AI in medical diagnosis: AI prediction & human judgment.

AI has long been regarded as a panacea for decision-making and many other aspects of knowledge work; as something that will help humans get rid of their shortcomings. We believe that AI can be a useful asset to support decision-makers, but not that it should replace decision-makers. Decision-making uses algorithmic analysis, but it is not solely algorithmic analysis; it also involves other factors, many of which are very human, such as creativity, intuition, emotions, feelings, and value judgments. We have conducted semi-structured open-ended research interviews with 17 dermatologists to understand what they expect from an AI application to deliver to medical diagnosis. We have found four aggregate dimensions along which the thinking of dermatologists can be described: the ways in which our participants chose to interact with AI, responsibility, 'explainability', and the new way of thinking (mindset) needed for working with AI. We believe that our findings will help physicians who might consider using AI in their diagnosis to understand how to use AI beneficially. It will also be useful for AI vendors in improving their understanding of how medics want to use AI in diagnosis. Further research will be needed to examine if our findings have relevance in the wider medical field and beyond.

Anger and disgust shape judgments of social sanctions across cultures, especially in high individual autonomy societies.

When someone violates a social norm, others may think that some sanction would be appropriate. We examine how the experience of emotions like anger and disgust relate to the judged appropriateness of sanctions, in a pre-registered analysis of data from a large-scale study in 56 societies. Across the world, we find that individuals who experience anger and disgust over a norm violation are more likely to endorse confrontation, ostracism and, to a smaller extent, gossip. Moreover, we find that the experience of anger is consistently the strongest predictor of judgments of confrontation, compared to other emotions. Although the link between state-based emotions and judgments may seem universal, its strength varies across countries. Aligned with theoretical predictions, this link is stronger in societies, and among individuals, that place higher value on individual autonomy. Thus, autonomy values may increase the role that emotions play in guiding judgments of social sanctions.

Utility of artificial intelligence-based large language models in ophthalmic care.

PURPOSE: With the introduction of ChatGPT, artificial intelligence (AI)-based large language models (LLMs) are rapidly becoming popular within the scientific community. They use natural language processing to generate human-like responses to queries. However, the application of LLMs and comparison of the abilities among different LLMs with their human counterparts in ophthalmic care remain under-reported. RECENT FINDINGS: Hitherto, studies in eye care have demonstrated the utility of ChatGPT in generating patient information, clinical diagnosis and passing ophthalmology question-based examinations, among others. LLMs' performance (median accuracy, %) is influenced by factors such as the iteration, prompts utilised and the domain. Human expert (86%) demonstrated the highest proficiency in disease diagnosis, while ChatGPT-4 outperformed others in ophthalmology examinations (75.9%), symptom triaging (98%) and providing information and answering questions (84.6%). LLMs exhibited superior performance in general ophthalmology but reduced accuracy in ophthalmic subspecialties. Although AI-based LLMs like ChatGPT are deemed more efficient than their human counterparts, these AIs are constrained by their nonspecific and outdated training, no access to current knowledge, generation of plausible-sounding 'fake' responses or hallucinations, inability to process images, lack of critical literature analysis and ethical and copyright issues. A comprehensive evaluation of recently published studies is crucial to deepen understanding of LLMs and the potential of these AI-based LLMs. SUMMARY: Ophthalmic care professionals should undertake a conservative approach when using AI, as human judgement remains essential for clinical decision-making and monitoring the accuracy of information. This review identified the ophthalmic applications and potential usages which need further exploration. With the advancement of LLMs, setting standards for benchmarking and promoting best practices is crucial. Potential clinical deployment requires the evaluation of these LLMs to move away from artificial settings, delve into clinical trials and determine their usefulness in the real world.

Social, intellectual, psychological, and attractiveness judgements of lay people about patients before and after combined orthodontic-orthognathic surgical treatment.

