were found to be related to physicians' specialty and seniority. CLINICAL RELEVANCE STATEMENT: These findings underscore the urgent need for improved imaging referral practices to ensure appropriate healthcare delivery and effective resource management. Additionally, they highlight the potential benefits and necessity of integrating CDSS as a standard medical practice. By implementing CDSS, healthcare providers can make more informed decisions, leading to enhanced patient care, optimized resource allocation, and improved overall healthcare outcomes. KEY POINTS: • The overall mean of appropriateness for the actual exam according to the ESR-iGuide was 6.62 ± 2.69 on a scale of 0-9. • Seventy percent of the actual imaging referrals resulted in an ESR-iGuide score corresponding to "usually appropriate." • Inappropriate examination is related to both the specialty of the physician who requested the exam and the seniority status of the physician.

Maternal iodine deficiency: a newborns' overweight risk factor? A prospective study.

OBJECTIVES: Childhood obesity and iodine deficiency are global public health concerns. Whether maternal iodine status mediates overweight in infancy has yet to be explored. We aimed to assess the relationship between maternal iodine status and infant birth weight, including small and large for gestational age (SGA and LGA, respectively). METHODS: A prospective study was carried out among 134 mother-infant pairs from Israel. Maternal iodine intake and status were estimated via questionnaire and serum thyroglobulin (Tg), respectively. Estimated iodine intake below the Recommended Daily Allowance for iodine sufficiency in pregnancy (220 µg/d) considered Inadequate. Maternal and neonatal thyroid function and anthropometric measurements, as well as maternal thyroid antibodies were also tested. RESULTS: After screening, 118 participants met the inclusion criteria (distributed trimesters I, II and III: n = 3, n = 21, and n = 94, respectively). There was a negative association of iodine intake with Tg values among the study population. Maternal median Tg value was higher than the sufficiency cutoff (16.5 vs 13 µg/L), indicating insufficient iodine status. No SGA cases were found. Inadequate iodine intake was associated with maternal isolated hypothyroxinemia (OR = 3.4; 95% CI 1.2, 9.9) and higher birthweight (including macrosomia and LGA) rates. A suggestive association of elevated Tg with a greater risk of LGA was observed. Offsprings' birth weight percentiles were associated with Tg values in pregnant women with suggestive sufficient iodine status (n = 62, R2 = 0.11, p < 0.05). CONCLUSIONS: Iodine status during pregnancy can be associated with newborn anthropometric index. Maternal inadequate iodine intake may alter fetal growth and might increase the risk of LGA among newborns. These initial findings support the need to further study the impact of iodine deficiency on newborns overweight in Israel and elsewhere.

An evaluation of the capabilities of language models and nurses in providing neonatal clinical decision support.

AIM: To assess the clinical reasoning capabilities of two large language models, ChatGPT-4 and Claude-2.0, compared to those of neonatal nurses during neonatal care scenarios. DESIGN: A cross-sectional study with a comparative evaluation using a survey instrument that included six neonatal intensive care unit clinical scenarios. PARTICIPANTS: 32 neonatal intensive care nurses with 5-10 years of experience working in the neonatal intensive care units of three medical centers. METHODS: Participants responded to 6 written clinical scenarios. Simultaneously, we asked ChatGPT-4 and Claude-2.0 to provide initial assessments and treatment recommendations for the same scenarios. The responses from ChatGPT-4 and Claude-2.0 were then scored by certified neonatal nurse practitioners for accuracy, completeness, and response time. RESULTS: Both models demonstrated capabilities in clinical reasoning for neonatal care, with Claude-2.0 significantly outperforming ChatGPT-4 in clinical accuracy and speed. However, limitations were identified across the cases in diagnostic precision, treatment specificity, and response lag. CONCLUSIONS: While showing promise, current limitations reinforce the need for deep refinement before ChatGPT-4 and Claude-2.0 can be considered for integration into clinical practice. Additional validation of these tools is important to safely leverage this Artificial Intelligence technology for enhancing clinical decision-making. IMPACT: The study provides an understanding of the reasoning accuracy of new Artificial Intelligence models in neonatal clinical care. The current accuracy gaps of ChatGPT-4 and Claude-2.0 need to be addressed prior to clinical usage.

