AIM in Alternative Medicine

Alternative medicine (AM) is one of the medical fields that use more natural and traditional therapies for disease diagnosis and treatment, in which traditional Chinese medicine (TCM) now has been recognized as one of the main approaches of AM. As a clinical and evidencedriven discipline with long histories, AM is also heavily relied on in the utilization of big healthcare and therapeutic data for improving the capability of diagnosis and treatment. In particular, artificial intelligence (AI) has been widely adopted in AM to deliver more practical and feasible intelligent solutions for clinical operations since 1970s. This chapter summarizes the main approaches, related typical applications, and future directions of AI in AM to give related researchers a brief useful reference. We find that although AM has not been widely used in clinical practice internationally, the AI studies showed abundant experiences and technique trials in expert system, machine learning, data mining, knowledge graph, and deep learning. In addition, various types of data, such as bibliographic literatures, electronic medical records, and images were used in the related AI tasks and studies. Furthermore, during this COVID-19 pandemic era, we have witnessed the clinical effectiveness of TCM for COVID-19 treatment, which mostly was detected by real-world data mining applications. This indicates the potential opportunity of the booming of AI research and applications in various aspects (e.g., effective clinical therapy discovery and network pharmacology of AM drugs) in AM fields. © Springer Nature Switzerland AG 2022.

MentalNet: Heterogeneous Graph Representation for Early Depression Detection

Depression is one of the leading factors in global disability and a top driver for suicides. Studies have shown that depression has an effect on language usage. In recent years, especially during the COVID pandemic, social media platforms have become the de facto platform for many individuals to self-disclose or discuss mental health issues like depression. This trend presents a unique opportunity for researchers and healthcare professionals to detect potential mental illnesses for early intervention or treatment by taking advantage of the recent advances in machine learning approaches. Existing depression detection methods on social media, however, suffer from two major limitations. First, these solutions heavily rely on the amount, quality, and type of user-posted content. Second, the overlooked social circle impact should be leveraged to enhance the prediction capabilities. In this paper, we propose a depression detection framework, MentalNet, based on heterogeneous graph convolution by capturing users' interactions (replies, mentions, and quotetiveets) with their friends on social media and differentiating the intimacy of users' social circles (e.g., family, friends, or acquaintances). Specifically, we formulate the problem of depression detection on social media as a graph classification problem by representing users' social circles in the format of heterogeneous graphs. MentalNet embraces three modules, (1) extraction of ego-network node features, (2) construction of user interaction graphs, and (3) depression detection based on heterogeneous graph classification. The extensive experiments on Twitter data demonstrate that MentalNet consistently and significantly outperforms the state-of-the-art methods in terms of all the effectiveness metrics. Compared to the baseline methods, MentalNet is able to effectively predict early depression in Twitter users with up to 24% improvement on F1 score. © 2022 IEEE.

Guest Editorial for Selected Papers From BIOKDD 2020

THE 19th International Workshop on Data Mining in Bioinformatics (BIOKDD 2020) was held virtually on August 24, 2020 due to the COVID-19 pandemic. BIOKDD 2020 featured the special theme of "Battling COVID-19" which particularly welcomed paper submissions and invited talks related to COVID-19 research. As a whole-day workshop, altogether 15 submissions were accepted among a total of 35 submissions, and they were divided into 4 sessions: (1) Bioinformatics, (2) Data Curation, (3) Deep Learning with Biomedical Data, and (4) Data Mining & Statistical Methods. There are also 7 invited talks by domain experts. This special section features the extended versions of 6 quality papers presented in BIOKDD 2020.

A phase i does-escalation and expansion study of epidiolex (cannabidiol) in patients with biochemically recurrent prostate cancer

