Artificial intelligence-enabled screening strategy for drug repurposing in monoclonal gammopathy of undetermined significance

Monoclonal gammopathy of undetermined significance (MGUS) is a benign hematological condition with the potential to progress to malignant conditions including multiple myeloma and Waldenstrom macroglobulinemia. Medications that modify progression risk have yet to be identified. To investigate, we leveraged machine-learning and electronic health record (EHR) data to screen for drug repurposing candidates. We extracted clinical and laboratory data from a manually curated MGUS database, containing 16,752 MGUS patients diagnosed from January 1, 2000 through December 31, 2021, prospectively maintained at Mayo Clinic. We merged this with comorbidity and medication data from the EHR. Medications were mapped to 21 drug classes of interest. The XGBoost module was then used to train a primary Cox survival model; sensitivity analyses were also performed limiting the study group to those with non-IgM MGUS and those with M-spikes >0.3 g/dl. The impact of explanatory features was quantified as hazard ratios after generating distributions using bootstrapping. Medication data were available for 12,253 patients; those without medications data were excluded. Our model achieved a good fit of the data with inverse probability of censoring weights concordance index of 0.883. The presence of multivitamins, immunosuppression, non-coronary NSAIDS, proton pump inhibitors, vitamin D supplementation, opioids, statins and beta-blockers were associated with significantly lower hazard ratio for MGUS progression in our primary model; multivitamins and non-coronary NSAIDs remained significant across both sensitivity analyses. This work could inform subsequent prospective studies, or similar studies in other disease states.

Blockchain for Electronic Vaccine Certificates: More Cons Than Pros?

Electronic vaccine certificates (EVC) for COVID-19 vaccination are likely to become widespread. Blockchain (BC) is an electronic immutable distributed ledger and is one of the more common proposed EVC platform options. However, the principles of blockchain are not widely understood by public health and medical professionals. We attempt to describe, in an accessible style, how BC works and the potential benefits and drawbacks in its use for EVCs. Our assessment is BC technology is not well suited to be used for EVCs. Overall, blockchain technology is based on two key principles: the use of cryptography, and a distributed immutable ledger in the format of blockchains. While the use of cryptography can provide ease of sharing vaccination records while maintaining privacy, EVCs require some amount of contribution from a centralized authority to confirm vaccine status; this is partly because these authorities are responsible for the distribution and often the administration of the vaccine. Having the data distributed makes the role of a centralized authority less effective. We concluded there are alternative ways to use cryptography outside of a BC that allow a centralized authority to better participate, which seems necessary for an EVC platform to be of practical use.

Assessing the Generalizability of a Clinical Machine Learning Model Across Multiple Emergency Departments

Objective

To assess the generalizability of a clinical machine learning algorithm across multiple emergency departments (EDs).

Patients and Methods

We obtained data on all ED visits at our health care system's largest ED from May 5, 2018, to December 31, 2019. We also obtained data from 3 satellite EDs and 1 distant-hub ED from May 1, 2018, to December 31, 2018. A gradient-boosted machine model was trained on pooled data from the included EDs. To prevent the effect of differing training set sizes, the data were randomly downsampled to match those of our smallest ED. A second model was trained on this downsampled, pooled data. The model's performance was compared using area under the receiver operating characteristic (AUC). Finally, site-specific models were trained and tested across all the sites, and the importance of features was examined to understand the reasons for differing generalizability.

Results

The training data sets contained 1918-64,161 ED visits. The AUC for the pooled model ranged from 0.84 to 0.94 across the sites; the performance decreased slightly when Ns were downsampled to match those of our smallest ED site. When site-specific models were trained and tested across all the sites, the AUCs ranged more widely from 0.71 to 0.93. Within a single ED site, the performance of the 5 site-specific models was most variable for our largest and smallest EDs. Finally, when the importance of features was examined, several features were common to all site-specific models; however, the weight of these features differed.

Conclusion

A machine learning model for predicting hospital admission from the ED will generalize fairly well within the health care system but will still have significant differences in AUC performance across sites because of site-specific factors.

Practical development and operationalization of a 12-hour hospital census prediction algorithm

Hospital census prediction has well-described implications for efficient hospital resource utilization, and recent issues with hospital crowding due to CoVID-19 have emphasized the importance of this task. Our team has been leading an institutional effort to develop machine-learning models that can predict hospital census 12 hours into the future. We describe our efforts at developing accurate empirical models for this task. Ultimately, with limited resources and time, we were able to develop simple yet useful models for 12-hour census prediction and design a dashboard application to display this output to our hospital’s decision-makers. Specifically, we found that linear models with ElasticNet regularization performed well for this task with relative 95% error of +/− 3.4% and that this work could be completed in approximately 7 months.