A sub wavelength localization scheme in optical imaging using conical diffraction.

In this paper we present a scheme for the acquisition of high temporal resolution images of single particles with enhanced lateral localization accuracy. The scheme, which is implementable as a part of the illumination system of a standard confocal microscope, is based on the generation of a vector beam that is manipulated by polarimetry techniques to create a set of illumination PSFs with different spatial profiles. The combination of data collected in different illumination states enables the extraction of spatial information obscured by diffraction in the standard imaging system. An implementation of the scheme based on the utilization of the unique phenomenon of conical diffraction is presented, and the basic strategy it provides for enhanced localization in the diffraction limited region is demonstrated.

Advancing acceptance: assessing acceptance of the ESR iGuide clinical decision support system for improved computed tomography test justification.

Background: A clinical decision support system (CDSS), the European Society of Radiologists (ESR) iGuide, was developed to address gaps in the availability and use of effective imaging referral guidelines. Aim: This study aimed to assess the appropriateness of computed tomography (CT) exams with and without ESR iGuide use, as well as the usability and acceptance of the physician systems. Methods: A retrospective single-center study was conducted in which data from 278 consecutive CT tests referred by physicians were collected in the first phase (T1), and physicians used the ESR iGuide system for imaging referrals in the second phase (T2; n = 85). The appropriateness of imaging referrals in each phase was assessed by two experts, and physicians completed the System Usability Scale. Results: The mean appropriateness level on a scale of 0-9 was 6.62 ± 2.69 at T1 and 7.88 ± 1.4 at T2. When using a binary variable (0-6 = non-appropriate; 7-9 = appropriate), 70.14% of cases were found appropriate at T1 and 96.47% at T2. Surgery physician specialty and post-intervention phase showed a higher likelihood of ordering an appropriate test (p = 0.0045 and p = 0.0003, respectively). However, the questionnaire results indicated low system trust and minimal clinical value, with all physicians indicating they would not recommend collegial use (100%). Conclusion: The study suggests that ESR iGuide can effectively guide the selection of appropriate imaging tests. However, physicians showed low system trust and use, indicating a need for further understanding of CDSS acceptance properties. Maximizing CDSS potential could result in crucial decision-support compliance and promotion of appropriate imaging.

Does Iodine Intake Modify the Effect of Maternal Dysglycemia on Birth Weight in Mild-to-Moderate Iodine-Deficient Populations? A Mother-Newborn Prospective Cohort Study.

It is unclear how maternal glycemic status and maternal iodine status influence birth weight among individuals with mild-to-moderate iodine deficiency (ID). We studied the association between birth weight and both maternal glucose levels and iodine intake among pregnant women with mild-to-moderate ID. Glucose values were assessed using a glucose challenge test (GCT) and non-fasting glucose levels that were determined before delivery; individuals' iodine statuses were assessed using an iodine food frequency questionnaire; and serum thyroglobulin (Tg) and urinary iodine concentrations (UIC) were used to assess each group's iodine status. Thyroid antibodies and free thyroxine (FT4) levels were measured. Obstetric and anthropometric data were also collected. Large-for-gestational age (LGA) status was predicted using a Cox proportional hazards model with multiple confounders. Tg > 13 g/L was independently associated with LGA (adjusted hazard ratio = 3.4, 95% CI: 1.4-10.2, p = 0.001). Estimated iodine intake correlated with FT4 among participants who reported consuming iodine-containing supplements (ICS) after adjusting for confounders (ß = 0.4, 95% CI: 0.0002-0.0008, p = 0.001). Newborn weight percentiles were inversely correlated with maternal FT4 values (ß = -0.2 95% CI:-0.08--56.49, p = 0.049). We conclude that in mild-to-moderate ID regions, insufficient maternal iodine status may increase LGA risk. Iodine status and ICS intake may modify the effect that maternal dysglycemia has on offspring weight.