BACKGROUND: Facial appearance plays a significant role in the success of social interactions. There is a limited amount of evidence investigating the influence of combined orthodontic-orthognathic surgical treatment on the social judgments of lay people. OBJECTIVE: The aim of this study was to investigate whether changes in facial appearance following orthognathic surgery alter the social judgements made by lay people. ETHICAL APPROVAL: Ethical approval was granted from the University of Sheffield School of Clinical Dentistry Research Ethics Committee on 17th August 2020 (Reference: 033775). MATERIALS AND METHODS: This cross-sectional, web-based survey involved clinical photographs of six Caucasian female patients pre- and post-combined orthodontic-orthognathic treatment. Three patients had a pre-treatment class 2 skeletal pattern, and three patients had a pre-treatment class 3 skeletal pattern. Staff and students at the University of Sheffield, UK were invited to evaluate five personality traits: (i) friendliness, (ii) intelligence, (iii) attractiveness, (iv) self-confidence, and (5) trustworthiness using a 5-point Likert scale. The trait scores were summed to obtain a total social judgement score, and a paired t-test was used to compare the total scores from pre- and post-treatment images. RESULTS: There were 261 responses to the survey of which 181 (75%) were completed fully. The total social judgement scores from after treatment images were higher compared with the pre-treatment images (mean diff 1.6; P < .001) indicating more positive social judgements. The improvements in perceived social judgments were more notable for class 3 patients (mean diff 2.7) compared to class 2 patients (mean diff 0.7). CONCLUSION: Social judgement scores were higher (more positive) from post-treatment images of patient faces than their pre-treatment images. The findings highlight the possible indirect benefits combined orthodontic-orthognathic surgical treatment may have on an individual in a social setting.

Comparative Sensing and Judgment Control System for Temperature Maintenance for Optimal Treatment in Hyperthermic Intraperitoneal Chemotherapy Surgery.

For tumors wherein cancer cells remain in the tissue after colorectal cancer surgery, a hyperthermic anticancer agent is injected into the abdominal cavity to necrotize the remaining cancer cells with heat using a hyperthermic intraperitoneal chemotherapy system. However, during circulation, the processing temperature is out of range and the processing result is deteriorated. This paper proposes a look-up table (LUT) module design method that can stably maintain the processing temperature range during circulation via feedback. If the temperature decreases or increases, the LUT transmits a command signal to the heat exchanger to reduce or increase heat input, thereby maintaining the treatment temperature range. The command signal for increasing and decreasing heat input is Tp and Ta, respectively. The command signal for the treatment temperature range is Ts. If drug temperatures below 41 and above 43 °C are input to the LUT, it sends a Tp or Ta signal to the heat exchanger to increase or decrease the input heat, respectively. If the drug's temperature is 41-43 °C, the LUT generates a Ts signal and proceeds with the treatment. The proposed system can automatically control drug temperature using temperature feedback to ensure rapid, accurate, and safe treatment.

Effects of Character Accent on Perceived Similarity, Transportation, and Narrative Persuasion.

Guided by narrative transportation theory and the social identity approach, this study examined the effects of character accent on perceived similarity, transportation, and narrative persuasion. Cigarette smokers from Kentucky (N = 492) listened to a first-person narrative about smoking-induced lung cancer. The character spoke either with a Southern American English (SAE; ingroup) or a General American English (GAE; outgroup) accent. Opposite to predictions, the GAE-accented character was perceived as more similar overall, engendered greater transportation, elevated lung cancer risk perceptions, and promoted higher intentions to quit smoking than the SAE-accented character. Consistent with predictions, the effects of character accent on risk perceptions and intentions to quit were mediated by perceived similarity and transportation. Taken together, these findings indicate that narrative character accent is a potent cue to similarity judgments, but that actual linguistic similarity is not isomorphic with perceived overall similarity. Theoretical and practical implications for narrative persuasion are discussed.

What Goes into Patient Selection for Lung Cancer Screening? Factors Associated with Clinician Judgments of Suitability for Screening.

Rationale: Achieving the net benefit of lung cancer screening (LCS) depends on optimizing patient selection. Objective: To identify factors associated with clinician assessments that a patient was unlikely to benefit from LCS ("LCS-inappropriate") because of comorbidities or limited life expectancy. Methods: Retrospective analysis of patients assessed for LCS at 30 Veterans Health Administration facilities from January 1, 2015 to February 1, 2021. We conducted hierarchical mixed-effects logistic regression analyses to determine factors associated with clinicians' designations of LCS inappropriateness (primary outcome), accounting for 3-year predicted probability (i.e., competing risk) of non-lung cancer death. Measurements and Main Results: Among 38,487 LCS-eligible patients, 1,671 (4.3%) were deemed LCS-inappropriate by clinicians, whereas 4,383 (11.4%) had an estimated 3-year competing risk of non-lung cancer death greater than 20%. Patients with higher competing risks of non-lung cancer death were more likely to be deemed LCS-inappropriate (odds ratio [OR], 2.66; 95% confidence interval [CI], 2.32-3.05). Older patients (ages 75-80; OR, 1.45; 95% CI, 1.18-1.78) and those with interstitial lung disease (OR, 1.98; 95% CI, 1.51-2.59) were more likely to be deemed LCS-inappropriate than would be explained by competing risk of non-lung cancer death, whereas patients currently smoking (OR, 0.65; 95% CI, 0.58-0.73) were less likely to be deemed LCS-inappropriate, suggesting that clinicians over- or underweighted these factors. The probability of being deemed LCS-inappropriate varied from 0.4% to 74%, depending on the clinician making the assessment (median OR, 3.07; 95% CI, 2.89-3.25). Conclusion: Concerningly, the likelihood that a patient is deemed LCS-inappropriate is more strongly associated with the clinician making the assessment than with patient characteristics. Patient selection may be optimized by providing decision support to help clinicians assess net LCS benefit.

