Harnessing color vision for visual oximetry in central cyanosis

Preterm Infants off Positive Pressure Respiratory Support Have a Higher Incidence of Occult Cerebral Hypoxia

OBJECTIVE

To use cerebral near-infrared spectroscopy (NIRS) to quantify occult cerebral hypoxia across respiratory support modes in preterm infants.

STUDY DESIGN

In this prospective, longitudinal, observational study, infants ≤32 weeks gestation underwent serial pulse oximetry (oxygen saturation [SpO2]) and cerebral NIRS monitoring (4-6 hours per session) following a standardized recording schedule (daily for 2 weeks, every other day for 2 weeks, then weekly until 35 weeks corrected gestational age). Four calculations were made: median cerebral saturation, median cerebral hypoxia burden (proportion of NIRS samples below the hypoxia threshold [<67%]), median systemic saturation, and median systemic hypoxia burden (proportion of SpO2 samples below the desaturation threshold [<85%]). During each recording session, respiratory support mode was noted (room air, low-flow nasal cannula, high-flow nasal cannula, noninvasive positive pressure ventilation, continuous positive airway pressure, and invasive ventilation).

RESULTS

There were 1013 recording sessions made from 174 infants with a median length of 6.9 hours. Although the systemic (SpO2) hypoxia burden was significantly greater for infants on the highest respiratory support (invasive and noninvasive positive pressure ventilation), the cerebral hypoxia burden was significantly greater during recording sessions made on the lowest respiratory support (8% for room air; 29% for low-flow nasal cannula).

CONCLUSIONS

Premature infants on the highest levels of respiratory support have less cerebral hypoxia than those on lower respiratory support. These results raise concern about unrecognized cerebral hypoxia during lower acuity periods of neonatal intensive care unit hospitalization and adverse outcomes.

Developing Low-Cost Mobile Device and Apps for Accurate Skin Spectrum Measurement via Low-Cost Spectrum Sensors and Deep Neural Network Technology

In recent years, skin spectral information has been gradually applied in various fields, such as the cosmetics industry and clinical medicine. However, the high price and the huge size of the skin spectrum measurement device make the related applications of the skin spectrum unable to be widely used in practical applications. We used convolutional neural network (CNN) to achieve a satisfying accuracy of the Fitzpatrick skin-type classification by using a simple self-developed device in 2018. Leveraging on the hardware, firmware, and software app-developing experience, a low-cost miniature skin spectrum measurement system (LMSSMS) using deep neural network (DNN) technology was further studied, and the feasibility of the system is verified in this paper. The developed LMSSMS is divided into three parts: (1) miniature skin spectrum measurement device (MSSMD), (2) DNN model, and (3) mobile app. The MSSMD was developed with innovative low-cost MSSC, 3D printing, and a simple LED light source. The DNN model is designed to enhance measurement accuracy. Finally, the mobile app is used to control and show the measurement results. The developed app also includes a variety of skin-spectrum-related applications, such as erythema index and melanin index (EI/MI) measurement, Fitzpatrick skin-type classification, Pantone SkinTone classification, sun-exposure estimation, and body-fat measurement. In order to verify the feasibility of LMSSMS, we used the standard instrumentation device as a reference. The results show that the accuracy of the LMSSMS can reach 94.7%, which also confirms that this development idea has much potential for further development.

Racial discrepancy in pulse oximeter accuracy in preterm infants

OBJECTIVE

Pulse oximetry is commonly used in Neonatology, however recent adult data suggest racial disparity in accuracy, with overestimation of oxygen saturation for Black patients.

STUDY DESIGN

Black and White infants <32 weeks gestation underwent simultaneous arterial blood gas and pulse oximetry measurement. Error by race was examined using mean bias, Arms, Bland-Altman, and linear/non-linear analysis.

RESULTS

A total of 294 infants (124 Black, 170 White) were identified with mean GA of 25.8 ± 2.1 weeks and mean BW of 845 ± 265 grams, yielding 4387 SaO2-SpO2 datapoints. SpO2 overestimation, measured by mean bias, was 2.4-fold greater for Black infants and resulted in greater occult hypoxemia (SpO2 > 90% when SaO2 < 85%; 9.2% vs. 7.7% of samples). Sensitivity and specificity for detection of true hypoxemia were similar between groups (39 vs. 38%; 81 vs. 78%).

CONCLUSION

There is a modest but consistent difference in SpO2 error between Black and White infants, with increased incidence of occult hypoxemia in Black infants.

The color of skin: blue diseases of the skin, nails, and mucosa

Diseases of the skin, hair, nails and mucosa can appear as flesh-colored lesions or may present as any of the colors of the visual spectrum. Diseases associated with blue (or shades of blue) discoloration represent a unique group of conditions that occur de novo or as a reaction to either a topical or a systemic agent to which the individual has been exposed. Blue diseases can affect the skin, the nails or the mucosal membranes of the mouth (buccal mucosa, gingiva, lips, palate or tongue) or eyes (sclera). In addition to appearing blue, they can also appear as blue-black, blue-brown, blue-gray, blue-green, blue-purple, blue-red, and blue-silver. The conditions range from those secondary to exogenous agents (systemic or tattoo or topical) to syndromes to systemic diseases to tumors (adnexal, melanocytic, vascular, or miscellaneous). A comprehensive attempt to include all conditions that have been described as blue (or a shade of blue) has been performed by evaluating the following terms using the medical search engine PubMed: blue and either gingiva, lips, lunula, mucosa, nails, oral, palate, sclera, skin, or tongue. Subsequently, the conditions were organized by color (blue and shades of blue) and within each color by location (skin, nails, oral mucosa and sclera). The results are presented in organized tables; in addition, there is discussion of some of the conditions that are unique to one or more specific locations. In conclusion, 'preserve and cherish the pale blue dot' and remember that a big red rock eater with chrysiasis is the answer to the riddle, "What is big and blue and eats rocks?"

Optimization of LED Lighting for Clinical Settings

The advent of the LED light source has promoted the concept of human-centric lighting (HCL). The LED has also been responsible for increases in the electrical efficiency of lighting systems, coupled with recent improvements in their colour properties. We have found that it is also possible to create a lit environment with enhanced clinical attributes by providing a source spectrum that meets the requirements of the Cyanosis Observation Index (COI). This paper describes the use of a differential evolution (DE) algorithm for the spectral design of a mixed LED light source capable of meeting COI recommendations as well as HCL performance criteria.

Social Perception of Facial Color Appearance for Human Trichromatic Versus Dichromatic Color Vision

Typical human color vision is trichromatic, on the basis that we have three distinct classes of photoreceptors. A recent evolutionary account posits that trichromacy facilitates detecting subtle skin color changes to better distinguish important social states related to proceptivity, health, and emotion in others. Across two experiments, we manipulated the facial color appearance of images consistent with a skin blood perfusion response and asked participants to evaluate the perceived attractiveness, health, and anger of the face (trichromatic condition). We additionally simulated what these faces would look like for three dichromatic conditions (protanopia, deuteranopia, tritanopia). The results demonstrated that flushed (relative to baseline) faces were perceived as more attractive, healthy, and angry in the trichromatic and tritanopia conditions, but not in the protanopia and deuteranopia conditions. The results provide empirical support for the social perception account of trichromatic color vision evolution and lead to systematic predictions of social perception based on ecological social perception theory.