Can Mild-to-Moderate Iodine Deficiency during Pregnancy Alter Thyroid Function? Lessons from a Mother-Newborn Cohort.

Severe iodine deficiency during pregnancy has substantial hormonal consequences, such as fetal brain damage. Data on the potential effects of mild-to-moderate iodine deficiency on the thyroid function of pregnant women and their newborns are scarce and divergent. We investigated the association between iodine intake in pregnancy and maternal and neonatal thyroid function in a region with mild-to-moderate iodine deficiency. Pregnant women's iodine status was evaluated using an iodine food frequency questionnaire, serum thyroglobulin (Tg), and urinary iodine concentration (UIC). Neonatal thyrotropin (nTSH) values were measured after birth. Obstetrics and anthropometric data were also collected. Among the 178 women (median age 31 years) included in the study, median (interquartile range) estimated dietary iodine intake, Tg and UIC were 179 (94−268) µg/day, 18 (11−33) µg/L, and 60 (41−95) µg/L, respectively. There was a significant inverse association of iodine intake with Tg values among the study population (ß = −0.2, F = 7.5, p < 0.01). Women with high free triiodothyronine (FT3) values were more likely to exhibit an estimated iodine intake below the estimated average requirement (160 µg/day, odds ratio [OR] = 2.6; 95% confidence interval [CI], 1.1−6.4; p = 0.04) and less likely to consume iodine-containing supplements (OR = 0.3, 95% CI, 0.1−0.8; p = 0.01). It is possible that thyroid function may be affected by iodine insufficiency during pregnancy in regions with mild-to-moderate iodine deficiency. The relatively small sample size of the studied population warrants further investigation.

Low intake of iodized salt and iodine containing supplements among pregnant women with apparently insufficient iodine status - time to change policy?

BACKGROUND: Iodine is an essential nutrient for human health throughout the life cycle, especially during early stages of intrauterine life and infancy, to ensure adequate neurocognitive development. The growing global reliance on desalinated iodine-diluted water raises the specter of increased iodine deficiency in several regions. The case of Israel may be instructive for exploring the link between iodine status and habitual iodine intake in the setting of extensive national reliance on desalinated water. The aim of this study was to explore the relationship between iodine intake, including iodized salt and iodine-containing supplements intake, and iodine status among pregnant women residing in a sub-district of Israel that is highly reliant on desalinated iodine-diluted water. METHODS: A total of 134 consecutive pregnant women were recruited on a voluntary basis from the obstetrics department of the Barzilai University Medical Center during 2018. Blood was drawn from participants to determine levels of serum thyrotropin (TSH), thyroid peroxidase antibodies (TPOAb), thyroglobulin antibodies (TgAb) and thyroglobulin (Tg). An iodine food frequency questionnaire (sIFFQ) was used to assess iodine intake from food, IS and ICS. A questionnaire was used to collect data on demographic and health characteristics. RESULTS: A total of 105 pregnant women without known or reported thyroid disease were included in the study. Elevated Tg values (≥ 13 µg/L), were found among 67% of participants, indicating insufficient iodine status. The estimated iodine intake (median, mean ± SD 189, 187 ± 106 µg/d by sIFFQ) was lower than the levels recommended by the World Health Organization and the Institute of Medicine (250 vs. 220 µg/day respectively). The prevalence of iodized salt intake and iodine containing supplement intake were 4 and 52% (respectively). Values of Tg > 13 µg/L were inversely associated with compliance with World Health Organization and Institute of Medicine recommendations. CONCLUSIONS: While the Israeli Ministry of Health has recommended the intake of iodized salt and iodine containing supplements, this is apparently insufficient for achieving optimal iodine status among Israeli pregnant women. The evidence of highly prevalent probable iodine deficiency in a sample of pregnant women suggests an urgent need for a national policy of iodized salt regulation, as well as guidelines to promote iodine containing supplements and adherence to them by caregivers. In addition, studies similar to this one should be undertaken in additional countries reliant on desalinated iodine-diluted water to further assess the impact of desalinization on maternal iodine status.