Comparison of the diagnostic efficiency between the O-RADS US risk stratification system and doctors' subjective judgment.

BACKGROUND: This study aimed to compare the diagnostic efficiency of Ovarian-Adnexal Reporting and Data System (O-RADS) and doctors' subjective judgment in diagnosing the malignancy risk of adnexal masses. METHODS: This was an analysis of 616 adnexal masses between 2017 and 2020. The clinical findings, preoperative ultrasound images, and pathological diagnosis were recorded. Each adnexal mass was evaluated by doctors' subjective judgment and O-RADS by two senior doctors and two junior doctors. A mass with an O-RADS grade of 1 to 3 was a benign tumor, and a mass with an O-RADS grade of 4-5 was a malignant tumor. All outcomes were compared with the pathological diagnosis. RESULTS: Of the 616 adnexal masses, 469 (76.1%) were benign, and 147 (23.9%) were malignant. There was no difference between the area under the curve of O-RADS and the subjective judgment for junior doctors (0.83 (95% CI: 0.79-0.87) vs. 0.79 (95% CI: 0.76-0.83), p = 0.0888). The areas under the curve of O-RADS and subjective judgment were equal for senior doctors (0.86 (95% CI: 0.83-0.89) vs. 0.86 (95% CI: 0.83-0.90), p = 0.8904). O-RADS had much higher sensitivity than the subjective judgment in detecting malignant tumors for junior doctors (84.4% vs. 70.1%) and senior doctors (91.2% vs. 81.0%). In the subgroup analysis for detecting the main benign lesions of the mature cystic teratoma and ovarian endometriosic cyst, the junior doctors' diagnostic accuracy was obviously worse than the senior doctors' on using O-RADS. CONCLUSIONS: O-RADS had excellent performance in predicting malignant adnexal masses. It could compensate for the lack of experience of junior doctors to a certain extent. Better performance in discriminating various benign lesions should be expected with some complement.

Purity is not a distinct moral domain.

Purity violations overlap with other moral domains. They are not uniquely characterized by hypothesized markers of purity - the witness's emotion of disgust, taint to perpetrator's soul, or the diminished role of intention in moral judgment. Thus, Fitouchi et al.'s proposition that puritanical morality (a subset of violations in the purity domain) is part of cooperation-based morality is an important advance.

There are no beautiful surfaces without a terrible depth.

Fitouchi et al. persuasively argue against popular disgust-based accounts of puritanical morality. However, they do not consider alternative account of moral condemnation that is also based on the psychology of disgust. We argue that these other disgust-based accounts are more promising than those dismissed in the target article.

Deep Learning-Based Evaluation of Ultrasound Images for Benign Skin Tumors.

In this study, a combined convolutional neural network for the diagnosis of three benign skin tumors was designed, and its effectiveness was verified through quantitative and statistical analysis. To this end, 698 sonographic images were taken and diagnosed at the Department of Dermatology at Severance Hospital in Seoul, Korea, between 10 November 2017 and 17 January 2020. Through an empirical process, a convolutional neural network combining two structures, which consist of a residual structure and an attention-gated structure, was designed. Five-fold cross-validation was applied, and the train set for each fold was augmented by the Fast AutoAugment technique. As a result of training, for three benign skin tumors, an average accuracy of 95.87%, an average sensitivity of 90.10%, and an average specificity of 96.23% were derived. Also, through statistical analysis using a class activation map and physicians' findings, it was found that the judgment criteria of physicians and the trained combined convolutional neural network were similar. This study suggests that the model designed and trained in this study can be a diagnostic aid to assist physicians and enable more efficient and accurate diagnoses.

Examining explainable clinical decision support systems with think aloud protocols.