Background: There is a need for a low toxicity option for men with prostate cancer with biochemical recurrence (BCR) following primary curative therapy. Cannabinoids (CBD) have antitumor activity in preclinical studies, but products may vary in activity without clear standardization. As epidiolex is a standardized FDA approved oral CBD solution for treatment of certain types of seizures, we studied epidiolex in patients with BCR of prostate cancer to determine safety and dosing of this therapy to support future studies. Methods: We present an open-label, single center, phase I dose escalation study followed by a dose expansion. Patients with BCR prostate cancer after primary definitive local therapy (prostatectomy +/- salvage radiotherapy or primary definitive radiotherapy) were eligible. Majority of our patients' prostate-specific antigen (PSA) doubling time was ≤ 12 months. All patients were screened for urine tetrahydrocannabinol (THC) prior to enrollment. With use of a Bayesian optimal interval design, patients received escalating doses of epidiolex starting at 600mg daily and up to 800mg daily. All patients were treated for 90 days followed by a 10 day taper. The Primary endpoints were safety and tolerability. Patients were monitored for both acute (30 days) and chronic (90 days) treatment-related toxicities. Secondary endpoints included change in PSA levels and testosterone levels from baseline throughout the treatment period. Results: A total of 21 patients were enrolled but four withdrew from the study (one patient was hospitalized with COVID-19 and three patients requested to stop due to grade 2 adverse events (AEs). There were seven patients included in the dose escalation phase. Four patients received 600mg daily;two of the four in this phase did not finish the first 30 days (one with COVID-19 and one withdrew). The other three patients received 800 mg daily. No dose-limiting toxicities were observed at any dose level so an additional 14 patients were enrolled at the 800mg dose. Treatment-related chronic AEs occurring in >10% of patients were grade 1 or 2 diarrhea (47.6%), grade 1 or 2 nausea (23.8%) and grade 1 or 2 fatigue (19%). The mean PSA at baseline was 2.9 ng/ml. One patient developed oligo-metastasis disease, two patients progressed after the study period, and one patient died from a non-treatment or disease-related cause. Conclusions: Epidiolex at a dose of 800mg daily appears to be safe and tolerable in patients with BCR of prostate cancer, supporting a safe dose for future studies to determine if there is clinical activity to delay development of hormone refractory metastatic disease.

20th International Workshop on Data Mining in Bioinformatics (BIOKDD 2021)

The goal of the 20th International Workshop on Data Mining in Bioinformatics (BIOKDD 2021) is to encourage KDD researchers to tackle the numerous problems and challenges in Bioinformatics using Data Mining technologies. Based on the organizers' expertise and the BIOKDD communities, BIOKDD 2021 features the theme of "Artificial Intelligence in Medicine". This topic focuses on the use of machine learning and data mining techniques for the analysis of large amounts of heterogeneous, complex, biological and medical data, with a particular focus on deep learning methods that have seen rapid advance and wider adoption in Bioinformatics (e.g., DeepVariant, AlphaFold 2). We also particularly welcome COVID-19 related research. The key goal is to accelerate the convergence between Data Mining and Bioinformatics communities to expedite discoveries in basic biology, medicine and healthcare. © 2021 Owner/Author.

Survey results of patients with neuroendocrine cancer to find an overall high satisfaction with telemedicine and identify weaknesses of telemedicine unique to patients with rare cancers

Background: The COVID-19 pandemic has presented significant challenges to healthcare providers;especially in the treatment of patients with cancer. Many centers have delayed in-person visits by expanding the use of telemedicine (TM). The New Orleans Louisiana Neuroendocrine Tumor Specialists (NOLANETS) is a specialty referral center for patients with neuroendocrine tumors (NET), a rare cancer. This study sought to analyze the experience of TM in patients with a rare cancer and compare their experience with general oncology (Gen Onc) patients. Methods: NET patients completed an online survey conducted by the Neuroendocrine Cancer Awareness Network (NCAN), or an identical mailed paper survey conducted by NOLANETS. Data from these patients were pooled. Gen Onc patients completed the identical online survey using REDCap. Multi-disciplinary oncology physicians completed a unique online survey using REDCap. Results: NET patients (n = 247) rated their overall experience of TM as excellent (47%;n = 116) or good (41%;n = 102), and Gen Onc patients (n = 508) rated their experience as excellent, (54.6%;n = 305) and good (35.2%;n = 197);with no statistical difference between the cohorts. However, NET patients were less likely to agree that all their questions were answered than Gen Onc patients (p < 0.001). Factors associated with suboptimal experience for both cohorts included: telephone format and connection issues. Patients who experienced connection issues were less likely to agree that their questions were answered (NET p = 0.004;Gen Onc p < 0.0001) or that they wanted additional virtual visits (NET p = 0.004;Gen Onc p < 0.0001). NET patients reported a significant difference in the travel required to receive inperson care than Gen Onc patients (p < 0.0001) and significant cost savings associated with TM (p = 0.012). Physicians (n = 51) reported that they were able to effectively care for their patients using TM (88%), however there were significant differences when providers were asked if they were able to provide adequate care for follow-up (FU) visits vs new patient visits vs end-of-life visits (FU vs new, p = 0.000;FU vs End of Life, p < 0.0001;New vs End of Life, p = 0.009). Conclusions: While most NET and Gen Onc patients had a positive experience with TM, connection issues, and audio-only platform significantly decreased the overall experience. Importantly, while NET patients reported a significant cost savings, they were less likely to agree that all their questions were answered when compared to Gen Onc patients. And while most physicians agreed that they were able to effectively care for their patients, additional considerations should be made when new patients or end-of-life patients participate in TM. These results suggest that TM may offer new opportunities for rare-cancer patients but also poses unique challenges.

