Investigating the clinical reasoning abilities of large language model GPT-4: an analysis of postoperative complications from renal surgeries

PURPOSE

Large language models, a subset of artificial intelligence, have immense potential to support human tasks. The role of these models in science and medicine is unclear, requiring strong critical thinking and analysis skills. The objective of our study was to evaluate GPT-4's abilities to assess postoperative complications after renal surgeries.

MATERIALS AND METHODS

Discharge summaries were compiled, and patient information was deidentified in a Python-based program. Prompts were engineered in GPT-4 to assess for the presence of postoperative complications. GPT-4 was further asked to interpret each complication's Clavien-Dindo classification and institutional-specific category. GPT-4's database was compared to a human-curated database. Discrepancies were manually reviewed to calculate match and accuracy rates.

RESULTS

Approximately 944 renal surgeries were conducted from August 2005 to March 2022. There was a 79.6% match rate between GPT-4 and human-curated data in detecting postoperative complications. Accuracy rates were 86.7% for GPT-4 and 92.9% for human-curated. A subgroup of 139 patients had a complication detected by both GPT-4 and human with available Clavien-Dindo classification and category information. There was a 37.4% overall match rate for Clavien-Dindo grade and 55.4% match rate for category.

CONCLUSIONS

GPT-4 was able to accurately detect if there were any postoperative complications. It struggled with the complex task of further analyzing complications, especially with Clavien-Dindo classification, which requires more critical thinking and interpretation. While GPT-4 is not yet ready for advanced postoperative complication analysis, it can still be used to support clinicians in this endeavor.

Reducing False-Positives Due to Urinary Stagnation in the Prostatic Urethra on 18F-DCFPyL PSMA PET/CT With MRI

PURPOSE

Prostate-specific membrane antigen (PSMA)-targeting PET radiotracers reveal physiologic uptake in the urinary system, potentially misrepresenting activity in the prostatic urethra as an intraprostatic lesion. This study examined the correlation between midline 18F-DCFPyL activity in the prostate and hyperintensity on T2-weighted (T2W) MRI as an indication of retained urine in the prostatic urethra.

PATIENTS AND METHODS

Eighty-five patients who underwent both 18F-DCFPyL PSMA PET/CT and prostate MRI between July 2017 and September 2023 were retrospectively analyzed for midline radiotracer activity and retained urine on postvoid T2W MRIs. Fisher's exact tests and unpaired t tests were used to compare residual urine presence and prostatic urethra measurements between patients with and without midline radiotracer activity. The influence of anatomical factors including prostate volume and urethral curvature on urinary stagnation was also explored.

RESULTS

Midline activity on PSMA PET imaging was seen in 14 patients included in the case group, whereas the remaining 71 with no midline activity constituted the control group. A total of 71.4% (10/14) and 29.6% (21/71) of patients in the case and control groups had urethral hyperintensity on T2W MRI, respectively (P < 0.01). Patients in the case group had significantly larger mean urethral dimensions, larger prostate volumes, and higher incidence of severe urethral curvature compared with the controls.

CONCLUSIONS

Stagnated urine within the prostatic urethra is a potential confounding factor on PSMA PET scans. Integrating PET imaging with T2W MRI can mitigate false-positive calls, especially as PSMA PET/CT continues to gain traction in diagnosing localized prostate cancer.

Impact of neoadjuvant relugolix on patient-reported sexual function and bother

Introduction

Sexual function following local treatment for prostate cancer is an important quality of life concern. Relugolix is a novel oral GnRH receptor antagonist used in combination with radiation therapy in the treatment of unfavorable prostate cancer. It has been shown to achieve rapid and profound testosterone suppression. As a result, these very low testosterone levels may impact both sexual functioning and perceptions. This prospective study sought to assess neoadjuvant relugolix-induced sexual dysfunction prior to stereotactic body radiation therapy (SBRT).