Machine learning tools are increasingly used to improve the quality of care and the soundness of a treatment plan. Explainable AI (XAI) helps users in understanding the inner mechanisms of opaque machine learning models and is a driver of trust and adoption. Explanation methods for black-box models exist, but there is a lack of user studies on the interpretability of the provided explanations. We used a Think Aloud Protocol (TAP) to explore oncologists' assessment of a lung cancer relapse prediction system with the aim of refining the purpose-built explanation model for better credibility and utility. Novel to this context, TAP is used as a neutral methodology to elicit experts' thought processes and judgements of the AI system, without explicit prompts. TAP aims to elicit the factors which influenced clinicians' perception of credibility and usefulness of the system. Ten oncologists took part in the study. We conducted a thematic analysis of their verbalized responses, generating five themes that help us to understand the context within which oncologists' may (or may not) integrate an explainable AI system into their working day.

The Design of an Automatic Temperature Compensation System through Smart Heat Comparison/Judgment and Control for Stable Thermal Treatment in Hyperthermic Intraperitoneal Chemotherapy (HIPEC) Surgery.

After surgery for ovarian cancer or colorectal cancer, residual tumors are left around. A practical way to treat residual tumors is to destroy them with heat by injecting high-temperature drugs into the abdominal cavity. The injected medicinal substances are induced to flow out of the abdominal cavity; then, the spilled drug flows back into the abdominal cavity through feedback. During this process, the heat starts to decrease; thus, the treatment performance reduces. To overcome this problem, this study compares and assesses the temperature needed to maintain the heat for treatment and transmits a command signal to the heat exchanger through a look-up table (LUT). When the temperature decreases during the circulation of medications leaking out of the abdominal cavity, the LUT transmits a control signal (Tp) to the heat exchanger, which increases or vice versa. However, if the temperature (To) is within the treatment range, the LUT sends a Ts signal to the heat exchanger. This principle generates a pulse signal for the temperature difference (Tdif) in TC by comparing and determining the temperature (To) of the substance flowing out of the abdominal cavity with the reference temperature (Tref) through the temperature comparator (TC). At this time, if the signal is 41 °C or less, the LUT generates (heats) a Tp signal so that the temperature of the heat exchanger can be maintained in the range of 41 °C to 43 °C. If the Tdif is 44 °C or higher, the LUT generates (cools) the Ta signal and maintains the temperature of the heat exchanger at 41-43 °C. If the Tdif is maintained at 41-43 °C, the LUT generates a Tx signal to stop the system performance. At this time, the TC operation performance and Tdif generation process for comparing and determining the signal of To and Tref for drugs leaking out of the abdominal cavity is very important. It was observed that the faster the response signal, the lower the comparison and judgment error was; therefore, the response signal was confirmed to be 0.209 µs. The proposed method can guarantee rapid/accurate/safe treatment and automatically induce temperature adjustment; thus, it could be applied to the field of surgery.

Source-specific risk judgement and environmental impact of potentially toxic elements in fine road dust from an integrated industrial city, North China.

The contamination of potentially toxic elements (PTEs) in road dust of large industrial cities is extremely serious. Determining the priority risk control factors of PTE contamination in road dust is critical to enhance the environmental quality of such cities and mitigate the risk of PTE pollution. The Monte Carlo simulation (MCS) method and geographical models were employed to assess the probabilistic pollution levels and eco-health risks of PTEs originating from different sources in fine road dust (FRD) of large industrial cities, and to identify key factors affecting the spatial variability of priority control sources and target PTEs. It was observed that in FRD of Shijiazhuang, a typical large industrial city in China, more than 97% of the samples had an INI > 1 (INImean = 1.8), indicating moderately contaminated with PTEs. The eco-risk was at least considerable (NCRI >160) with more than 98% of the samples, mainly caused by Hg (Ei (mean) = 367.3). The coal-related industrial source (NCRI(mean) = 235.1) contributed 70.9% to the overall eco-risk (NCRI(mean) = 295.5) of source-oriented risks. The non-carcinogenic risk of children and adults are of less importance, but the carcinogenic risk deserves attention. The coal-related industry is a priority control pollution source for human health protection, with As corresponding to the target PTE. The major factors affecting the spatial changes of target PTEs (Hg and As) and coal-related industrial sources were plant distribution, population density, and gross domestic product. The hot spots of coal-related industrial sources in different regions were strongly interfered by various human activities. Our results illustrate spatial changes and key-influencing factors of priority source and target PTEs in Shijiazhuang FRD, which are helpful for environmental protection and control of environmental risks by PTEs.

In-Field Tobacco Leaf Maturity Detection with an Enhanced MobileNetV1: Incorporating a Feature Pyramid Network and Attention Mechanism.