Network-based gene prediction for TCM symptoms

The diagnosis and treatment of traditional Chinese medicine (TCM) are formed based on the differentiation of syndromes and symptoms. Symptom management is always the core task of nursing science. Connotation between TCM symptoms and Modern medicine (MM) symptoms are obvious different, especially tongue and pulse symptoms of TCM. However, the underlying molecular mechanisms of most TCM symptoms remain unclear. Here, we developed a network-based framework to predict candidate genes of TCM symptoms (called PTsGene) and construction a high-quality set of TCM symptom-gene associations. Experimental results indicated that PTsGene performed significantly better than the baseline algorithms. The reliability of the candidate genes of symptoms (containing one of typical symptoms of COVID-19, fever) were validated by the analysis of functional homogeneity, molecular co-expression, and recently published literatures. Finally, a high-quality set of TCM symptom-gene associations is constructed to promote the mechanism developments of TCM symptoms. Prediction and construction for reliable TCM symptom-gene associations are valuable for uncovering the underlying molecular mechanisms of TCM symptoms. Our TCM symptom-gene associations deliver a highly insightful data sources for researchers both from basic and clinical settings of precision healthcare. © 2020 IEEE.

An Evaluation of Neurosurgical Practices During the Coronavirus Disease 2019 Pandemic.

OBJECTIVE: We sought to understand how the coronavirus disease 2019 pandemic has affected the neurosurgical workforce. METHODS: We created a survey consisting of 22 questions to assess the respondent's operative experience, location, type of practice, subspecialty, changes in clinic and operative volumes, changes to staff, and changes to income since the pandemic began. The survey was distributed electronically to neurosurgeons throughout the United States and Puerto Rico. RESULTS: Of the 724 who opened the survey link, 457 completed the survey. The respondents were from throughout the United States and Puerto Rico and represented all practices types and subspecialties. Nearly all respondents reported hospital restrictions on elective surgeries. Most reported a decline in clinic and operative volume. Nearly 70% of respondents saw a decrease in the work hours of their ancillary providers, and almost one half (49.1%) of the respondents had had to downsize their practice staff, office assistants, nurses, schedulers, and other personnel. Overall, 43.6% of survey respondents had experienced a decline in income, and 27.4% expected a decline in income in the upcoming billing cycle. More senior neurosurgeons and those with a private practice, whether solo or as part of a group, were more likely to experience a decline in income as a result of the pandemic compared with their colleagues. CONCLUSION: The coronavirus disease 2019 pandemic will likely have a lasting effect on the practice of medicine. Our survey results have described the early effects on the neurosurgical workforce. Nearly all neurosurgeons experienced a significant decline in clinical volume, which led to many downstream effects. Ultimately, analysis of the effects of such a pervasive pandemic will allow the neurosurgical workforce to be better prepared for similar events in the future.

An Evaluation of Neurosurgical Resident Education and Sentiment During the Coronavirus Disease 2019 Pandemic: A North American Survey.

BACKGROUND: The coronavirus disease 2019 (COVID-19) pandemic has had a tremendous impact on the healthcare system. Owing to restrictions in elective surgery and social distancing guidelines, the training curriculum for neurosurgical trainees has been rapidly evolving. This evolution could have significant long-term effects on the training of neurosurgery residents. The objective of the present study was to assess the effects of COVID-19 on neurosurgical training programs and residents. METHODS: A survey consisting of 31 questions assessing changes to resident clinical and educational workload and their sentiment regarding how these changes might affect their careers was distributed electronically to neurosurgery residents in the United States and Canada. RESULTS: The survey respondents were from 29 states and Canada and were relatively evenly spread across all levels of residency. Nearly 82% reported that the inpatient and outpatient volumes had been either greatly (44.0%) or moderately (37.8%) reduced. Greater than 91% reported that their work responsibilities or access to the hospital had been reduced, with a significant reduction in work hours and a significant increase in resident didactics (P < 0.001). Senior residents expressed concern about their educational experience and their future career prospects as a result of the pandemic. CONCLUSION: Universally, residents have experienced reduced work hours and a reduction in their operative case volumes. Programs have adapted by increasing didactic time and using electronic platforms. It is quite possible that this remarkable period will prompt a critical reappraisal of the pre-COVID-19 adequacy of educational content in our training programs and that the enhanced educational efforts driven by this pandemic could be lasting.