Public health impact of delaying second dose of BNT162b2 or mRNA-1273 covid-19 vaccine: simulation agent based modeling study

OBJECTIVE

To estimate population health outcomes with delayed second dose versus standard schedule of SARS-CoV-2 mRNA vaccination.

DESIGN

Simulation agent based modeling study.

SETTING

Simulated population based on real world US county.

PARTICIPANTS

The simulation included 100 000 agents, with a representative distribution of demographics and occupations. Networks of contacts were established to simulate potentially infectious interactions though occupation, household, and random interactions.

INTERVENTIONS

Simulation of standard covid-19 vaccination versus delayed second dose vaccination prioritizing the first dose. The simulation runs were replicated 10 times. Sensitivity analyses included first dose vaccine efficacy of 50%, 60%, 70%, 80%, and 90% after day 12 post-vaccination; vaccination rate of 0.1%, 0.3%, and 1% of population per day; assuming the vaccine prevents only symptoms but not asymptomatic spread (that is, non-sterilizing vaccine); and an alternative vaccination strategy that implements delayed second dose for people under 65 years of age, but not until all those above this age have been vaccinated.

MAIN OUTCOME MEASURES

Cumulative covid-19 mortality, cumulative SARS-CoV-2 infections, and cumulative hospital admissions due to covid-19 over 180 days.

RESULTS

Over all simulation replications, the median cumulative mortality per 100 000 for standard dosing versus delayed second dose was 226 v 179, 233 v 207, and 235 v 236 for 90%, 80%, and 70% first dose efficacy, respectively. The delayed second dose strategy was optimal for vaccine efficacies at or above 80% and vaccination rates at or below 0.3% of the population per day, under both sterilizing and non-sterilizing vaccine assumptions, resulting in absolute cumulative mortality reductions between 26 and 47 per 100 000. The delayed second dose strategy for people under 65 performed consistently well under all vaccination rates tested.

CONCLUSIONS

A delayed second dose vaccination strategy, at least for people aged under 65, could result in reduced cumulative mortality under certain conditions.

Four variations of the Mondini inner ear malformations as seen in microdissections

Four variations and degrees of severity of the Mondini malformation were found in the temporal bones from two neonates, one with congenital heart disease and the other with trisomy D, and from one teenager with leukemia: 1) short cochlea and normal vestibular organs; 2) short cochlea and persistent horizontal canal anlage; 3) markedly shortened cochlea with no modiolus, wide internal auditory meatus, and persistent horizontal canal anlage; 4) same as variation 3, but with persistent anlagen in all semicircular canals. Variations 3 and 4 were from the case of trisomy D, in which the left cochlea had a normal hair cell population but few nerve fibers, and the intraganglionic spiral bundle was displaced from Rosenthal's canal to the osseous spiral lamina. The right ear had no cochlear nerve fibers; the organ of Corti was present, but hair cells were unusually small. In the case of trisomy D, both ears showed subtotal loss of vestibular nerve fibers. Although the rudimentary cristae of the right ear had numerous hair cells, the macular hair cells were fewer and malformed. No hydrops was present.

Hereditary deafness with hydrops and anomalous calcium phosphate deposits

The temporal bones from a 58-year-old white woman who had had hereditary congenital deafness were examined with the techniques of microdissection and surface preparations followed by sectioning of the modiolus. There was bilateral, almost total sensorineural degeneration, which also involved the saccule. The degeneration of the distal processes of the cochlear neurons in the osseous spiral lamina was almost complete, whereas numerous ganglion cells and proximal processes remained in the modiolus and the internal auditory canal. Severe cochleo-saccular hydrops was present in the left ear with Reissner's membrane bulging into the horizontal canal. X-ray diffraction and electron probe analysis were used to study the abnormal crystalline deposits in both ears. On the left side the saccular otoconia were composed of calcite, but the utricular macula was covered by a crust of apatite spherulites. More apatite occurred around the maculae and in the scala media. The cupulae were composed of apatite and octacalcium phosphate. On the right side the utricular otoconia were of normal calcite, but there was a deposit of apatite on the macula sacculi. The upper part of the scala media was completely filled by a deposit of apatite and octacalcium phosphate.

Asymptomatic intracochlear neurinoma. A temporal bone report

A small intracochlear neurinoma was found in the temporal bone of a 54-year-old man who had no history of hearing loss or dizziness. The tumor was small, confined to the scala tympani, and did not visibly alter the tissues around it. The neurinoma was derived from the distal processes of the cochlear neuron. Intralabyrinthine tumors can cause auditory and vestibular symptoms and are difficult to diagnose.