Cost-effectiveness of Artificial Intelligence for Proximal Caries Detection

Artificial intelligence (AI) can assist dentists in image assessment, for example, caries detection. The wider health and cost impact of employing AI for dental diagnostics has not yet been evaluated. We compared the cost-effectiveness of proximal caries detection on bitewing radiographs with versus without AI. U-Net, a fully convolutional neural network, had been trained, validated, and tested on 3,293, 252, and 141 bitewing radiographs, respectively, on which 4 experienced dentists had marked carious lesions (reference test). Lesions were stratified for initial lesions (E1/E2/D1, presumed noncavitated, receiving caries infiltration if detected) and advanced lesions (D2/D3, presumed cavitated, receiving restorative care if detected). A Markov model was used to simulate the consequences of true- and false-positive and true- and false-negative detections, as well as the subsequent decisions over the lifetime of patients. A German mixed-payers perspective was adopted. Our health outcome was tooth retention years. Costs were measured in 2020 euro. Monte-Carlo microsimulations and univariate and probabilistic sensitivity analyses were conducted. The incremental cost-effectiveness ratio (ICER) and the cost-effectiveness acceptability at different willingness-to-pay thresholds were quantified. AI showed an accuracy of 0.80; dentists’ mean accuracy was significantly lower at 0.71 (minimum–maximum: 0.61–0.78, P < 0.05). AI was significantly more sensitive than dentists (0.75 vs. 0.36 [0.19–0.65]; P = 0.006), while its specificity was not significantly lower (0.83 vs. 0.91 [0.69–0.98]; P > 0.05). In the base-case scenario, AI was more effective (tooth retention for a mean 64 [2.5%–97.5%: 61–65] y) and less costly (298 [244–367] euro) than assessment without AI (62 [59–64] y; 322 [257–394] euro). The ICER was −13.9 euro/y (i.e., AI saved money at higher effectiveness). In the majority (>77%) of all cases, AI was less costly and more effective. Applying AI for caries detection is likely to be cost-effective, mainly as fewer lesions remain undetected. Notably, this cost-effectiveness requires dentists to manage detected early lesions nonrestoratively.

NPM1, FLT3 and CEBPA mutations in pediatric patients with AML from Argentina: incidence and prognostic value

Mutations in NPM1, FLT3 and CEBPA genes are found in 25-35 % of adult acute myeloblastic leukemia (AML) cases and correlate with prognosis. To date, there have been no reports about these mutations in pediatric AML from Argentina. The aims of the present study were to describe the incidence of NPM1, FLT3 and CEBPA mutations and to analyze their prognostic impact in this population. The incidences of these mutations within a population of 216 pediatric AML cases were: NPM1-mutated 4.2 %, CEBPA-mutated 1.9 %, FLT3-ITD 10.2 % and FLT3-TKD 7.9 %. Among 33 patients with normal karyotype, we found significantly higher frequencies for NPM1-mutated 24.2 % and CEBPA-mutated 12.1 %. Overall survival (pOS) for the 163 eligible non-acute promyelocytic leukemia cases was 46.2 ± 4.3 %, while leukemia-free survival probability was 51.0 ± 4.4 % (n = 135). The NPM1-mutated/FLT3-ITD-negative genotype showed better outcome than any other combined NPM1/FLT3 genotype; this difference was statistically significant within the group of high-risk patients (pOS ± SE 83.3 ± 15.2 % versus 33.1 ± 4.7 %; p = 0.0251). This is the first report of the frequencies of these mutations in Argentina. Despite the limited number of patients, a favorable prognosis of AML with genotype NPM1-mutated/FLT3-ITD-negative was confirmed. This is especially relevant within the high-risk group of patients, as it may contribute to the detection of patients with better prognosis, and thus avoid unnecessary treatment intensification.

Good outcome of children with acute myeloid leukemia and t(8;21)(q22;q22), even when associated with granulocytic sarcoma: a report from a single institution in Argentina

BACKGROUND

The association between t(8;21) and granulocytic sarcoma (GS) is well known, but to the authors' knowledge the prognostic significance of GS in these patients has not been defined clearly.

METHODS

Between January 1990 and July 1999 174 children with acute myeloid leukemia were admitted to the study institution. Translocation (8;21) was identified in 20 patients (11.5%). Eighteen patients were evaluable for the current study and 8 presented with GS at the time of diagnosis (GS+).

RESULTS

The authors defined two groups of patients: those who were GS+ and those who were GS-. One patient in the GS+ group and two patients in the GS- group died during the induction phase of the study. Complete remission was achieved in seven patients in the GS+ group and eight patients in the GS- group. Two patients developed a recurrence in the GS+ group as did one patient in the GS- group. The event free-survival probability (the standard error) was 58% (18%) in the GS+ group and 70% (14%) in the GS- group. Localization of GS was in only one site in seven patients and at multiple sites in one patient. Patients with an epidural mass received local radiotherapy (one patient) or surgery (two patients). Two of these patients developed paraplegia as sequelae: one patient after surgery and one patient after radiotherapy. One patient with orbital GS received local radiotherapy because of progressive proptosis. The remaining four patients had a complete resolution of the GS with chemotherapy only.

CONCLUSIONS

In the current study of patients with t(8;21)(q22;q22), the presence of granulocytic sarcoma was not found to be an adverse prognostic factor. However, careful attention should be paid, especially to patients with an epidural site, to avoid sequelae. Chemotherapy appears to be the optimum treatment for these children.

[Translocation t(9;11) in acute childhood lymphoblastic leukemia]

We report a case of a de novo acute lymphoblastic leukaemia (ALL) with t(9;11) (p21;q23) and a novel translocation t(2;8) (p15;q24). The former is characteristic of acute nonlymphoblastic leukaemia (ANLL) and has rarely been detected in ALL. The blasts showed L2 morphology by the French American British (FAB) classification and pre B ALL immunophenotype.