Application of artificial intelligence in cataract management: current and future directions

The rise of artificial intelligence (AI) has brought breakthroughs in many areas of medicine. In ophthalmology, AI has delivered robust results in the screening and detection of diabetic retinopathy, age-related macular degeneration, glaucoma, and retinopathy of prematurity. Cataract management is another field that can benefit from greater AI application. Cataract is the leading cause of reversible visual impairment with a rising global clinical burden. Improved diagnosis, monitoring, and surgical management are necessary to address this challenge. In addition, patients in large developing countries often suffer from limited access to tertiary care, a problem further exacerbated by the ongoing COVID-19 pandemic. AI on the other hand, can help transform cataract management by improving automation, efficacy and overcoming geographical barriers. First, AI can be applied as a telediagnostic platform to screen and diagnose patients with cataract using slit-lamp and fundus photographs. This utilizes a deep-learning, convolutional neural network (CNN) to detect and classify referable cataracts appropriately. Second, some of the latest intraocular lens formulas have used AI to enhance prediction accuracy, achieving superior postoperative refractive results compared to traditional formulas. Third, AI can be used to augment cataract surgical skill training by identifying different phases of cataract surgery on video and to optimize operating theater workflows by accurately predicting the duration of surgical procedures. Fourth, some AI CNN models are able to effectively predict the progression of posterior capsule opacification and eventual need for YAG laser capsulotomy. These advances in AI could transform cataract management and enable delivery of efficient ophthalmic services. The key challenges include ethical management of data, ensuring data security and privacy, demonstrating clinically acceptable performance, improving the generalizability of AI models across heterogeneous populations, and improving the trust of end-users.

Clinical and Epidemiological Profile of Patients with Invasive Aspergillosis from a Fourth Level Hospital in Bogota, Colombia: A Retrospective Study

Invasive aspergillosis (IA) is a severe mycosis caused by Aspergillus species. The infection mainly affects immunocompromised patients with a significant clinical burden. This study aimed to determine the clinical and epidemiological characteristics of patients diagnosed with IA in a fourth level hospital in Colombia, as these data are scarce in the country. A retrospective, observational study, from a single center was conducted with 34 male and 32 female patients, between 1 month- and 90-year-old, diagnosed with proven (18.2%), probable (74.2%) and possible (7.6%) IA, during a 21-year period. The most frequent underlying conditions for IA were chemotherapy (39.4%) and corticosteroid use (34.8%). The lung was the most common affected organ (92.4%). Computed tomography (CT) imaging findings were mainly nodules (57.6%) and consolidation (31.8%). A low positive correlation was found between serum galactomannan and hospitalization length. Aspergillus fumigatus prevailed (73.3%) in sputum and bronchoalveolar lavage cultures. Most patients were hospitalized in general wards (63.6%) and treated with voriconazole (80.3%). Mortality rate was 15.2%. Common risk factors for IA were identified in the Colombian cohort, including medications and underlying diseases. However, their frequency differs from other countries, reinforcing the idea that local surveillance is essential and at-risk patients should be carefully monitored.

Hepatitis C Vaccination: Where We Are and Where We Need to Be

The hepatitis C virus (HCV) is a common cause of chronic liver disease and liver cancer worldwide. Despite advances in curative therapies for HCV, the incidence of new infections is not decreasing at the expected rate to hit the World Health Organization (WHO) target for the elimination of HCV by 2030. In fact, there are still more new cases of infection in the United States and worldwide than are being cured. The reasons for the rise in new cases include poor access to care and the opioid epidemic. The clinical burden of HCV requires a multimodal approach to eradicating the infection. Vaccination would be an excellent tool to prevent incidence of new infections; however, the genetic diversity of HCV and its ability to generate quasispecies within an infected host make creating a broadly reactive vaccine difficult. Multiple vaccine candidates have been identified, but to date, there has not been a target that has led to a broadly reactive vaccine, though several of the candidates are promising. Additionally, the virus is very difficult to culture and testing candidates in humans or chimpanzees is ethically challenging. Despite the multiple barriers to creating a vaccine, vaccination still represents an important tool in the fight against HCV.

Reliability and Validity of the Mental Health Quotient (MHQ)

Background: The MHQ is an assessment of mental health and wellbeing that comprehensively covers symptoms across 10 major psychiatric disorders as defined by the DSM-5, in addition to constructs defined by RDoC and positive dimensions of mental function using a novel life-impact scale. An overall measure of mental wellbeing, the Mental Health Quotient or MHQ, is computed based on these elements using a nonlinear transformation of the scale followed by a rescaling. The MHQ has been deployed as part of the Mental Health Million Project as a freely available anonymous online assessment that, on completion, provides a score to the individual that places them on a spectrum from Distressed to Thriving along with a personal report spanning their various dimensions of mental wellbeing with strategies for improvement. Since its launch in April 2020 over 200,000 people have taken the MHQ. Here we provide various demonstrations of the reliability and validity of the MHQ.Objective: This paper outlines the reliability and validity of the Mental Health Quotient (MHQ), including construct validity of the life impact scale, sample and test-retest reliability of the assessment and criterion validation of the MHQ with respect to productivity loss and clinical burden.Methods: To assess sample reliability, random demographically matched samples of 11,033 people were compared from within the same 6-month period. Test retest reliability was determined using the subset of individuals who had taken the assessment twice at least 3 days apart (N=1907). In addition, a subset of respondents (N=4,247 or 7,625) were asked additional questions (along with the standard MHQ questions) on symptom frequency and severity for an example symptom (Feelings of Sadness, Distress or Hopelessness), days of work missed in the past month, and days with reduced productivity. In addition, elements with high negative life impact considered to meet the threshold to be considered a ‘symptom’ were mapped to the criteria for each of 10 major DSM-5 based mental health disorders to calculate the clinical burden (N=174,618).Results: Distinct samples collected during the same period had indistinguishable MHQ distributions and average ratings for each of the 47 elements, demonstrating the reliability of the assessment and MHQ scores were correlated with r=0.84 between retakes. The life impact rating was correlated with both frequency and severity of symptoms and mean values had a clear linear relationship with an R2>0.99. Furthermore, aggregate MHQ scores were systematically related to both productivity and clinical burden. At one end of the scale, those in the Distressed category had an average productivity loss of 15.2±0.5 days per month with 89.08% (8,986/10,087) mapping to 1 or more DSM-5 based clinical disorders. In contrast those at the other end of the scale, in the Thriving category, had an average productivity loss of 1.3±0.1 and 0.00% (1/24,365) had any DSM-5 based clinical disorder.Conclusions: The MHQ is a valid and reliable assessment of mental wellbeing when delivered anonymously online

Uncommon presentation of craniospinal tuberculosis

Tuberculosis (TB) is a bacterial infection with multisystem presentations. Involvement of the central nervous system (CNS) is considered the most lethal form among all types. In addition to possible fatality, CNS TB has serious neurological sequelae. These morbidity issues along with diagnostic challenges doubles the clinical burden. In recent years, there have been improvements in diagnostic sensitivity and specificity due to advances in technology. Herein, we report an atypical case of a patient with TB who presented to our department and discuss the flow of the diagnostic workup.