The maturity of tobacco leaves plays a decisive role in tobacco production, affecting the quality of the leaves and production control. Traditional recognition of tobacco leaf maturity primarily relies on manual observation and judgment, which is not only inefficient but also susceptible to subjective interference. Particularly in complex field environments, there is limited research on in situ field maturity recognition of tobacco leaves, making maturity recognition a significant challenge. In response to this problem, this study proposed a MobileNetV1 model combined with a Feature Pyramid Network (FPN) and attention mechanism for in situ field maturity recognition of tobacco leaves. By introducing the FPN structure, the model fully exploits multi-scale features and, in combination with Spatial Attention and SE attention mechanisms, further enhances the expression ability of feature map channel features. The experimental results show that this model, with a size of 13.7 M and FPS of 128.12, performed outstandingly well on the task of field maturity recognition of tobacco leaves, achieving an accuracy of 96.3%, superior to classical models such as VGG16, VGG19, ResNet50, and EfficientNetB0, while maintaining excellent computational efficiency and small memory footprint. Experiments were conducted involving noise perturbations, changes in environmental brightness, and occlusions to validate the model's robustness in dealing with the complex environments that may be encountered in actual applications. Finally, the Score-CAM algorithm was used for result visualization. Heatmaps showed that the vein and color variations of the leaves provide key feature information for maturity recognition. This indirectly validates the importance of leaf texture and color features in maturity recognition and, to some extent, enhances the credibility of the model. The model proposed in this study maintains high performance while having low storage requirements and computational complexity, making it significant for in situ field maturity recognition of tobacco leaves.

Predicting Severe Complications from Cytoreductive Surgery with Hyperthermic Intraperitoneal Chemotherapy: A Data-Driven, Machine Learning Approach to Augment Clinical Judgment.

BACKGROUND: CRS-HIPEC provides oncologic benefit in well-selected patients with peritoneal carcinomatosis; however, it is a morbid procedure. Decision tools for preoperative patient selection are limited. We developed a risk score to predict severity of 90 day complications for cytoreductive surgery with hyperthermic intraperitoneal chemotherapy (CRS-HIPEC). PATIENTS AND METHODS: Adults who underwent CRS-HIPEC at the University of Pittsburgh Medical Center (March 2001-April 2020) were analyzed as part of this study. Primary endpoint was severe complications within 90 days following CRS-HIPEC, defined using Comprehensive Complication Index (CCI) scores as a dichotomous (determined using restricted cubic splines) and continuous variable. Data were divided into training and test sets. Several machine learning and traditional algorithms were considered. RESULTS: For the 1959 CRS-HIPEC procedures included, CCI ranged from 0 to 100 (median 32.0). Adjusted restricted cubic splines model defined severe complications as CCI > 61. A minimum of 20 variables achieved optimal performance of any of the models. Linear regression achieved the highest area under the receiving operator characteristic curve (AUC, 0.74) and outperformed the NSQIP Surgical Risk calculator (AUC 0.80 vs. 0.66). Factors most positively associated with severe complications included peritoneal carcinomatosis index score, symptomatic status, and undergoing pancreatectomy, while American Society of Anesthesiologists 2 class, appendiceal diagnosis, and preoperative albumin were most negatively associated with severe complications. CONCLUSIONS: This study refines our ability to predict severe complications within 90 days of discharge from a hospitalization in which CRS-HIPEC was performed. This advancement is timely and relevant given the growing interest in this procedure and may have implications for patient selection, patient and referring provider comfort, and survival.

Deep learning-assisted radiomics facilitates multimodal prognostication for personalized treatment strategies in low-grade glioma.

Determining the optimal course of treatment for low grade glioma (LGG) patients is challenging and frequently reliant on subjective judgment and limited scientific evidence. Our objective was to develop a comprehensive deep learning assisted radiomics model for assessing not only overall survival in LGG, but also the likelihood of future malignancy and glioma growth velocity. Thus, we retrospectively included 349 LGG patients to develop a prediction model using clinical, anatomical, and preoperative MRI data. Before performing radiomics analysis, a U2-model for glioma segmentation was utilized to prevent bias, yielding a mean whole tumor Dice score of 0.837. Overall survival and time to malignancy were estimated using Cox proportional hazard models. In a postoperative model, we derived a C-index of 0.82 (CI 0.79-0.86) for the training cohort over 10 years and 0.74 (Cl 0.64-0.84) for the test cohort. Preoperative models showed a C-index of 0.77 (Cl 0.73-0.82) for training and 0.67 (Cl 0.57-0.80) test sets. Our findings suggest that we can reliably predict the survival of a heterogeneous population of glioma patients in both preoperative and postoperative scenarios. Further, we demonstrate the utility of radiomics in predicting biological tumor activity, such as the time to malignancy and the LGG growth rate.