(1) Background: Design thinking is a problem-solving approach that has been applied in various sectors, including healthcare and medical education. While deep learning (DL) algorithms can assist in clinical practice, integrating them into clinical scenarios can be challenging. This study aimed to use design thinking steps to develop a DL algorithm that accelerates deployment in clinical practice and improves its performance to meet clinical requirements. (2) Methods: We applied the design thinking process to interview clinical doctors and gain insights to develop and modify the DL algorithm to meet clinical scenarios. We also compared the DL performance of the algorithm before and after the integration of design thinking. (3) Results: After empathizing with clinical doctors and defining their needs, we identified the unmet need of five trauma surgeons as “how to reduce the misdiagnosis of femoral fracture by pelvic plain film (PXR) at initial emergency visiting”. We collected 4235 PXRs from our hospital, of which 2146 had a hip fracture (51%) from 2008 to 2016. We developed hip fracture DL detection models based on the Xception convolutional neural network by using these images. By incorporating design thinking, we improved the diagnostic accuracy from 0.91 (0.84–0.96) to 0.95 (0.93–0.97), the sensitivity from 0.97 (0.89–1.00) to 0.97 (0.94–0.99), and the specificity from 0.84 (0.71–0.93) to 0.93(0.990–0.97). (4) Conclusions: In summary, this study demonstrates that design thinking can ensure that DL solutions developed for trauma care are user-centered and meet the needs of patients and healthcare providers.

This study was designed to examine the most up-to-date evidence about how low plasma selenium (Se) concentration affects clinical outcomes, such as mortality, infectious complications, and length of ICU or hospital stay, in patients with major trauma. We searched three databases (MEDLINE, EMBASE, and Web of Science) with the following keywords: “injury”, “trauma”, “selenium”, and “trace element”. Only records written in English published between 1990 and 2021 were included for analysis. Four studies were eligible for meta-analyses. The results of the meta-analysis showed that a low serum selenium level did not exert a negative effect on the mortality rate (OR 1.07, 95% CI: 0.32, 3.61, p = 0.91, heterogeneity, I² = 44%). Regarding the incidence of infectious complications, there was no statistically significant deficit after analyses of the four studies (OR 1.61, 95% CI: 0.64, 4.07, p = 0.31, heterogeneity, I² = 70%). There were no differences in the days spent in the ICU (difference in means (MD) 1.53, 95% CI: −2.15, 5.22, p = 0.41, heterogeneity, I² = 67%) or the hospital length of stay (MD 6.49, 95% CI: −4.05, 17.02, p = 0.23, heterogeneity, I² = 58%) in patients with low serum Se concentration. A low serum selenium level after trauma is not uncommon. However, it does not negatively affect mortality and infection rate. It also does not increase the overall length of ICU and hospital stays.

(1) Background: Hip degenerative disorder is a common geriatric disease is the main causes to lead to total hip replacement (THR). The surgical timing of THR is crucial for post-operative recovery. Deep learning (DL) algorithms can be used to detect anomalies in medical images and predict the need for THR. The real world data (RWD) were used to validate the artificial intelligence and DL algorithm in medicine but there was no previous study to prove its function in THR prediction. (2) Methods: We designed a sequential two-stage hip replacement prediction deep learning algorithm to identify the possibility of THR in three months of hip joints by plain pelvic radiography (PXR). We also collected RWD to validate the performance of this algorithm. (3) Results: The RWD totally included 3766 PXRs from 2018 to 2019. The overall accuracy of the algorithm was 0.9633; sensitivity was 0.9450; specificity was 1.000 and the precision was 1.000. The negative predictive value was 0.9009, the false negative rate was 0.0550, and the F1 score was 0.9717. The area under curve was 0.972 with 95% confidence interval from 0.953 to 0.987. (4) Conclusions: In summary, this DL algorithm can provide an accurate and reliable method for detecting hip degeneration and predicting the need for further THR. RWD offered an alternative support of the algorithm and validated its function to save time and cost.

The biochemical processes in the body, including wound healing, are influenced by pH. When skin is damaged, in the inflammation phase, the pH of the skin is under pH 6.0, and in the granulation and spontaneous reepithelization phase, the pH of the skin oscillates between 6 and 8. If there is a frequent change in the wound dressing, it will make the damage to the skin hard to cure, especially for chronic wounds. In this article, we design and implement a highly sensitive micro-electro-mechanical-system (MEMS) cavity-based pH image biosensor of a $100\times100$ array with an integrated readout circuit in a CMOS bulk technology. Based on the proposed pH fringing electrical field model, we predict and optimize the performance of the proposed sensor pattern with cavity structure for operation frequency and various pH ions. The proposed pH biosensor with MEMS cavity structure exhibits a high sensitivity of 201 mV/pH, low drift voltage over time of 2.08 mV, a fast response time of 5 s, high precise repetition of 98.9%, and a pH image of 20 frame rate/s. Since the sensor is a $100\times100$ array, it displays a detailed change in the pH image of wound exudate to identify the inflammation stage under pH 6 or spontaneous reepithelization above pH 6 to indicate the need to change the dressing, reducing the clinician’s wasted resources on frequency change of wound dressings.