Predicting Extubation Readiness in Preterm Infants Utilizing Machine Learning: A Diagnostic Utility Study.

OBJECTIVE: The objective of this study was to predict extubation readiness in preterm infants using machine learning analysis of bedside pulse oximeter and ventilator data. STUDY DESIGN: This is an observational study with prospective recordings of oxygen saturation (SpO2) and ventilator data from infants <30 weeks of gestation age. Research pulse oximeters collected SpO2 (1 Hz sampling rate) to quantify intermittent hypoxemia (IH). Continuous ventilator metrics were collected (4-5-minute sampling) from bedside ventilators. Data modeling was completed using unbiased machine learning algorithms. Three model sets were created using the following data source combinations: (1) IH and ventilator (IH + SIMV), (2) IH, and (3) ventilator (SIMV). Infants were also analyzed separated by postnatal age (infants <2 or ≥2 weeks of age). Models were compared by area under the receiver operating characteristic curve (AUC). RESULTS: A total of 110 extubation events from 110 preterm infants were analyzed. Infants had a median gestation age and birth weight of 26 weeks and 825 g, respectively. Of the 3 models presented, the IH + SIMV model achieved the highest AUC of 0.77 for all infants. Separating infants by postnatal age increased accuracy further achieving AUC of 0.94 for <2 weeks of age group and AUC of 0.83 for ≥2 weeks group. CONCLUSIONS: Machine learning analysis has the potential to enhance prediction accuracy of extubation readiness in preterm infants while utilizing readily available data streams from bedside pulse oximeters and ventilators.

Utility of artificial intelligence in a binary classification of soft tissue tumors.

Soft tissue tumors (STTs) pose diagnostic and therapeutic challenges due to their rarity, complexity, and morphological overlap. Accurate differentiation between benign and malignant STTs is important to set treatment directions, however, this task can be difficult. The integration of machine learning and artificial intelligence (AI) models can potentially be helpful in classifying these tumors. The aim of this study was to investigate AI and machine learning tools in the classification of STT into benign and malignant categories. This study consisted of three components: (1) Evaluation of whole-slide images (WSIs) to classify STT into benign and malignant entities. Five specialized soft tissue pathologists from different medical centers independently reviewed 100 WSIs, representing 100 different cases, with limited clinical information and no additional workup. The results showed an overall concordance rate of 70.4% compared to the reference diagnosis. (2) Identification of cell-specific parameters that can distinguish benign and malignant STT. Using an image analysis software (QuPath) and a cohort of 95 cases, several cell-specific parameters were found to be statistically significant, most notably cell count, nucleus/cell area ratio, nucleus hematoxylin density mean, and cell max caliper. (3) Evaluation of machine learning library (Scikit-learn) in differentiating benign and malignant STTs. A total of 195 STT cases (156 cases in the training group and 39 cases in the validation group) achieved approximately 70% sensitivity and specificity, and an AUC of 0.68. Our limited study suggests that the use of WSI and AI in soft tissue pathology has the potential to enhance diagnostic accuracy and identify parameters that can differentiate between benign and malignant STTs. We envision the integration of AI as a supportive tool to augment the pathologists' diagnostic capabilities.

Artificial intelligence evaluation of focused assessment with sonography in trauma.

BACKGROUND: The focused assessment with sonography in trauma (FAST) is a widely used imaging modality to identify the location of life-threatening hemorrhage in a hemodynamically unstable trauma patient. This study evaluates the role of artificial intelligence in interpretation of the FAST examination abdominal views, as it pertains to adequacy of the view and accuracy of fluid survey positivity. METHODS: Focused assessment with sonography for trauma examination images from 2015 to 2022, from trauma activations, were acquired from a quaternary care level 1 trauma center with more than 3,500 adult trauma evaluations, annually. Images pertaining to the right upper quadrant and left upper quadrant views were obtained and read by a surgeon or radiologist. Positivity was defined as fluid present in the hepatorenal or splenorenal fossa, while adequacy was defined by the presence of both the liver and kidney or the spleen and kidney for the right upper quadrant or left upper quadrant views, respectively. Four convolutional neural network architecture models (DenseNet121, InceptionV3, ResNet50, Vgg11bn) were evaluated. RESULTS: A total of 6,608 images, representing 109 cases were included for analysis within the "adequate" and "positive" data sets. The models relayed 88.7% accuracy, 83.3% sensitivity, and 93.6% specificity for the adequate test cohort, while the positive cohort conferred 98.0% accuracy, 89.6% sensitivity, and 100.0% specificity against similar models. Augmentation improved the accuracy and sensitivity of the positive models to 95.1% accurate and 94.0% sensitive. DenseNet121 demonstrated the best accuracy across tasks. CONCLUSION: Artificial intelligence can detect positivity and adequacy of FAST examinations with 94% and 97% accuracy, aiding in the standardization of care delivery with minimal expert clinician input. Artificial intelligence is a feasible modality to improve patient care imaging interpretation accuracy and should be pursued as a point-of-care clinical decision-making tool. LEVEL OF EVIDENCE: Diagnostic Test/Criteria; Level III.

The personal digital assistant (PDA) as a tool for telementoring endoscopic procedures.

The telementoring of surgical procedures is currently achieved via a wired infrastructure that usually requires sophisticated videoconference systems. This project represents the first step in assessing the potential for using handheld computers as a mobile alternative to current telementoring systems. Specifically, this project compares a handheld computer to a standard CRT monitor regarding their capability to accurately display video images from an endoscopic procedure. Video images from two previously recorded endoscopic procedures were transmitted from a standard VCR to: 1) a handheld computer (iPAQ 3670 running Pocket PC) via a wireless LAN and 2) a standard CRT monitor via a wired analog connection. The software-used on the handheld device was custom designed to allow 320 X 240 pixel video images to be broadcast in real time. Twenty-three surgical residents who had completed an endoscopy rotation were randomized to watch one of the two videotaped endoscopic procedures on the hand held computer or on the CRT monitor. After viewing the procedure, a ten-question quiz was used to assess the ability of each participant to recognize several anatomic landmarks. The result of each questionnaire was expressed as the percentage of correct responses. Using a crossover design, each participant then viewed the other videotaped procedure using the alternate device and completed a second quiz. The mean test score for each device was calculated, and these data was analyzed using a Student T test. The observed difference between the mean test score associated with the handheld device (77.93 +/- 11.26) and the CRT monitor (81.30 +/- 12.54) was not statistically significant (p<0.41). In addition, regardless of the device used, scores corresponding to video tape one were significantly higher than those recorded for video tape two (84.35 +/- 9.92 vs. 74.35 +/- 11.61; p < 0.01) All participants were able to recognize anatomic landmarks equally well when viewing broadcasted endoscopic procedures on a handheld display or a standard CRT monitor. Handheld computers may have a role in telementoring residents who are performing endoscopic procedures. Further research is needed to evaluate the integration of handheld devices into telementoring and robotic system to perform surgical procedures.