Methods

Between March 2021 and September 2023, 87 patients with localized prostate cancer were treated with neoadjuvant relugolix followed by SBRT per an institutional protocol. Sexual function and bother were assessed via the sexual domain of the validated Expanded Prostate Index Composite (EPIC-26) survey. Responses were collected for each patient at pre-treatment baseline and after several months of relugolix. A Utilization of Sexual Medications/Devices questionnaire was administered at the same time points to assess erectile aid usage.

Results

The median age was 72 years and 43% of patients were non-white. The median baseline Sexual Health Inventory for Men (SHIM) score was 13 and 41.7% of patients utilized sexual aids prior to relugolix. Patients initiated relugolix at a median of 4.5 months (2-14 months) prior to SBRT. 95% and 87% of patients achieved effective castration (≤ 50 ng/dL) and profound castration (< 20 ng/dl) at SBRT initiation, respectively. Ability to have an erection, ability to reach orgasm, quality of erections, frequency of erections, and overall sexual function significantly declined following relugolix. There was a non- significant increase in sexual bother.

Discussion

In concordance with known side effects of androgen deprivation therapy (ADT), neoadjuvant relugolix was associated with a significant decline in self-reported sexual function. However, patients indicated only a minimal and non-significant increase in bother. Future investigations should compare outcomes while on relugolix directly to GnRH agonist-induced sexual dysfunction.

Internal transcribed spacer regions of rRNA genes of Pneumocystis carinii from monkeys

Analysis of sequence variations among isolates of Pneumocystis carinii f. sp. macacae from 14 Indian rhesus monkeys (Macaca mulatta) at the internal transcribed spacer (ITS) regions of the nuclear rRNA gene was undertaken. Like those from P. carinii f. sp. hominis, the ITS sequences from various P. carinii f. sp. macacae isolates were not identical. Two major types of sequences were found. One type of sequence was shared by 13 isolates. These 13 sequences were homologous but not identical. Variations were found at 13 of the 180 positions in the ITS1 region and 28 of the 221 positions in the ITS2 region. These sequence variations were not random but exhibited definite patterns when the sequences were aligned. According to this sequence variation, ITS1 sequences were classified into three types and ITS2 sequences were classified into five types. The remaining specimen had ITS1 and ITS2 sequences substantially different from the others. Although some specimens had the same ITS1 or ITS2 sequence, all 14 samples exhibited a unique whole ITS sequence (ITS1 plus ITS2). The 5.8S rRNA gene sequences were also analyzed, and only two types of sequences that differ by only one base were found. Unlike P. carinii f. sp. hominis infections in humans, none of the monkey lung specimens examined in this study were found to be infected by more than one type of P. carinii f. sp. macacae. These results offer insights into the genetic differences between P. carinii organisms which infect distinct species.

Clinical correlation of variations in the internal transcribed spacer regions of rRNA genes in Pneumocystis carinii f.sp. hominis

OBJECTIVES

To analyse the importance of sequence variations in the internal transcribed spacer (ITS) regions 1 and 2 of the nuclear rRNA operon in AIDS patients with Pneumocystis carinii pneumonia (PCP).

DESIGN AND METHODS

ITS 1 and 2 genotypes were determined in 162 bronchoalveolar lavage samples from 130 patients participating in a prospective cohort study of PCP.

RESULTS

A total of 49 different ITS genotypes were detected. ITS genotype was not associated with the clinical severity or outcome of PCP. In 37 of 162 (23%) samples infection with two or more genotypes was observed. A genotype switch was detected in six of 10 patients (60%) with recurrent episodes of PCP. However, genotype changes were also seen in 10 of 19 patients (53%) who had repeated bronchoscopies within the same episode of PCP. The same ITS type was observed twice in 13 (46%) of the 28 patients with repeat bronchoscopies during single or recurrent episodes of pneumonia, but in only 14 of 81 (17%) randomly selected pairs (P < 0.01).

CONCLUSION

Although the detection of ITS genotypes is not a random event, changes in genotype can be detected in a single episode of disease, with 23% of PCP patients being infected with more than one P. carinii genotype, thus complicating the use of this locus as a genetic marker to separate new infection from the reactivation of latent infection. ITS genotypes are not associated with the clinical severity of PCP.